Search

The enormous demand for self-powered sensors in industry 4.0 has drawn a lot of research interest in these vital devices that do not need external power sources. This study presents the development of a self-powered paper-based humidity sensor that uses copper and aluminium as electrodes and a composite of MgCl 2 and carbon nanotubes (CNTs) as sensing material. The results demonstrate a significant improvement in humidity sensing performance as a result of the addition of CNTs and MgCl 2. In particular, the self-powered paper-based humidity sensor with MgCl 2 /CNTs composites has impressive repeatability, broad detection ranging from 11 % to 97 % relative humidity, and quick response and recovery times of 10 and 46 s, respectively. Furthermore, the self-powered paper-based humidity sensor can generate a maximum voltage of 1.07 V and a maximum power of approximately 1.984 µW. Furthermore, connecting the paper-based humidity sensors in series increases their voltage output, making them useful for charging capacitors and lighting up to six LEDs. This endeavour offers a straightforward, cost-effective, and highly responsive self-powered paper-based humidity sensor that is ideal for high-performance applications in humidity sensing within power generation fields. [Display omitted] • This study proposed a paper-based humidity sensor with MgCl 2 /CNTs composites. • The developed sensor has quick response and recovery times of 10 and 46 s. • The sensor exhibited impressive repeatability and a broad detection ranging of 11–97 % RH. • The sensor can generate a maximum voltage of 1.07 V and a maximum power of 1.984 µW. [ABSTRACT FROM AUTHOR]

• Introduced SWM 4.0 by considering Industry 4.0 technologies in waste management. • Reviewed I4.0 role in waste types, processes, and strategies of waste management. • Developed SWM 4.0 framework through smart factories, cities, businesses, and people. Smart Waste Management (SWM) discusses the waste management process for different types of waste while introducing an intelligent approach to controlling the amount of waste. This paper introduces SWM4.0, which applies Industry4.0 (I4.0) technologies in various related events. First, the paper presents a systematic literature review on the role of I4.0 technologies in SWM activities regarding waste types, waste management processes, and 5R strategies. Then, existing solutions supporting SWM4.0 are extracted to develop a framework for exploring the use of I4.0 technologies. This framework includes sharing the four main pillars that contribute to the success of SWM4.0, namely smart people, smart cities, smart enterprises, and smart factories. Furthermore, this review suggests the possibility of unifying and extending existing solutions and identifying the necessary links and interfaces for researchers. For managerial implications, the framework identifies future strategies to fulfill specific SWM tasks and to foster new technological solutions for future research. [ABSTRACT FROM AUTHOR]

Safety instrumented systems (SISs) are installed on process plants to protect against undesired events like e.g., gas leakage and overpressure. A SIS has reliability requirements that are determined during design, and conformance to these requirements should be verified during operation. It is therefore important that all SIS failures are recorded and classified according to their impact on the SIS reliability. Failures of SIS equipment classified as dangerous undetected are of particular interest because they are dormant (undetected) and will prevent the execution of the safety function (dangerous). Analysis of the failure mode and detection method is essential when deciding if a failure is dangerous and undetected. Such information is often provided as unstructured text in notifications registered into the maintenance management system. Therefore, the work of classifying failures requires considerable manual effort in reading and analyzing the texts. Approaches within natural language processing, like technical language processing, have the potential to be deployed more actively for this purpose. However, successful adoption relies on groundwork where classification rules are derived from international standards and commonly agreed industry practice. This paper presents a semi-automated process that incorporates classification rules and gives examples that indicate some of the capabilities of technical language processing for failure classification. The paper also elaborates on how the work relates to Industry 4.0 in creating digital representations to monitor the performance of safety instrumented systems. This work has been carried out as part of the APOS project (Automated process for follow-up of safety instrumented systems). The APOS project has developed knowledge and specifications that simplify and automate the design and operation of safety equipment and investigated how the failure classification process can be made more efficient. [ABSTRACT FROM AUTHOR]

A cyber-physical system (CPS) is an interconnected physical system that can be monitored, controlled, and operated remotely. A systems-based analysis of CPS is critical for enhancing operational safety and security. Such analysis is particularly important in light of the evolving Fourth Industrial Revolution (Industry 4.0) which is largely driven by CPS, Internet of Things (IoT), algorithmic systems, automation, and smart manufacturing. As a result of industries' and societies' growing dependence on CPSs, their safe and secure applications need to be scrutinized to avoid any threats or harm to processes and human lives. In order to achieve this target, the current work analyzes the literature to investigate challenges and opportunities present in the CPSs. The analysis attempts to answer the following Research Questions (RQs): (RQ1) What are the prominent trends in the field of safety and security of CPSs? (RQ2) What are the opportunities in Industry 4.0 technologies related to safety? (RQ3) What characteristics of CPSs are likely to cause safety and security issues? (RQ4) What are the emerging safety and security issues introduced by CPSs? (RQ5) How were these issues addressed in the literature? CPSs can address some traditional safety issues due to characteristics like high efficiency and control. However, a CPS is challenged by heterogeneity, dependencies, complexity, unattended nature, increased machine intelligence, autonomous reconfiguration, and uncertainties. Safety and security challenges include opaque system failure, complex socio-technical system, human-machine interface, cyber-physical attacks, unsecured remote configuration, lack of standards, and resilience. The paper is structured under the following key headings: bibliometric results, opportunities from Industry 4.0 technologies, issues introduced by Industry 4.0 technologies, literature proposed solutions, and research challenges. Based on the assessment of about 900 relevant publications extracted from two databases (Web of Science (WoS) Core Collection and Engineering village (EV)), the documents were categorized into eight major divisions: (i) Safety Opportunities, (ii) Hazardous Characteristics, (iii) Fault Occurrence, (iv) Cyber-physical attacks, (v) Human factors, (vi) occupational Health and safety, (vii) standards, and (viii) Reliability and resiliency. Proactive strategies were classified under four options: identification, evaluation, prevention, and management. The paper also raises some research needs and unanswered questions that require further analysis to address how security and safety mechanisms can introduce more complexity in the system that can lead to new risks. The paper concludes by emphasizing digital process safety as part of the engineering curriculum to address the process industry's need for digital solutions and to make process safety learning a conscious choice. [ABSTRACT FROM AUTHOR]

Meat, as protein-rich food, provides essential nutrition to humans. Meat consumption is expected to increase by 15% over the next decade, requiring the meat industry to boost its capacity. However, the meat cutting industry's harsh working environment and long-term heavy workload result in a labor shortage. Low-margin and low capacity require innovative processing methods. Hence, some novel automation methods are urgently demanded to meet these challenges. Accompanied by the development of Industry 4.0, robotization and intelligent systems are progressively applied in the meat cutting industry, which can provide a flexible, adaptive, and sustainable processing approach. The paper selected 50 papers using the systematic literature review method. This paper provides an overview of the current research and commercial applications of cutting robotization from livestock, poultry, and fish in the meat industry. Additionally, intelligent sensing technologies, advanced cutting techniques, and a novel manufacturing concept called the meat factory cell, are emphasized to promote efficiency, scalability, and modularization. Finally, we discuss the potential applications of digital technologies in the meat cutting industry and the focal points of future research aiming to promote cutting robotization. The meat cutting process can be highly robotized by integrating dexterous cutting robots, advanced sensing techniques, and digital systems, driving the transformation from manual labor to robotic, efficient, and intelligent manufacturing. Consequently, robotization and intelligent digital systems can provide a brand-new manufacturing method to the meat cutting industry and advance the Meat factory 4.0. [Display omitted] • Advanced perception techniques assist robots to perform adaptive cutting. • Intelligent robotic systems in the meat cutting industry are reviewed. • Commercial applications regarding meat cutting robotization are presented. • Advanced cutting techniques are highlighted to promote cutting performance. • Potential applications of advanced digital systems are provided for sustainability. [ABSTRACT FROM AUTHOR]

The evaluation of the volumetric accuracy of a machine tool is an open challenge in the industry, and a wide variety of technical solutions are available in the market and at research level. All solutions have advantages and disadvantages concerning which errors can be measured, the achievable uncertainty, the ease of implementation, possibility of machine integration and automation, the equipment cost and the machine occupation time, and it is not always straightforward which option to choose for each application. The need to ensure accuracy during the whole lifetime of the machine and the availability of monitoring systems developed following the Industry 4.0 trend are pushing the development of measurement systems that can be integrated in the machine to perform semi-automatic verification procedures that can be performed frequently by the machine user to monitor the condition of the machine. Calibrated artefact based calibration and verification solutions have an advantage in this field over laser based solutions in terms of cost and feasibility of machine integration, but they need to be optimized for each machine and customer requirements to achieve the required calibration uncertainty and minimize machine occupation time. This paper introduces a digital twin-based methodology to simulate all relevant effects in an artefact-based machine tool calibration procedure, from the machine itself with its expected error ranges, to the artefact geometry and uncertainty, artefact positions in the workspace, probe uncertainty, compensation model, etc. By parameterizing all relevant variables in the design of the calibration procedure, this simulation methodology can be used to analyse the effect of each design variable on the error mapping uncertainty, which is of great help in adapting the procedure to each specific machine and user requirements. The simulation methodology and the analysis possibilities are illustrated by applying it on a 3-axis milling machine tool. • Artefact-based volumetric error mapping process is modelled for optimization. • Digital twin of the machine simulates machine geometric and elastic errors. • Error mapping uncertainty can be estimated before experimental implementation. • Artefact design and measurement strategy can be optimized based on simulation. [ABSTRACT FROM AUTHOR]

This comprehensive review paper investigates the possibilities and prospects of operation and maintenance (O&M) technologies in small modular reactors (SMRs). The necessity for innovation within the regulatory restrictions is a primary concern. Artificial intelligence, digital twins, and robotics are emphasized as promising technologies for autonomous operation, real-time monitoring, predictive maintenance, and maintenance automation, respectively. The paper argues that these technologies can improve safety, increase economic efficiency, and enhance the competitiveness of SMRs. In addition, the paper proposes a methodology for performance verification that employs separate effect tests (SETs) and integral effect tests (IETs) facilities. A realistic roadmap is also provided, suggesting a six-year timeframe for the implementation and licensing of these technologies. By combining innovative technologies and regulatory considerations, the study proposes a future direction for SMRs' operation and maintenance. The final objective of this work is to provide insights into the current status of SMRs' O&M technologies, to suggest potential paths forward, and to make SMRs a more competitive choice in the global energy market. The conclusions drawn from this review can serve as a valuable guide for researchers, plant operators, and policymakers in the nuclear energy sector. • There is an economic issue with small modular reactors (SMRs). • Currently, reducing operation and maintenance (O&M) costs is essential. • A comprehensive review has been conducted regarding regulations and technology. • Presents a realistically achievable cost reduction strategy for SMRs. [ABSTRACT FROM AUTHOR]

Data infrastructures are expanding rapidly across African societies, renewing the promise of modernisation, and providing a massive data resource to the dominant tech powers of the world. Google's private undersea cable, named Equiano, landed in west Africa with the intention of igniting data services, smart environments, investment opportunities and jobs. Non-governmental and multilateral agencies are busy supporting African governments in building regulatory frameworks that aim to 'ready' countries for the 4th industrial revolution. Young Africans labour in remodelled shipping containers to annotate data and train algorithms. While future promises pan out in wide-angled, utopian visions, this paper sets out an approach to understand African contexts as sites of heterogeneous experience of data infrastructures that are historically and politically contingent. The paper explores the spatial politics of extraction, surveillance, and exploitation in three examples of the Equiano pipeline, the Artificial Intelligence (AI) Readiness Index, and the AI annotative labour force. We challenge the homogenising discourses of global tech companies and transnational governance institutions in accounting for the geographical histories of colonialism and its afterlives in African societies. We further call for empirical studies that examine the granular multiplicities of data, providing nuanced understandings of AI in and from Africa. [ABSTRACT FROM AUTHOR]

• Focus on new digital technologies: very uneven diffusion among Italian firms displaying different adoption behaviours. • Analysis of the technology adoption choices made by individual firms exploring the nexus between technology, skills and the organisation of work. • Application of probit and zero inflated poisson models to estimate the probability of introducing at least one technology and the total number of new digital technologies. • In continuity with previous studies of ICTs: strong complementarities between skills and new technologies. • Results point to the importance of knowledge accumulation embodied in firm employees and techno-organizational capabilities of firms. New digital technologies are shaping the transformation of production activities. This process of change is characterised by growing digitization, inter-connectivity and automation. The diffusion of new technologies is, however, very uneven, and firms display different adoption behaviours. By using data on a representative sample of Italian firms, we explore the patterns and determinants of new digital technology adoption. We build our theoretical framework on the nexus between technology, skills and the organisation of work. We then provide novel econometric evidence on the positive effects of education and training. Among the notable results of the paper, labour flexibility does not seem to favour new technology adoption, whereas second-level collective bargaining plays a positive role in the process. Results also show heterogeneous effects between large vs. small and medium-size firms, and between manufacturing and service sectors. [ABSTRACT FROM AUTHOR]

This paper presents a framework of employee skills and competencies useful for developing occupational profiles for employees of companies transitioning towards Industry 4.0. The paper consists of a discussion of the theoretical and practical parts of case studies. The theoretical portion was created on the basis of a review of scientific literature and research studies regarding the competencies and skills of employees in the ongoing fourth industrial revolution. This part focuses on the skills profile of an Industry 4.0 employee and an Operator 4.0 (O4.0) from a creativity and innovativeness point of view. The link between the theoretical part and the case study analysis was a general framework for building the competencies and skills of the steelworker in the emerging fourth industrial revolution. The case study analysis covered the framework of competencies and skills of a metallurgist in smart manufacturing built into the organization of steel mills. Recruitment offers of a steel company implementing smart manufacturing (SM) projects and educational programmes of technical universities in the field of metallurgy were analysed. The aim of the study was to develop a framework for the profile of an employee working in an innovative company transforming to I4.0. The publication posed the following research questions (purposes/hypotheses): P1. To what extent do Polish companies in the metallurgical sector pay attention to creativity and innovation issues when looking for employees? P2. To what extent do the profile (portfolio) of metallurgy graduates of Polish technical universities turn their attention to the issues related to creativity and innovation? [ABSTRACT FROM AUTHOR]

The industrial sector is nowadays experiencing a digital transformation motivated by the Industry 4.0 paradigm. Concepts such as data-driven models, Artificial Neural Networks (ANNs), and Transfer Learning (TL) are part of the current vocabulary in the industrial management and control topics. For that reason, in this paper the application of TL techniques is proposed to derive new ANN-based control structures from pre-existing ones. Notice that if an ANN-based controller is transferred into a new industrial environment, its appropriate behaviour must be ensured, and what it is more important, this must be known a priori. Nevertheless, TL techniques do not always ensure this. That is why the Transfer Suitability Metric (TSM) is proposed here. Determining the similarity among environments, this metric tells if the controller can be transferred, transferred with certain limitations, or if it cannot be transferred at all. Here, the metric is applied over a Wastewater Treatment Plant (WWTP). The objective is to derive the control structure of one control loop, let us say the Dissolved Oxygen (DO), and then transfer it into another basic control loop in a WWTP, the Nitrate–nitrogen (NO), and vice-versa. Results show that with the help of the TSM, an improvement around a 68.54% and 80.53% in the Integrated Absolute Error (IAE) and the Integrated Squared Error (ISE) is obtained in the NO management, respectively. Moreover, a simplification and speed-up of the controller design process is achieved. • Reduce the complexity and speed-up the design process of ANN-based controllers. • Transfer ANN-based structures between industrial environments. • Measure the transfer suitability of an ANN-based controller. • Measure the transfer suitability by means of the Transfer Suitability Metric (TSM). [ABSTRACT FROM AUTHOR]

This paper delves into the integration of Industry 4.0 technologies in the manufacturing sector, providing a framework tailored for adoption in India, a rapidly advancing digital economy. The current literature does not go into detail on industry 4.0 technology in the context of agile manufacturing. Addressing this critical gap in the literature, we identify 15 criteria across six categories, leveraging the entropy method to compute their weights. We prioritize Industry 4.0 technologies in the context of agile manufacturing using a comprehensive analysis that employs the TOPSIS and Fuzzy DEMATEL methodologies. Results indicate that cybersecurity, Cloud, and the Internet of Things (IoT) are the most commonly used technologies in agile manufacturing. The fuzzy DEMATEL-based framework identifies cybersecurity, Big data, Cloud, simulation, augmented reality, and IoT as 'cause' technologies, while additive manufacturing, robotics, mobile devices, and systems integration are identified as 'effect' technologies. The paper proposes practical strategies for managers in India to facilitate the adoption of Industry 4.0 technologies, thereby enhancing firms' agility in the digital age. By highlighting the specific technologies critical to agile manufacturing, our study not only addresses a notable gap in the literature but also provides a roadmap for their practical implementation, empowering businesses to thrive in an increasingly digitalized landscape. [ABSTRACT FROM AUTHOR]

The Industry 4.0 paradigm represents the fourth industrial revolution, embodied by the marriage between information and communication technologies and manufacturing. Assessment campaigns are conducted to examine the status of deployment of that paradigm, mostly through self-assessment questionnaires. Each campaign is typically limited in scope, involving just a group of companies located in a few countries at most. Such limitation does not allow an overall view of Industry 4.0's diffusion. In this paper, we offer that panoramic view through a systematic literature review. The number of papers devoted to Industry 4.0 assessment grows steadily. However, many papers do not provide essential information about the assessment campaigns they report, e.g., not detailing the number, type, or location of companies involved and the questionnaire employed. We observe a large diffusion in Europe and Asia but not in the U.S., with the Top 5 countries being Malaysia, Poland, Italy, Germany and Slovakia. The campaigns uniformly cover small, medium, and large companies but not all industrial sectors. The choice of questionnaires is extremely varied, with no standard emerging. [ABSTRACT FROM AUTHOR]

For the past decade, Industry 4.0 has become the basis for building competitive advantage for business operations. The key technologies of Industry 4.0 are implemented in enterprises of various industries. This paper focuses on presenting the results of research on the influence of the Industry 4.0 concept on the operations of enterprises that are implementing smart manufacturing (SM) projects. The paper analyses the following areas of influence of projects on the enterprises' operations: productivity, agility and speed, quality, competitiveness and enterprise value, profitability, staff reduction, delivery improvements, vertical and horizontal integration, resource savings, reduction of operating costs, technology adaptability and quality of machine operations. The paper belongs to the research paper category. The research tool was a questionnaire. The research was carried out in the segment of steel enterprises in Poland. The results of the presented research belong to pilot research of a segment of steel industry in Poland. The main conclusion of the study is that implementation of Industry 4.0 in the Polish steel sector had a positive influence on many factors strictly connected with the innovativeness of the company. Especially, the implementation of this conception in the steel sector leads to an increase in the quality of the product and the possibility to achieve a good level of customization of the product. Those factors are very important for the steel sector potential to succeed on the competitive market. The individual SM projects that were evaluated were a form of case study. The participants of the research were employees in managerial positions and operating technological installations in steel sector enterprises. In the opinion of the surveyed (79 people), depending on the type and scope of changes implemented in the company in the direction of Industry 4.0, decision-makers expect a higher quality of processes and products, the ability to meet customer requirements—the direction of the personalization of products and services, agility and flexibility of performed operations with the use of smart technology and accuracy and precision of performance higher than in the case of manual human activities. [ABSTRACT FROM AUTHOR]

Rapid advances in Industry 4.0 have the potential to transform production planning and control (PPC) through the emerging concept of smart PPC. This paper provides a visionary perspective by addressing the gap in research on how the characteristics of a company's planning environment impact on the need for, and potential benefit of, smart PPC. The paper posits that the potential of smart PPC to improve PPC performance increases with the complexity of the planning environment. A set of propositions is developed for how 12 product, market, and process variables impact on the need for smart PPC. These are operationalized into a conceptual framework that can be used as a tool by practitioners and academics to assess a company's need for smart PPC. A case study from the food sector illustrates the applicability of the framework and describes three potential applications for how four elements of smart PPC (real-time data management, dynamic production planning and re-planning, autonomous production control, and continuous learning) can be used to address key PPC challenges and open new opportunities for improving PPC. Future research should strengthen the validity and applicability of the proposed framework through additional cases across industrial sectors and carry out case studies, surveys, and structural equation modeling to investigate the specific relationship between planning environment characteristics, smart technologies, and the elements of smart PPC. [ABSTRACT FROM AUTHOR]

Thermal error compensation is one of the most research-oriented topics in manufacturing with rising importance in the industry. This paper presents an innovative Industry 4.0 application of thermal error compensation for precision engineering. A federated learning-based thermal error compensation approach running in the cloud is applied to two machine tools, one located at ETH Zürich, and another one at TU Wien. Although environmental conditions and thermal error behaviour of both machines differ, the implemented knowledge transfer across machines is a viable compensation strategy, albeit with limited precision. A detailed comparison of the two machines of the same type under the same load conditions shows foreseeable similarities in behaviour, but also clear differences due to the different configurations and lifetime status. The cloud-based compensation reduced the crucial thermal errors in the best case of both machine tools by more than 80% under critical conditions. • A new cloud-based thermal error compensation approach is introduced. • Federated learning in terms of cloud and edge computing for reaching a high level of safety and security is presented. • Detailed analysis of the same type of machine tool with different wear and slightly different configurations. • The transferability of the model calibration period (learning phase) is reached by model transfer (transfer learning). • Compensation results already reduce the thermal error by up to 80 %. [ABSTRACT FROM AUTHOR]

Detecting the anomalies in a large amounts of high-dimensional data has been a challenging task. In the Industry 4.0 environment, large-scale high-dimensional monitoring data features the complex pattern of high level semantics. In order to provide enterprise-wide monitoring solutions, it is necessary to identify the high-level semantic patterns of the anomalies in these data without splitting them. Existing end-to-end deep neural networks for time series are capable of recognizing the high-level semantics in natural language or speech signals, but they are barely applied in real-time anomaly detection of industrial data because of the large time costs. In this paper, we leverage the self-supervised contrastive learning methodology and propose a Composite Semantic Augmentation Encoder (CSAE) to provide an appropriate representation of industrial data and implement quick detection of anomalies in industrial application environments. CSAE is a non-sequential deep neural network with two augmentation layers and a mandatory layer. The two layers of data-augmentation are built to expand the size of samples of both low-level semantic anomalies and high-level semantic anomalies, which enables CSAE to discover diverse anomalies and improves its accuracy of high-level semantic pattern recognition. The mandatory layer is built to compress and reserve the temporal information in the industrial data to accelerate the anomaly detection. Therefore, as a non-sequential contrastive learning model, CSAE has faster training convergence than the usual sequence models. The experiment results have verified that CSAE can achieve higher prediction accuracy with less time consumption than existing machine learning models in the tasks of high dimensional anomaly pattern detection. [ABSTRACT FROM AUTHOR]

Introducing Artificial Intelligence (AI) tools is one of the development trends in complex industrial systems in the industry 4.0 environment. Unique challenges in system operations need to be handled by effective operation support systems. The knowledge-based operation support systems are developing rapidly in recent years. The paper aims at highlighting the concerns of knowledge acquisition and representation in one of the knowledge-based methodologies, the Multilevel Flow Modelling (MFM). A procedure of knowledge acquisition and representation for building MFM models is proposed to aim at improving the overall model quality and consistency. An interface linking systems' instrumentations to MFM functions are introduced. The new reasoning engine is used for MFM based real-time cause-consequence reasoning about dynamic plant situations. The model verification and validation, and the model performance evaluation analysis method are proposed. This paper also provides case studies that illustrate the effectiveness of intelligent operation support by applying MFM to an off-shore water injection system. It demonstrates that the procedure of knowledge acquisition and representation can facilitate the model builders, and ensure the quality of the models used for operation support. [ABSTRACT FROM AUTHOR]

• First survey of relevant research activities on Digital Calibration Certificate-DCC. • A thorough analysis of both the calibration process and the calibration certificate. • Modeling the calibration process, the calibration certificate life-cycle. • Identifying Calibration use-cases and stakeholders. • Advantages and disadvantages of various potential DCC formats. Calibration Certificates (CC) are essential for maintaining the accuracy of measurement instruments, which in turn are necessary to maintain the quality of products and services. Such certificates are mainly used in legal metrology for quality audits, accreditation and examination processes; and also in the operational metrology to adjust measurement results according to device uncertainty. Paper-based CC (PCC) or a digital copy of the paper format has been successfully used for this purpose for many decades. However, the PCC starts to fail short with the emergence of new technologies and applications that require automated creation, processing and updates of the calibration certificates. The last years have witnessed an intense effort on digital transformation in metrology and especially developing Digital Calibration Certificates (DCC). Until recently, we noticed the lack of agreement on the nature and the usage of such important new metrology artifacts as well as some repetition in the work by different researchers. To help reaching a minimum consensus on the subject, we present in this paper, a thorough analysis of the calibration certificate and the calibration process. Besides that, we aim by this work to provide an overview of the carried research on that point to help peer researchers to view the big picture and to avoid wasting their efforts in repeating same work on same ideas. Consequently, they can recognize the peer researchers and organizations working on the same topics, find available resources, identify research gaps and identify the best potential directions of their efforts as well. Finally, our paper aims also to establish a bridge between the metrological concepts and information technology concepts such that more computer science researchers can be involved in solving the problem. [ABSTRACT FROM AUTHOR]

This perspective paper features the process intensification (PI) application for advanced distillation-based processes. Starting with the historical background of generic PI, we subsequently narrow down the discussion to extractive distillation (ED), reactive distillation (RD), and hybrid reactive-extractive distillation (RED). We categorize the existing PI techniques onto internal and external intensification, where the former does not involve altering the distillation configuration while the latter does. Instead of deliberating the technical aspects, we explicitly highlight the contribution of PI applied to ED, RD, and RED towards societal impact covering energy, economic, environmental, control, and safety perspectives. The future perspectives of PI are discussed in the last section, covering the development of hybrid PI technologies, exploring the energy efficiency of different PI configurations, prioritizing PI beyond energy by considering some other sustainability aspects, and linking PI with the ever-increasing Industry 4.0 applications. • Historical application of PI of conventional distillation. • Extension of PI to advanced distillation processes covering ED, RD, RED. • Categorization of internal and external PI techniques. • Contribution of PI to sustainability and societal impact. • Future perspectives of PI applied to ED, RD, and RED. [ABSTRACT FROM AUTHOR]

With the advent of industry 4.0, many traditional industries are moving toward automation, intelligence, and large-scale. The continuous expansion of production scale also means that the structure of industrial processes and the interactions between subsystems are becoming increas- ingly complex, which also introduced potential safety risks into the actual production. Due to the complexity and danger of the production process, the process safety of the modern blast furnace (BF) ironmaking process is a prominent problem. In this paper, a novel fault detection and di- agnosis (FDD) framework is proposed, which can detect the abnormality and infer the root cause with no need of building an accurate mechanism model as the traditional methods. After a fault is detected, to better learn fault propagation mechanisms of the BF ironmaking process, a process knowledge model was proposed and integrated with the data-driven approaches for fault diagnosis. Then, to discover the causalities matrix of the faulty data generating procedure, a novel root cause analysis method based on Graph Neural Networks (GNN) was developed. Moreover, to accurately describe the causal interactions of faulty variables and solve the problem of the redundant edges in the causal discovery, the process knowledge constraint item was added to the GNN model to guarantee the discovered causal graph matches with the practical domain knowledge to strengthen its application in the practical industry. The experimental results on real BF data set and a bench- mark data set (The RT 580 data set) demonstrate that our algorithm not only obtains a significant improvement over other methods but also has a favorable application in the industrial process. [ABSTRACT FROM AUTHOR]

Under the promotion of sustainable development goals, cleaner production (CP) has become an important strategy for energy-intensive manufacturing industries to maintain their competitiveness. Studies have shown that the implementation of Industry 4.0 (I4.0) can effectively promote the CP process in manufacturing. However, existing studies often focus on specific scenarios, limiting a comprehensive assessment of the industry's overall status. This paper aims to provide a comprehensive overview of the main research areas of I4.0 and its key impacts on CP by employing systematic mapping studies. By reviewing 121 studies retrieved from the Web of Science, a hierarchical analysis framework centered on the product life cycle (PLC) has been introduced. This framework provides a holistic analysis of sustainable intelligent manufacturing, summarizing the application of I4.0 and its impact on CP across the PLC stages. The main findings reveal a growing focus on I4.0 and CP, with the manufacturing and maintenance stages of the PLC being primary research scenarios. Moreover, attention should be directed towards integrating clean technologies, bolstering industrial data security, fostering circular economy practices, and exploring emerging fields like Industry 5.0. Moreover, to better explain the impact of this study, management implications are also provided from the three dimensions of theory, practice, and policy. These viewpoints and conclusions are of great significance for guiding future research and practical applications. • A comprehensive review of Industry 4.0 and cleaner production is conducted. • Systematic mapping and bibliometric methods are employed. • A hierarchical framework based on product life cycle is proposed. • The current challenges and future prospects are discussed. • Management implications from theory, practice, and policy are provided. [ABSTRACT FROM AUTHOR]

Additive manufacturing in construction has witnessed exponential growth over the recent years. In this paper, advancements in 3D Concrete Printing (3DCP) in additive construction are explored. The authors synthesize the states of research and practice of 3DCP technology for construction through an extensive examination of 137 projects and various publications. Insights are provided into the key factors influencing 3DCP structural performance. The technology is shown to be advantageous, although with varying benefits observed in different cases, including but not limited to reduced cost, labor requirements, material, and construction time. Nevertheless, challenges, such as limited control over the quality, unexplored long-term performance, being counter-cost-effective in certain circumstances, manual intervention during printing, and the absence of adapted code and regulations are identified. It is found that the practiced 3DCP construction automates some but not all aspects of traditional construction. • 3D concrete printing demonstrates significant promise in the construction industry. • Large-scale 3D-printed concrete structures worldwide are reviewed. • Analyzed 137 projects and various research to bridge the practitioner-academic gap. • Combining 3DCP and conventional methods can address the issues in the technology. [ABSTRACT FROM AUTHOR]

Remanufacturing, a crucial step of reverse logistics, focuses on restoring or enhancing the functionality of waste products. The challenge in planning an effective remanufacturing reverse logistics system lies in the uncertainties from various sources. In addition, the evolving industrial landscape in Industry 5.0 necessitates adaptability to technological advancements. This paper proposes an integrated and digitalized architecture for uncertain reverse logistics network design. A fuzzy optimization model is first formulated to identify potential network configurations under varying demand-satisfying and capacity constraints. These solutions are automatically converted and assessed in a dynamic simulation environment with practical operational logic under a set of real-world scenarios. Numerical experiments are performed to validate the method and show the advantages of integrating optimization with dynamic simulation on a digital platform for strategic network planning. The results, built upon previous research, indicate that while initial investments in technology might be substantial, they may lead to long-term reductions in both costs and emissions. Moreover, collaborative decision-making is essential to mitigate potential disruptions and cascading effects. Our research contributes to the development of a novel integrated decision-support architecture and underscores the role of digitalization and Industry 5.0 in future smart and sustainable reverse logistics planning. [ABSTRACT FROM AUTHOR]

Due to the ongoing development of urban infrastructure and higher living standards, waste glass has become a significant component of municipal solid waste that cannot be disregarded. To address this issue, researchers have been looking for sustainable solutions to establish Circular Economy best practices for the full value chain of products made of glass, particularly for waste from high-quality glass sheets. Unfortunately, most of this waste is either dumped in landfills or recycled in an open-loop manner, due to its diverse composition and low volume. However, with the advent of Industry 4.0 and 5.0 technologies, including machine-to-machine communication, artificial intelligence, Internet of Things, collaborative robots, dynamic life cycle assessment, and advanced remanufacturing techniques, it could now become possible to characterize and recover end-of-life high-quality glass sheets like chemically strengthened glasses, e.g. used in smartphone screens, real time in smart factories for use in other high-tech applications. Such smart factories can economically produce on-demand batch-size 1 products, marking a fundamental transition from conventional recycling methods to a sustainable solution. This paper delves into the integration of Industry 4.0 technologies in glass recycling research and the potential contributions of Industry 5.0, addressing its societal implications. It also introduces an intelligent method to assess and optimize the lifespan of smartphone screen glass, suggesting potential reuse or remanufacturing solutions. [Display omitted] • Challenges in traditional glass waste management and the complexities of recycling. • Recycling's contribution to resource conservation and the Circular Economy. • New methods for recovering high-value materials like Chemically Strengthened Glass. • Identification of research gaps and future directions for recovery of high-quality glass materials. • Influence of Industry 4.0 and 5.0 on advancing glass recovery practices. [ABSTRACT FROM AUTHOR]

Radio Frequency Identification (RFID) systems have remarkable potential to be used in the supply chain management systems of the construction industry. RFID's ability to identify, track and locate objects provides tremendous flexibility in planning and operation of the industry. Consequently, RFID systems can contribute to on-time project completion, cost savings, enhanced reputation, and avoidance of regulatory fines. Moreover, RFID enhances visibility into inventory, equipment, and workforce, ensuring real-time safety measures. This paper conducts an in-depth analysis of state-of-the-art RFID detection and localization techniques, identifying gaps specific to the construction sector. The paper proposes the integration of emerging technologies, with a particular focus on the Internet of Things (IoT) and security mechanisms. This integration aims to solve challenges in using RFID systems in the construction industry's supply chain. It promises to enhance efficiency, security, and effectiveness of RFID technology, leading to a more efficient and resilient supply chain management system. [Display omitted] • Provides an in-depth analysis of state-of-the-art RFID detection and localization techniques, uncovering gaps and limitations specific to construction, and proposing innovative solutions. • Discovers how RFID, combined with emerging technologies like IoT, enhances supply chain efficiency and resilience, addressing specific challenges unique to the construction sector. • Addresses security concerns related to RFID localization and proposes a practical solution tailored to the construction industry's needs. [ABSTRACT FROM AUTHOR]

This paper demonstrates how the application of machine learning techniques can be used in Magnetron Sputtering (MS) processes, to detect anomalies and reduce their failure rate. Magnetron Sputtering is a widely used technique in materials science and engineering to deposit thin films of various materials for a range of applications. However, the process is complex and can be prone to various anomalies that can lead to defects in the deposited films, resulting in a non-negligible waste of coated objects. In this paper, we focus on the use of machine learning algorithms for both online and offline anomaly detection, which can help identify and diagnose process anomalies in real-time or post-process. Our results demonstrate that machine learning techniques can be used to develop anomaly detection systems, to limit failure in magnetron sputtering processes. • Simple machine learning tools can be applied to magnetron sputtering processes to detect anomalies, offline or online. • This innovative approach can limit failure in magnetron sputtering processes • Although machine learning is not common for surface scientist, this approach is reliable and based on accessible algorithms • The algorithms assist the operator in the decision making without seeking to replace him. [ABSTRACT FROM AUTHOR]

The emergence of Industry 4.0 marks a transformative era for businesses and industries, characterized by advanced technologies like automation, Internet of Things (IoT), artificial intelligence (AI), smart factories, and cyber-physical systems. This revolution promises significant advantages, including enhanced productivity, sustainable progress, and heightened resilience. However, the integration of Industry 4.0 is challenged by the need for a skilled workforce with expertise in areas such as information technology and data analytics. Higher education institutions (HEIs) play a vital role in equipping future professionals with these skills, necessitating curriculum updates and infrastructure enhancements. Simultaneously, the importance of education for sustainable development (ESD) has been underscored by global initiatives like the Sustainable Development Goals (SDGs). ESD instills a sense of responsibility for economic, ecological, and equitable well-being. As digital technologies blur the lines between industries, education faces the challenge of adapting to evolving demands. The integration of AI tools in education has emerged as a catalyst for reshaping learning experiences, fostering innovation, and preparing individuals for the digital age. AI chatbots such as ChatGPT have garnered widespread attention and possess the potential to revolutionize various aspects of education. However, their integration raises ethical concerns, necessitates curriculum redesign, requires strategies for continuous learning, and demands alignment with industry standards. While the potential of AI integration in education is promising, there is a notable gap in the existing literature when it comes to exploring the ethical implications, the influence of AI on ESD, the impact on the structure of Blooms Taxonomy, collaboration between academia and industry, strategies for continuous learning, and the effective integration of AI tools for personalized learning. This paper aims to critically examine the integration of AI tools, with a specific emphasis on ChatGPT, in education within the context of ESD. It delves into the transformative potential, ethical considerations, imperatives for continuous learning, and the role of industry partnerships. By providing insights and strategies, this paper contributes to the ongoing discussion about the evolving nature of education in a technologically driven world, equipping academic institutions to navigate the complexities and opportunities associated with AI integration in education more effectively. [ABSTRACT FROM AUTHOR]

Industry 4.0 process fault detection and diagnosis(FDD) is built on the foundations of Industrial Internet of Things(IIoT) for sensing and artificial intelligence for recognizing patterns. Despite the performance and application of various learning-based algorithms in multiple sectors, their black-box nature makes industrial experts skeptical. So, this paper proposes an eXplainable Fault Detection, Diagnosis, and Correction(XFDDC) Framework to create best-fit FDD models that are explainable. The XFDDC framework is designed to explain the FDD model predictions using eXplainable Artificial Intelligence(XAI) techniques. The proposed framework was applied to the bench-marked Tennessee Eastman Process(TEP) dataset. On evaluation, an XGBoost model yielded better Fault Detection Rate(FDR) and F1 score against popular transparent and complex models like Naive Bayes, K-Nearest Neighbors, Random Forest and a rule-based version of XGBoost. To explain the predictions of the XGBoost model, the XFDDC framework suggests the use of feature-based XAI techniques. So, the TreeSHAP algorithm is applied on the XGBoost model to generate local and global explanations as part of fault diagnosis. The proposed framework also recommends counterfactual explanations to provide action recommendations for correcting the fault situation. Thus, a best-fit explainable XGBoost Fault Detection, Diagnosis, and Correction (XGBoost-XFDDC) model is created. [ABSTRACT FROM AUTHOR]

Dynamic changes in the global economy, resulting from the implementation of the Industry 4.0 concept, cover practically all areas of life. They mainly concern companies that need to adapt to these changes as soon as possible in order to face growing competition. The digitalization process is of great significance in this respect, as it requires having appropriate material and personal resources as well as knowledge necessary to implement new innovative solutions. Problems associated with the digitalization of economy are very well understood in the European Union (EU), which makes every effort to ensure the best possible conditions for the implementation of this process in companies in all member states. A special group of these countries belong to Central and Eastern Europe (CEE), the youngest members of the EU. Given this extremely important issue, the paper presents the results of research on the level of digitalization of small, medium and large enterprises in this group of countries (CEE). Their aim was to evaluate the level of digitalization of the studied groups of enterprises and individual CEE countries. It was important to determine digital technologies dominating in particular groups of enterprises and, with the use of non-parametric tests, the influence of the digitalization level on selected economic parameters of particular CEE countries. The research was based on 11 selected indicators characterizing the digital technologies used, infrastructure for Industry 4.0 and personnel training in new technologies. The level of digitalization of individual groups of companies was determined based on the multi-criteria decision-making method (MCDM). In this case, the TOPSIS and VIKOR methods were applied, for which the rankings and levels of digitalization of individual CEE countries were also determined. The entropy and CRITIC methods were utilized to measure the weights of indicators adopted for the study. The whole research was complemented by statistical analyses of the adopted indicators. The results showed a high differentiation in the level of digitalization for individual CEE countries and the studied groups of enterprises. The highest levels of digitalization were reported in Slovenia, Croatia and the Czech Republic. The lowest levels were reported in Bulgaria and Romania. From the point of view of the size of enterprises, the highest levels of digitalization were found in the group of large enterprises, which results from their potential and resources. The results are an important source of information regarding the current state of digitalization in the CEE countries, considering the size of enterprises. This, in turn, should be used when developing strategies for the digital transformation of the CEE countries and the entire EU. [ABSTRACT FROM AUTHOR]

• The EFCE 16th Loss Prevention Symposium was held in June 2019 in Delft, NL. • The first symposium of this series was in 1974 at the same location. • A comparison was made what knowledge has been gained in those 45 years. • An overview is given of the many interesting presentations at the current event. • The evolution toward Industry 4.0 presents new challenges to process safety. The first European Loss Prevention Symposium under the auspices of the European Federation of Chemical Engineering (EFCE) took place in 1974 in the then new Aula of the Delft University of Technology in the Netherlands. After the triennial symposium over a period of 45 years having been organized in several European cities, it returned in 2019 to the Delft Aula. Authors of this paper are members of EFCE Loss Prevention Working Party organizing the LP Symposia and after nearly half century, it is therefore worthwhile to look back and also to look forward, following the evolution of process safety. This paper presents an impression of the changes in process safety, risk management approaches, and methods over that 45-year period, while at the same time the last symposium contributions are briefly reviewed and a few highlights, called breakthroughs, are identified. [ABSTRACT FROM AUTHOR]

This paper argues that there is an emergent digital culture in the art and cultural sector in Hanoi, which is producing a paradigm shift in the nature of work for cultural professionals, the way of preserving and displaying art collections as well as the nature of international connections. The advent of the 'fourth industrial revolution' in Vietnam has brought about advances in digitization. While this transition is crucial in achieving national sustainable development goals, Vietnam remains at a disadvantage on a global scale due to country-specific challenges in digitization, including lack of human, technical, and financial resources. These challenges are hindering the pace and quality of the digitization process and impeding cultural professionals' ability to utilize digital platforms. In addition, the global digital divide is having impacts on access, inclusion and representation. This shows that the challenges faced in the digitization process are not only about access to technology but also about much more deep-seated issues related to culture, history, and social inequalities. This issue has become especially pertinent during the Covid-19 pandemic and has highlighted digital inequalities in access and inclusion. The research draws on 20 semi-structured interviews with cultural professionals across Hanoi. The interviews were carried out during the Covid-19 pandemic and addressed its impact on digitization projects as well as use of digital technologies for work. The findings show how geopolitical and socioeconomic factors can supress the ability to adopt new digital technologies and hinder the ability to exploit the opportunities of digitization. The Covid-19 pandemic has allowed more time to focus on digitization projects and to utilize digital tools and platforms, especially with free open-source platforms such as Facebook. This has become one route towards exploiting the opportunities of digitization for increased exposure, inclusion in the discourse, and creation of digital resources on Vietnamese art and culture. [ABSTRACT FROM AUTHOR]

The dynamic development of information and communication technology (ICT) reported in recent years has caused significant changes in almost all areas of social and economic life. The digitalization process resulting from this development is now becoming a determinant of both progress and modernity. This issue has been addressed in this paper, and thereby we present a methodology developed to study the level of digitalization and the use of innovative technologies among the enterprises of the EU-27 countries. The research was conducted using selected indicators—determinants (10) characterizing the main digital technologies and infrastructure associated with their implementation in the enterprises under study. Based on these indicators, the Entropy-Multi-Objective Optimization on the basis of Ratio Analysis (MOORA) method was used to determine the index (level) of digitalization among the companies of the EU-27. The level of use of digital technologies and infrastructure for Industry 4.0 was also determined. Another important goal of the study was to determine a relationship between the values of the digitalization index for the EU-27 countries and the economic parameters characterizing their economies. For this analysis, non-parametric tests such as the Kendall's Tau and Spearman's rank correlation coefficients were applied. The results significantly enrich the knowledge of methodology for studying the level of digitalization and its status among the enterprises of the EU-27. These findings provide great opportunities for interpretation and practical application, especially in terms of building an innovative knowledge-based economy. They show great diversity of the EU-27 countries in the field of digitalization and poor results reported in this area by the so-called "new EU" countries. Among the many interesting findings, it is worth pointing out the positive impact of spending on research and development on the process of digitalization of enterprises. The results should be used when creating a digitalization strategy for individual countries and their groups. [ABSTRACT FROM AUTHOR]

The rapid growth of the Industry 4.0 paradigm is increasing the pressure to develop effective automated monitoring systems. Artificial Intelligence (AI) is a convenient tool to improve the efficiency of industrial processes while reducing errors and waste. In fact, it allows the use of real-time data to increase the effectiveness of monitoring systems, minimize errors, make the production process more sustainable, and save costs. In this paper, a novel automatic monitoring system is proposed in the context of production process of plastic consumables used in analysis laboratories, with the aim to increase the effectiveness of the control process currently performed by a human operator. In particular, we considered the problem of classifying the presence or absence of a transparent anticoagulant substance inside test tubes. Specifically, a hand-designed deep network model is used and compared with some state-of-the-art models for its ability to categorize different images of vials that can be either filled with the anticoagulant or empty. Collected results indicate that the proposed approach is competitive with state-of-the-art models in terms of accuracy. Furthermore, we increased the complexity of the task by training the models on the ability to discriminate not only the presence or absence of the anticoagulant inside the vial, but also the size of the test tube. The analysis performed in the latter scenario confirms the competitiveness of our approach. Moreover, our model is remarkably superior in terms of its generalization ability and requires significantly fewer resources. These results suggest the possibility of successfully implementing such a model in the production process of a plastic consumables company. • Using Artificial Intelligence to increase the efficiency of industrial process. • A novel automated monitoring system to enhance control processes. • Addressing the production control issue of test tubes for analysis laboratories. • The model surpasses pre-trained networks in accuracy and generalization. • The results suggest the feasibility of implementing such a model in practice. [ABSTRACT FROM AUTHOR]

This paper presents a novel optical fiber sensor for measuring the bitterness of beer samples. The sensor is based on a Mach–Zehnder interferometer (MZI) composed of two long-period fiber gratings (LPFGs). The sensor exploits the sensitivity of the LPFGs to the refractive index of the surrounding medium, which varies according to the concentration of iso- α -acids that cause bitterness in beer. The sensor uses a two-point on-line self-calibrating procedure to estimate the bitterness of unknown samples by comparison with reference samples of known bitterness. The sensor performance was evaluated in both laboratory and factory settings, showing good repeatability, reproducibility, and low bias. The proposed sensor offers a fast, simple, and low-cost alternative to the conventional method of measuring beer bitterness based on UV spectroscopy. The sensor can be integrated into the Industry 4.0 framework to improve the quality and consistency of beer production. • Innovative Sensor Design: Introducing a novel optical fiber sensor based on a Mach-Zehnder interferometer. • Two-Point On-line Self-Calibration: Implementing a robust self-calibrating procedure to estimate beer bitterness. • Versatility in Evaluation Settings: Evaluating sensor performance in lab and factory settings with high accuracy. • Fast, Simple, and Cost-Effective Alternative: Offering a rapid, simple, and cost-effective solution for bitterness measurement. • Integration with Industry 4.0: Potential integration into Industry 4.0 for real-time monitoring of beer bitterness levels. [ABSTRACT FROM AUTHOR]

Equipment condition monitoring holds immense significance in modern industrial factories, facilitating sustained operation with heightened efficiency, safety, and cost-effectiveness. This paper presents an interactive networked condition monitoring strategy to enhance plant-wide production equipment condition monitoring, leveraging networked control and edge computing approaches. This strategy offers a rapid and efficient solution that comprises four key components: drag-and-drop monitoring algorithm design, executable program generation, networked algorithm implementation, and interactive monitoring process. Initially, algorithms for equipment condition monitoring are designed using pre-defined components and then seamlessly compiled into executable programs with a single click. Subsequently, these algorithms are implemented within an edge computing-based monitoring system using the networked control approach, where the generated programs are remotely deployed into edge nodes positioned adjacent to the equipment. Moreover, the monitoring process features visual displays of parameters and results using configurable widgets, enabling interactive adjustments. Real-world application cases from an aluminum manufacturing factory showcase the strategy's effectiveness in comprehensive condition monitoring of hundreds of equipment across nine workshops, significantly reducing the equipment inspection time to tens of minutes compared to manual inspection. With extensive implementation in various industrial factories, this strategy emerges as a promising solution for equipment condition monitoring in smart factories. • Proposing an interactive networked condition monitoring strategy. • Swift algorithm design and conversion into executable programs. • Deployment of executable programs on remote edge nodes. • Provision of interactive monitoring processes by intuitive visual widgets. [ABSTRACT FROM AUTHOR]

In recent years, Infant Formula Milk (IFM), a vital source of nutrition for infants lacking breast milk in their first two years, has been plagued by diverse and severe global supply chain disruptions. These challenges have triggered shortages, compromised product quality, and threatened food security, leading to dire health consequences and even fatalities among infants. However, despite the criticality of IFM, current research is lacking in terms of how to build or improve the resilience of IFM supply chains. This paper presents a detailed framework for building a resilient IFM supply chain. A key pillar of this framework is a comprehensive analysis of potential hazards. Using the Hazard and Operability Analysis (HAZOP) method, 91 potential hazards were identified across the entire IFM supply chain. Subsequently, a clustering method identified 17 critical risks with irreversible consequences for infant health and supply chain flow. Finally, mitigation strategies that combine traditional approaches with 4.0 technology-enabled solutions are proposed. Adapting this framework can provide valuable insights for IFM supply chain stakeholders, enabling them to secure the vital flow of this life-sustaining product and safeguard the health and well-being of infants. • Framework for resilience in the infant formula milk (IFM) supply chain is presented. • Risk assessment using HAZOP identifies 91 potential risks in the IFM supply chain. • Mitigation plan with traditional resilience and Industry 4.0 technologies is presented. [ABSTRACT FROM AUTHOR]

The intelligent diagnosis of faults in industrial assets helps avoid unexpected interruptions of critical services. Thus, machine learning systems for monitoring machinery have a fundamental role in smart factories. The goal of this paper is to promote generalization by combining binary models into multiclass ones. This approach avoids using customized models, which do not perform well if the required conditions do not match during inference. Hence, instead of proposing multiple models for each particular condition, e.g., a model for each machine type, we evaluate different multiclass models where this information becomes an additional outcome along with the operating status. In our experiments, we use the Synthetic Minority Over-sampling Technique (SMOTE) to deal with imbalanced datasets and the PyCaret library to pre-select the most promising algorithms using binary classification. After selecting the binary models for combination, we evaluate two multiclass approaches, called partially- and totally-mixed, using the Malfunctioning Industrial Machine Investigation and Inspection (MIMII) dataset of machinery audio. The number of classifiers needed is reduced up to 83% with our proposal compared with binary classification used as a baseline approach. Furthermore, in the partially-mixed multiclass proposal, it is possible to obtain the correct classification of anomalous states in at least 88% of the samples for most devices. We show that there is a cost on computational resources for model training, which is compensated by the generalization gains verified using the F1-Score metric two times higher than the binary models. We follow the same idea of building more generic models with another existing dataset, ToyADMOS, which similarly contains machine operating sounds. The experiments confirm the results obtained with the MIMII dataset. [ABSTRACT FROM AUTHOR]

In this position paper, we summarize history, current activities and future topics of IFAC Technical Committee (TC) 5.2 "Manufacturing Modelling for Management and Control". As a special focus, we discuss the results of the 9th IFAC Conference MIM 2019 that was recently organized by IFAC TC 5.2 in Berlin, Germany and attended by 740 participants. We analyse the current activities of the working groups within TC 5.2 and project some future research directions. Finally, we present an overview of papers from TC 5.2 in this special issue. [ABSTRACT FROM AUTHOR]

The Industrial-Internet of Things (I-IoT) stands out as one of the most dynamically evolving subfields within the expansive realm of the Internet of Things (IoT). Its exponential growth is reshaping industrial landscapes, bringing forth transformative innovations and advancements at an unprecedented pace, as the core of Industry 4.0. Among the formidable challenges faced by the Industrial-Internet of Things, cybersecurity stands out as a critical concern. Deep learning-based Intrusion Detection System (IDS) solutions showcase their steadfast ability to secure resource-limited, investigation-demanding, and complex I-IoT environments. However, their effectiveness hinges not only on the model but also on the dataset on which they are trained. While numerous literature studies delve into this field, existing proposed models often grapple with challenges. They are frequently trained on outdated, non-diverse datasets or lack specific features crucial for I-IoT networks. Recent efforts, thankfully, introduce more adequate datasets like Edge-IIoTset. Researchers leverage this extensive dataset to train models, focusing on detecting the 14 sophisticated attacks. These attacks predominantly target real I-IoT networks. Despite these efforts, none of the existing models proves entirely efficient. A review of literature solutions reveals that many models cannot detect all 15 classes in the dataset. Some are multi-staged or overly complex. In response to these challenges, this paper presents an End-to-End learning , non-complex CNN1D model tailored to the specific problem of detecting 14 sophisticated threats targeting I-IoT environments. Our proposed model demonstrated remarkable efficiency with an accuracy of 99.96%, successfully detecting all 15 classes in the Edge-IIoTset dataset with a minimal loss of 0.0011. Not only that, but our model was validated with k-fold cross-validation, demonstrating its efficiency in preserving the same performance on unseen data and its ability to be generalized for real-world I-IoT environments. • Explored I-IoT cyber threats under Industrial 4.0. • Emphasized deep learning IDS effectiveness. • Introduced efficient preprocessing method. • Designed simple End-to-End CNN1D model. • Achieved 99.96% accuracy across 15 classes. • Demonstrated robustness in real-world scenarios. • Developed lightweight solution for I-IoT. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative model designed to predict the optimal product prototype within the framework of sustainable development. The model takes into account both quality and environmental impact throughout the entire life cycle of the product, with a specific focus on light electric vehicles. By incorporating customer expectations using the Weighted Sum Model, the model assesses vehicle quality based on the importance of various criteria. Employing life cycle evaluations guided by the Pareto-Lorenz rule, environmental impact for vehicle prototypes is modeled. The resulting Quality-Environmental Indicator of LCA (QLCA) facilitates a qualitative environmental analysis, aiding in the selection of prototypes that align with customer expectations. The model proves effective in guiding decisions related to product development, providing a comprehensive approach to evaluating product value. Notable contributions to the scientific community include the introduction of the QLCA model, which integrates quality and environmental assessments, and underscores the significance of open innovation, sustainable development, and sensitivity analysis for organizational adaptation. Future research directions involve adapting the model to larger customer samples, exploring production costs, and assessing its applicability across diverse industries and contexts to enhance its universality and practical implications. [ABSTRACT FROM AUTHOR]

The evolution of journal bearings, from fixed profiles to adaptive configurations, signifies a captivating progression in journal bearing technology. A notable innovation in adaptive bearings is Multi-pad Bidirectional Adjustable Bearing (MBAB), which can control film thickness in radial and circumferential directions. This paper introduces a novel data-driven approach, utilizing machine learning to model and optimize the static performance of MBABs with asymmetric bearing element adjustments. The study uses a parameter-independent Jaya algorithm coupled with machine learning models to identify optimal combinations of adjustments. Results highlight the significance of negative radial adjustments and asymmetric profiles for optimal performance. This research contributes to Industry 4.0 by bridging the physical-digital gap, offering a data-driven solution to enhance the performance of these advanced bearings. [ABSTRACT FROM AUTHOR]

Human motion analysis plays a crucial role in industry 4.0 and, more recently, in industry 5.0 where human-centered applications are becoming increasingly important, demonstrating its potential for enhancing safety, ergonomics and productivity. Considering this opportunity, an increasing number of studies are proposing works on the analysis of human motion in an industrial context, taking advantage of the rise of artificial intelligence technologies and sensor technologies. The objective of this work is to provide a review of recent studies exploring these technologies in the analysis of human movement while specifically considering industrial context. First, a taxonomy of key human motion analysis applications is proposed, presenting statistical insights to reveal trends and highlighting lacks in current research. Furthermore, this work identifies benchmark datasets acquired in various industrial case studies and associated sensors. Many recommendations for selecting optimal sensors and valuable benchmarks are proposed. Then, the paper outlines the current trend of utilizing hybrid deep learning methodologies in human movement analysis while underscoring the performance and limitations of these proposed methods, considering industrial constraints such as real-time recognition and frugality. Finally, challenges and future works are highlighted, focusing on the opportunities to address problems related to the complex industrial environment in order to achieve reliable performances. [ABSTRACT FROM AUTHOR]

The industries engaged healthcare, manufacturing, and construction automated with exquisite creativity and innovation at the doorstep of Industry 4.0. In this process, digital twins are diligently used to supplement industrial processes, reduce costs, monitor assets, streamline maintenance, reduce downtime, and enable the creation of connected goods. The research is aimed at finding the digital representation of electro-mechanical railway interlocking elements are simulated and its functionality is verified accordingly. With respect to carry out this research, the Indian Railways Mangalagiri Railway Station blueprints were collected to represent the physical Model which consists of signals, points, a crank handle, an LC gate, and many more elements. In this paper, three interlocking elements such as points, crank handle, and LC gate, are analysed, modelled, and simulated by using Model Sim ME of Libero SoC software. Representation of these digital elements were developed using a smart design canvas. Therefore, the proposed methodology will enhance the safety measures and security levels of the train movements and reduces the time required to replace the faulty relay. Similarly, in future, the proposed model could be dumped into the FPGA kit to verify the real-time data for finding the faulty relay in the relay-based interlocking system. [ABSTRACT FROM AUTHOR]

Localization models, particularly for indoor applications like autonomous vehicles and smart manufacturing in Industry 4.0, have emerged as a crucial research area because of the growing need for precise positioning. In this context, distributed cell-free MIMO have demonstrated capabilities for a higher fine-grained resolution and accuracy. This paper explores different approaches to address challenges related to positioning and corresponding data transmission and model compression problems in cell-free massive MIMO systems. We present a novel deep-learning powered CSI compression model for reducing the signalization data associated with the localization task, minimizing the fronthaul capacity requirement by at least a factor of 2, without a significant loss of accuracy. In our research, we also focus on the challenges of deploying deep end-to-end neural networks on resource-constrained embedded platforms. Two approaches are proposed: model modification and magnitude-based pruning. Our results show that the pruned end-to-end localization model has a smaller size by 36% at the cost of an increase on the localization error by a factor of 1.5 (precision is reduced from approximately 5 mm to 7.8 mm). [ABSTRACT FROM AUTHOR]

In India, approximately one-third of agricultural produce is wasted every year due to the different issues present in the post-harvest supply chain stages. The supply chain management of perishable products becomes complex and challenging due to the inclusion of its perishability dynamics. Quality is the main factor that governs the buying or discarding of perishable products by consumers. Therefore, the main aim of this research work is to develop an accurate and efficient image processing model for the classification of the product (Tomato) based on its quality for managing the supply chain. There are three novelties in this research work. A four-stage supply chain architecture integrated with the image processing system at mandi, and warehouses is proposed (First). This image processing system is developed in two stages. In stage I, the acquired images of tomato during its life cycle are labelled with the help of machine learning algorithms (Second). This labelled data is used in stage II for the development of a classification model to segregate the product into various grades. For this, an optimized architecture of seven-layer Convolutional Neural Network (CNN) model is developed followed by optimization of its hyperparameters simultaneously using Design of Experiments (DOE) technique (Third). The optimized CNN model achieved maximum accuracy of 88.40% and reported an execution time of 7 min. Further, the results of standard hyperparameter optimization techniques like Grid search, Random search, Bayesian, and Hyperband are compared with the proposed DOE technique on the optimized CNN architecture. The work done in this paper enables the supply chain managers to take accurate and rapid decisions for pricing, procurement, storage, and transportation at various stages of the supply chain leading to Industry 4.0. This will result in reduced post-harvest losses and simultaneously achieve the benefits across social, economic, and environmental dimensions of sustainability leading to better supply chain management. • A supply chain architecture integrated with image processing system is proposed. • Decisions related to pricing, procurement, storage and transportation can be taken. • The quality of product is modelled and labelled using Machine Learning algorithms. • A CNN model is developed for quality-based classification and optimized using DoE. • A comparison of DoE with Grid search, Bayesian and Hyperband is presented. [ABSTRACT FROM AUTHOR]

[Display omitted] With the sustainable development of advanced manufacturing technology, the important link affecting the final quality of complex products has been transferred from design and manufacturing to the assembly process. However, traditional pre-defined assembly parameters could not respond to changes in the assembly process caused by assembly errors, leading to unstable assembly quality and poor consistency. To address these issues, this paper proposes a novel online modeling and control method for complex assembly process based on digital twins (DT) and an extended particle swarm optimization algorithm, which could dynamically adjust the assembly process parameters to quickly respond to changes in the assembly process. Firstly, a DT-enabled autonomous assembly framework is proposed for the online analysis, optimization and control of assembly quality, by considering the coupling effect of multi-dimensional assembly errors on assembly quality. Then, two key enabling technologies of the framework, including the multi-dimensional assembly error-fused DT modeling method and DT-driven online optimization and control method of assembly errors are introduced in detail. Finally, a smart assembly prototype is implemented, where its application examples and evaluation results show the superiority of the proposed approach. Compared with traditional method, the proposed approach could significantly reduce the iteration time by 64% and improve the assembly quality by 14.05%. [ABSTRACT FROM AUTHOR]

This paper presents the results of a study aimed at assessing the level of business digital maturity in Europe and at analyzing similarities between companies in terms of implemented Industry 4.0 technologies. The digital transformation of production and service enterprises has become a common direction of development for all economic sectors. The very idea of Industry 4.0 has become synonymous with innovation and is the basis for business development. The role and importance of these transformations are also recognized by the EU which has been promoting and supporting the development of an innovative digital economy for many years. However, individual EU countries differ in terms of digital business maturity due to the implementation of Industry 4.0 technology. The article addresses this problem by presenting the results of a comprehensive study of the implementation of Industry 4.0 digital technologies in enterprises in the EU-27 countries and by assessing similarities between these countries in terms of these technologies. The similarity analysis was carried out using the k-means method. The Gini coefficient and Lorenz curves were utilized to determine the unevenness of the implementation of these technologies in individual countries, and the Weighted Aggregated Sum Product Assessment method was used to assess the level of digital maturity. The research was based on eight selected determinants (indicators) that characterize the most important technologies related to Industry 4.0. The results showed high diversity among EU countries in terms of digital maturity. Scandinavian countries (Finland and Denmark) and Malta were found to be leaders in this area, while the weakest results were reported for Greece, Romania, Bulgaria, Hungary, and Latvia. The findings provide a lot of new information about the current state of development of the digital economy in EU countries, which should be used in both the development and implementation of new solutions related to economic digitalization policy in this region. [ABSTRACT FROM AUTHOR]

The take-off of a Fourth Industrial Revolution (4IR) is at the core of a vibrant academic debate with an increasingly larger number of studies investigating the effects of the latest generation of new technologies, namely artificial intelligence (AI), flexible automation, additive manufacturing, big data, etc., — hereinafter defined as intelligent technologies. A great deal of attention has been paid to the effects associated with the adoption of such transformative technologies, whilst the impact associated with their production, and in particular with the development of related technological knowledge, has remained almost unexplored. Using patent data at country level for a sample of industrialized economies between 1990 and 2014, this paper seeks to quantify the productivity spillovers associated with intelligent technologies. We show that the elasticity of aggregate productivity to the stock of knowledge related to intelligent technologies is statistically significant and economically important, ranging between 0.01 and 0.06. Since these innovations have increased by a factor of 3 from the early 1990s, based on our most conservative estimates, knowledge related to intelligent technologies would account for a range between 3 and 8% of observed productivity change. We also document that the time pattern of productivity spillovers associated with intelligent technology patents may conform to a productivity J-curve , corroborating the view that such innovations could behave as General Purpose Technologies (GPTs). [ABSTRACT FROM AUTHOR]