Search

This article presents research work on an intelligent system that was developed to monitor and continuously evaluate the quality of metal powder distribution in the laser powder bed fusion (LPBF) 3D printing process. The 3D printer that was used to carry out the work was equipped with an industrial vision system to capture images immediately after spreading powder on the work field. The powder distribution tests showed that the most common defects were identified as an insufficiently thick layer of powder applied to the working field (super elevation), unevenly distributed powder as a result of recoater vibration (so called recoater hopping), and its wear (so called recoater streaking). In the first stage of research, a set of training data (images) was collected. Then, the implementation of the machine learning process was prepared in the Roboflow environment. After that, the learning, validation, and prediction process was carried out several times using the selected machine learning model (YOLO model implemented in a Python environment) in order to select the most effective parameters. The study showed that deep machine learning can be effectively used to identify defects in powder distribution during the laser powder bed fusion (LPBF) process. [ABSTRACT FROM AUTHOR]

Predictive maintenance contributes to Industry 4.0, as it enables a decrease in maintenance costs and downtime while aiming to increase production and return on investment. Despite the increasing utilization of machine learning techniques in predictive maintenance in industrial systems over the past few years, several challenges remain to be addressed in the implementation of ML, including the quality of the data collected, resource constraints, and equipment heterogeneity. This study proposes an adaptive framework for predictive maintenance in the context of Industry 4.0, specifically in internet of things (IoT) systems, using machine learning (ML) models. In particular, this study introduces PdM-FSA, a new framework based on an ensemble classifier that takes advantage of four widely adopted ML models in the predictive maintenance literature: random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and k-nearest neighbors (KNN). The performance evaluation results showed that the PdM-FSA framework can perform well for predictive maintenance according to the severity of equipment malfunctions in a smart factory. The results of this study provide significant knowledge to researchers and practitioners on predictive maintenance in the context of Industry 4.0. and enables the optimization of processes and improves productivity. [ABSTRACT FROM AUTHOR]

The integration of artificial intelligence(AI) technologies into identity and access management (IAM) systems has greatly improved access control and management, offering more robust, adaptive, and intelligent solutions than traditional methods. AI-driven IAM systems enhance security, operational efficiency, and introduce new capabilities in industrial environments. In this narrative review, we present the state-of-the-art AI technologies in industrial IAM, focusing on methods such as biometric, comprising facial and voice recognition, and multifactor authentication for robust security. It addresses the challenges and solutions in implementing AI-based IAM systems in industrial settings, including security, privacy, evaluation, and continuous improvement. We present also the emerging trends and future directions, highlighting AI's potential to transform industrial security measures. This review aims to guide researchers and practitioners in developing and implementing next-generation access control systems, proposing future research directions to address challenges and optimize AI applications in this domain. [ABSTRACT FROM AUTHOR]

The widespread adoption of the Industry 5.0 paradigm puts people and their applications at the center of attention and, with the increasing automation and robotization of work, the need for workers to acquire new, more advanced skills increases. The development of artificial intelligence (AI) means that expectations for workers are further raised. This leads to the need for multiple career changes from life and throughout life. Belonging to a previous generation of workers makes this retraining even more difficult. The authors propose the use of machine learning (ML), virtual reality (VR) and brain–computer interface (BCI) to assess the conditions of work–life balance for employees. They use machine learning for prediction, identifying users based on their subjective experience of work–life balance. This tool supports intelligent systems in optimizing comfort and quality of work. The potential effects could lead to the development of commercial industrial systems that could prevent work–life imbalance in smart factories for Industry 5.0, bringing direct economic benefits and, as a preventive medicine system, indirectly improving access to healthcare for those most in need, while improving quality of life. The novelty is the use of a hybrid solution combining traditional tests with automated tests using VR and BCI. This is a significant contribution to the health-promoting technologies of Industry 5.0. [ABSTRACT FROM AUTHOR]

This comparative review explores the dynamic and evolving landscape of artificial intelligence (AI)-powered innovations within high-tech research and development (R&D). It delves into both theoretical models and practical applications across a broad range of industries, including biotechnology, automotive, aerospace, and telecommunications. By examining critical advancements in AI algorithms, machine learning, deep learning models, simulations, and predictive analytics, the review underscores the transformative role AI has played in advancing theoretical research and shaping cutting-edge technologies. The review integrates both qualitative and quantitative data derived from academic studies, industry reports, and real-world case studies to showcase the tangible impacts of AI on product innovation, process optimization, and strategic decision-making. Notably, it discusses the challenges of integrating AI within complex industrial systems, such as ethical concerns, technical limitations, and the need for regulatory oversight. The findings reveal a mixed landscape where AI has significantly accelerated R&D processes, reduced costs, and enabled more precise simulations and predictions, but also highlighted gaps in knowledge transfer, skills adaptation, and cross-industry standardization. By bridging the gap between AI theory and practice, the review offers insights into the effectiveness, successes, and obstacles faced by organizations as they implement AI-driven solutions. Concluding with a forward-looking perspective, the review identifies emerging trends, future challenges, and promising opportunities in AI-powered R&D, such as the rise of autonomous systems, AI-driven drug discovery, and sustainable energy solutions. It offers a holistic understanding of how AI is shaping the future of technological innovation and provides actionable insights for researchers, engineers, and policymakers involved in high-tech Research and Development (R&D). [ABSTRACT FROM AUTHOR]

Objective: The aim of processing iron ore in processing plants is to achieve a product with an appropriate grade and maximum iron recovery. The amount of iron recovery in processing systems depends on several parameters, and its determination through weighing and laboratory tests is time-consuming and costly .With the development of the use of artificial intelligence for predicting and optimizing the performance of industrial systems, it seems that this technology could address many of the issues faced in mineral processing industries, including iron ore processing plants. Therefore, the objective of this research is to assess the feasibility of using artificial intelligence to predict iron recovery based on iron (Fe) and iron oxide (FeO) grades as the first step towards developing the application of this technology in the mining industry. Materials and methods: For this study, daily data on the Fe and FeO grades in the feed as well as iron recovery from the Central Iron Ore Concentrate Plant, which includes two production lines (Choghart and Sechahun), were collected. Iron recovery modeling was performed using two neural network models: MLP (Multilayer Perceptron Neural Network) and CFNN (Cascade Forward Neural Network). In this modeling, the Fe and FeO grades of the feed were treated as the model inputs, while iron recovery was considered the output. Results: The results showed that both models performed relatively similarly, but CFNN exhibited better statistical parameters. The R² value for the CFNN model was obtained as 0.831 for the Choghart production line and 0.837 for the Sechahun line, while the RMSE for these models was calculated as 1.655 and 1.823, respectively. The analysis indicated that the CFNN model could confidently predict iron recovery with a relative error of less than 5% at a 95% confidence level for both production lines. Conclusions: Using Fe and FeO grades alone as inputs for the models cannot lead to a comprehensive model that can replace conventional calculations. Therefore, the influence of other effective parameters will be thoroughly identified in this study. Additionally, sensitivity analysis revealed a direct relationship between iron recovery and both input parameters, with the Fe grade having a greater impact on iron recovery. The results of this study show that using artificial intelligence to predict iron recovery is very promising. By increasing model accuracy through the addition of data and input parameters, it is possible to develop models that can reduce the costs and time required for grade assessment in the plant. [ABSTRACT FROM AUTHOR]

Copyright of Arab Journal for Scientific Publishing is the property of Research & Development of Human Recourses Center (REMAH) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This survey explores applications of explainable artificial intelligence in manufacturing and industrial cyber–physical systems. As technological advancements continue to integrate artificial intelligence into critical infrastructure and industrial processes, the necessity for clear and understandable intelligent models becomes crucial. Explainable artificial intelligence techniques play a pivotal role in enhancing the trustworthiness and reliability of intelligent systems applied to industrial systems, ensuring human operators can comprehend and validate the decisions made by these intelligent systems. This review paper begins by highlighting the imperative need for explainable artificial intelligence, and, subsequently, classifies explainable artificial intelligence techniques systematically. The paper then investigates diverse explainable artificial-intelligence-related works within a wide range of industrial applications, such as predictive maintenance, cyber-security, fault detection and diagnosis, process control, product development, inventory management, and product quality. The study contributes to a comprehensive understanding of the diverse strategies and methodologies employed in integrating explainable artificial intelligence within industrial contexts. [ABSTRACT FROM AUTHOR]

The adoption of artificial intelligence into industrial settings promises notable enhancements in productivity, quality, efficiency, competitiveness, and innovations. However, transitioning AI models from concept to full-scale industrial applications involves various complexities and challenges. These challenges are not only technical but also extend into the ethical and regulatory realms, calling for a comprehensive approach to AI integration. This paper examines the diverse hurdles faced during developing and deploying AI applications in the industrial domain. It addresses challenges in collecting the right data, construction of AI models, and ensuring that these models work accurately and responsibly when deployed in real industrial environment. Furthermore, the paper presents strategic recommendations, underscoring the necessity of ethical considerations and regulatory compliance to effectively overcome these obstacles. We provide guidelines aimed at maximizing AI's benefits in industrial environments while minimizing potential risks. [ABSTRACT FROM AUTHOR]

This paper addresses the challenges of large data management, prolonged operation times, and low detection efficiency encountered in automatic detection systems. To overcome these issues, we propose a novel research and application method utilizing AI machine vision technology. The methodology employs the Pulse-Coupled Neural Network (PCNN) algorithm for analyzing machine control points, enhancing system reliability and detection efficiency. Furthermore, a three-stage sliding table mechanism is implemented to facilitate seamless operation restarts. Notably, our approach significantly reduces the time required for key operations, such as feeding, imaging, decision-making, on-site inspection, and re-inspection, all within 5 seconds and 1 meter distance. It supports high-precision dynamic identification, detection, and correction of errors during high-speed movement, thereby enhancing overall system performance. The experimental results demonstrate exceptional accuracy, particularly in detecting small parts measuring 28.87 mm in length and 12.36 mm in width, achieving an impressive precision of 0.04 mm. Additionally, our system boasts meticulous hardware selection, robust software stability, and high-performance capabilities, culminating in improved detection efficiency and accuracy. This research not only contributes novel ideas and results but also holds significant commercial value in industrial applications. Overall, our proposed methodology represents a noteworthy advancement in automatic inspection systems, offering superior performance and reliability compared to existing approaches. [ABSTRACT FROM AUTHOR]

Modern industrial systems demand intricate connectivity and automation, especially in the realm of shop floor processes and intralogistics. Automated Guided Vehicle (AGV) systems are characterized by their potential for seamlessly networking value creation areas. However, failures and disruptions in AGV systems and adjacent facilities can lead to production halts, adversely affecting delivery reliability and quality. A substantial portion of the downtime stems from manual troubleshooting, underscoring the pivotal importance of the response time from maintenance staff. This paper introduces an approach employing a neural network with long short-term memory for forecasting and predictive maintenance to enhance AGV system reliability and availability in production environments. By analysing historical data, identifying patterns, and predicting potential failures or maintenance needs in AGV components and neighbouring facilities, the proposed AI-based forecasting ensures timely preventive measures. A case study shows the effectiveness of this approach in significantly improving AGV system performance, minimizing disruptions, and enhancing operational availability. This research contributes to smart manufacturing by providing a practical solution for optimizing availability of the concerned AGV system through advanced AI-based forecasting strategies. [ABSTRACT FROM AUTHOR]

Copyright of China Textile Leader is the property of China Textile Information Center and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Purpose: The hospitality industry is on the cusp of a culinary revolution, propelled by the integration of smart cooking technologies and artificial intelligence (AI). This article delves into how these innovations are transforming hotel and restaurant kitchens, emphasizing food quality, operational efficiency and sustainability. Through AI, the culinary domain promises not just refined dining experiences but also a fundamental reshaping of kitchen operations. Design/methodology/approach: The study includes a document review prepared by examining the academic literature regarding the chosen concepts in a wide range of contexts. Findings: Smart cooking provides much convenience in working life with the help of technology, and this technology will be given more space in the future. Originality/value: This article presents a review of the relevant literature on smart cooking systems, one of the developing digital gastronomy tools. [ABSTRACT FROM AUTHOR]

An Industrial Cyber-physical System (ICPS) provides a digital foundation for data-driven decision-making by artificial intelligence (AI) models. However, the poor data quality (e.g., inconsistent distribution, imbalanced classes) of high-speed, large-volume data streams poses significant challenges to the online deployment of offline-trained AI models. As an alternative, updating AI models online based on streaming data enables continuous improvement and resilient modeling performance. However, for a supervised learning model (i.e., a base learner), it is labor-intensive to annotate all streaming samples to update the model. Hence, a data acquisition method is needed to select the data for annotation to ensure data quality while saving annotation efforts. In the literature, active learning methods have been proposed to acquire informative samples. Different acquisition criteria were developed for exploration of under-represented regions in the input variable space or exploitation of the well-represented regions for optimal estimation of base learners. However, it remains a challenge to balance the exploration-exploitation trade-off under different online annotation scenarios. On the other hand, an acquisition criterion learned by AI adapts itself to a scenario dynamically, but the ambiguous consideration of the trade-off limits its performance in frequently changing manufacturing contexts. To overcome these limitations, we propose an ensemble active learning method by contextual bandits (CbeAL). CbeAL incorporates a set of active learning agents (i.e., acquisition criteria) explicitly designed for exploration or exploitation by a weighted combination of their acquisition decisions. The weight of each agent will be dynamically adjusted based on the usefulness of its decisions to improve the performance of the base learner. With adaptive and explicit consideration of both objectives, CbeAL efficiently guides the data acquisition process by selecting informative samples to reduce the human annotation efforts. Furthermore, we characterize the exploration and exploitation capability of the proposed agents theoretically. The evaluation results in a numerical simulation study and a real case study demonstrates the effectiveness and efficiency of CbeAL in manufacturing process modeling of the ICPS. [ABSTRACT FROM AUTHOR]

Enabled by the increasingly available embedded hardware accelerators, the capability of executing advanced machine learning models at the edge of the Internet of Things (IoT) triggers interest of applying Artificial Intelligence of Things (AIoT) systems for industrial applications. The in situ inference and decision made based on the sensor data allow the industrial system to address a variety of heterogeneous, local-area non-trivial problems in the last hop of the IoT networks. Such a scheme avoids the wireless bandwidth bottleneck and unreliability issues, as well as the cumbersome cloud. However, the literature still lacks presentations of industrial AIoT system developments that provide insights into the challenges and offer lessons for the relevant research and industry communities. In light of this, we present the design, deployment, and evaluation of an industrial AIoT system for improving the quality control of HP Inc.'s ink cartridge manufacturing lines. While our development has obtained promising results, we also discuss the lessons learned from the whole course of the work, which could be useful to the development of other industrial AIoT systems for quality control in manufacturing. [ABSTRACT FROM AUTHOR]

Copyright of Environmental & Social Management Journal / Revista de Gestão Social e Ambiental is the property of Environmental & Social Management Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Environmental & Social Management Journal / Revista de Gestão Social e Ambiental is the property of Environmental & Social Management Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The main objective of this work is the study of risk analysis, in the field of pharmaceutical production. Some dangers can affect pharmaceutical companies' personnel, as well as their internal and external environment, during the manufacturing process. Furthermore, the current regulations that governs this very sensitive field of manufacturing and the standards which are scrupulously very sharp. Also see the technical complexity of the industrial systems implemented. These three parameters constitute a real problem to be solved. To do this, we have developed an intelligent technique for monitoring these protection systems, in real time, in order to protect the personnel and the environment. This technique is mainly based on the use of an artificial neural network (ANN) which detects and localizes any anomalies that may occur at any time in the protection system. The experiment was carried out on an isolator belonging to BEKER Laboratories (a medecine manufacturing and development company in Dar El Beida-Algers). The test results allowed us to define the good and bad areas of the isolator operation. We concluded that, it is possible to define defaults in real time, using our new technique. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the editor discusses articles in the issue on topics including breast cancer image classification, intelligent engineering management with data mining, and identifying optimal methods for power grid error parameters.

Process monitoring of industrial production has always been one of the main concerns of process industry systems. As artificial intelligence booms, fault detection and diagnosis via deep learning has been widely used in industrial process monitoring, such as chemical process monitoring flow. Whereas, the current deep framework is difficult to simultaneously reconcile the relationship between different variables and time series caused by the increasing complexity of industrial systems, which reduces the accuracy of fault detection and diagnosis. Considering the significant time series processing potential of long short-term memory (LSTM) networks, this paper proposes a novel two-view LSTM variational auto-encoder, aliased as TVAE. First, the running data in period T is obtained through sliding window, then it utilizes two-view embedding to compress time series information and capture the correlation between time variables, after that it is judged whether it is fault data according to the anomaly score of the variational auto-encoder. Finally, since the encoding process makes the time-dependent and variable dependent features more obvious, the fault characteristic of the encoded data can be obtained by neuron grouping convolution, and then classified for diagnosis. Experimental results on Tennessee Eastman process benchmark show that TVAE is superior to the state-of-the-art methods and provides a new paradigm for industrial process fault detection and diagnosis. [ABSTRACT FROM AUTHOR]

Integrating industrial cyber-physical systems (ICPSs) with modern information technologies (5G, artificial intelligence, and big data analytics) has led to the development of industrial intelligence. Still, it has increased the vulnerability of such systems regarding cybersecurity. Traditional network intrusion detection methods for ICPSs are limited in identifying minority attack categories and suffer from high time complexity. To address these issues, this paper proposes a network intrusion detection scheme, which includes an information-theoretic hybrid feature selection method to reduce data dimensionality and the ALLKNN-LightGBM intrusion detection framework. Experimental results on three industrial datasets demonstrate that the proposed method outperforms four mainstream machine learning methods and other advanced intrusion detection techniques regarding accuracy, F-score, and run time complexity. [ABSTRACT FROM AUTHOR]

Predictive maintenance is one of the most important topics within the Industry 4.0 paradigm. We present a prototype decision support system (DSS) that collects and processes data from many sensors and uses machine learning and artificial intelligence algorithms to report deviations from the optimal process in a timely manner and correct them to the correct parameters directly or indirectly through operator intervention or self-correction. We propose to develop the DSS using open-source R packages because using open-source software such as R for predictive maintenance is beneficial for small and medium enterprises (SMEs) as it provides an affordable, adaptable, flexible, and tunable solution. We validate the DSS through a case study to show its application to SMEs that need to maintain industrial equipment in real time by leveraging IoT technologies and predictive maintenance of industrial cooling systems. The dataset used was simulated based on the information on the indicators measured as well as their ranges collected by in-depth interviews. The results show that the software provides predictions and actionable insights using collaborative filtering. Feedback is collected from SMEs in the manufacturing sector as potential system users. Positive feedback emphasized the advantages of employing open-source predictive maintenance tools, such as R, for SMEs, including cost savings, increased accuracy, community assistance, and program customization. However, SMEs have overwhelmingly voiced comments and concerns regarding the use of open-source R in their infrastructure development and daily operations. [ABSTRACT FROM AUTHOR]

Industrial cyber-physical systems (CPS) are vulnerable to cyberattacks that can compromise their operations, safety, and security. Traditional intrusion detection systems are ineffective in detecting and preventing cyberattacks in industrial CPS due to their dynamic and complex nature. In addition, there is a lack of interpretability and transparency in the decision-making process of IDS, which makes it challenging for system administrators to identify risks. Furthermore, deep learning approaches can be computationally intensive and challenging to deploy and scale in industrial CPS. This study proposes a novel intrusion detection system called TEA-EKHO-IDS that utilises trustworthy explainable artificial intelligence (XAI) and enhanced krill herd optimisation (EKHO) to detect breaches in the CPS. The proposed method uses XAI-EKHO for feature selection, which gives more robust global searching capabilities and faster convergence time by estimating the decision weighting factor. The intrusion detection performance is optimised through the integration of explainable AI, bi-directional LSTM, and Bayesian optimisation (BO-Bi-LSTM) for efficient detection and classification. The proposed approach has been shown to effectively and accurately identify and classify intrusions with a success rate of 98.96%, as demonstrated through experiments and analysis results. The TEA-EKHO-IDS system provides a promising solution for detecting cyber-attacks in industrial CPS, making it a valuable addition to existing industrial security systems. [ABSTRACT FROM AUTHOR]

Anomaly detection with machine learning in industrial inspection systems for manufactured products relies on labelled data. This raises the question of how the labelling by humans should be conducted. Moreover, such a system will most likely always be imperfect and potentially need a human fall-back mechanism for ambiguous cases. We consider the case where we want to optimise the cost of the combined inspection process done by humans together with a pre-trained algorithm. This gives improved combined performance and increases the knowledge of the performance of the pre-trained model. We focus on so-called one-class classification problems which produce a continuous outlier score. After establishing some initial setup mechanisms ranging from using prior knowledge to calibrated models, we then define some cost model for machine inspection with a possible second inspection of the sample done by a human. Further, we discuss in this cost model how to select two optimal boundaries of the outlier score, where in between these two boundaries human inspection takes place. Finally, we frame this established knowledge into an applicable algorithm and conduct some experiments for the validity of the model. [ABSTRACT FROM AUTHOR]

The advent of Industry 4.0 and propelled the application of Artificial Intelligence in different industrial fields and contexts, such as predictive maintenance (PdM). Through its ability to assess the condition of equipment to detect signs of failure and anticipate them, PdM brings several potential benefits in terms of reliability, safety and maintenance costs among many other benefits. Different approaches are proposed in the literature. They are based on data, physic models or knowledge but several problems and limits persist, in particular, to override this dependence on a particular context, to utilize data and business knowledge considering the challenges of applying existing solutions to another context, difficulties associated with data analysis, and uncertainty management. In this context, the goal of this paper is also to highlight the challenges faced in the area of PdM, both for implementation and use-case. PdM remains a hot topic in the context of Industry 4.0 but with several challenges to be better investigated in the area of machine learning, knowledge representation and semantic reasoning applications. [ABSTRACT FROM AUTHOR]

The refrigeration industry is an energy-intensive sector. Increasing the efficiency of industrial refrigeration systems is crucial for reducing production costs and minimizing CO2 emissions. Optimization of refrigeration systems is often a complex and time-consuming problem. This is where technologies such as big data and artificial intelligence play an important role. Nowadays, smart sensorization and the development of IoT (Internet of Things) make the massive connection of all kinds of devices possible, thereby enabling a new way of data acquisition. In this scenario, refrigeration systems can be measured comprehensively by acquiring large volumes of data in real-time. Then, artificial neural network (ANN) models can use the data to drive autonomous decision-making to build more efficient refrigeration systems. [ABSTRACT FROM AUTHOR]

Increasing complexity and data-generation rates in cyber-physical systems and the industrial Internet of things are calling for a corresponding increase in AI capabilities at the resource-constrained edges of the Internet. Meanwhile, the resource requirements of digital computing and deep learning are growing exponentially, in an unsustainable manner. One possible way to bridge this gap is the adoption of resource-efficient brain-inspired "neuromorphic" processing and sensing devices, which use event-driven, asynchronous, dynamic neurosynaptic elements with colocated memory for distributed processing and machine learning. However, since neuromorphic systems are fundamentally different fromconventional von Neumann computers and clock-driven sensor systems, several challenges are posed to large-scale adoption and integration of neuromorphic devices into the existing distributed digital-computational infrastructure. Here, we describe the current landscape of neuromorphic computing, focusing on characteristics that pose integration challenges. Based on this analysis, we propose a microservice-based conceptual framework for neuromorphic systems integration, consisting of a neuromorphic-system proxy, which would provide virtualization and communication capabilities required in distributed systems of systems, in combination with a declarative programming approach offering engineering-process abstraction. We also present concepts that could serve as a basis for the realization of this framework, and identify directions for further research required to enable large-scale system integration of neuromorphic devices. [ABSTRACT FROM AUTHOR]

Current approaches for monitoring machine health (SOH) and effective prognostics depend on the extensive use of complete degradation data trajectories, implying the reliance on data generation techniques that involve functional degradation of the real system until the failure state is reached. These commonly adopted approaches that depend on labeled target data remain operationally and economically nonviable for most industries and safety critical systems. This paper presents novel approaches that alleviate the existing dependence of most prognostics procedures on Remaining Useful Life (RUL) labeled data for training. To this end, firstly, a hybrid data augmentation procedure is proposed that enables the integration of system knowledge available a priori as well as physics of failure, within the training data. Secondly, an unsupervised Health Index (HI) extraction approach is developed, followed by a long-term prediction of this same HI, that leads to an efficient prediction of RUL without labeled data. Finally, a reliability-based assessment is performed to validate the proposed approach. This comprehensive approach (i.e. integrating all the various stages involved in achieving a RUL prediction based on unlabeled data) is tested on a real industrial aircraft system demonstrating the effectiveness of the proposed approach in real industrial context. [Display omitted] • Comprehensive, unsupervised approach adapted to real-life industrial cases (i.e. where no degradation data are available). • Use of physics-based data augmentation to overcome the lack of real degradation data. • Use of the reconstruction error of an autoencoder to extract the Health Index. • Validation of AI-based predictions using established laws of reliability. [ABSTRACT FROM AUTHOR]

Machine-health-surveillance systems are gaining popularity in industrial manufacturing systems due to the widespread availability of low-cost devices, sensors, and internet connectivity. In this regard, artificial intelligence provides valuable assistance in the form of deep learning methods to analyze and process big machine data. In diverse industrial applications, gears are considered a condemning element; many contributing failures occur due to an unexpected breakdown of the gears. In recent research, anomaly-detection and fault-diagnosis systems have been the gears' most contributing content. Thus, in work, we presented a smart deep learning-based system to detect anomalies in an industrial machine. Our system used vibrational analysis methods as a deciding tool for different machinery-maintenance decisions. We will first perform a data analysis of the gearbox data set to analyze the data's insights. By calculating and examining the machine's vibration, we aim to determine the nature and severity of the defect in the machine and hence detect the anomaly. A gearbox's vibration signal holds the fault's signature in the gears, and earlier fault detection of the gearbox is achievable by examining the vibration signal using a deep learning technique. Therefore, we aim to propose a 6-layer autoencoder-based deep learning framework for anomaly detection and fault analysis using a publically available data set of wind-turbine components. The gearbox fault-diagnosis data set is utilized for experimentation, including collecting vibration attributes recorded using SpectraQuest's gearbox fault-diagnostics simulator. Through comprehensive experiments, we have seen that the framework gains good results compared to others, with an overall accuracy of 91%. [ABSTRACT FROM AUTHOR]

Recently, artificial intelligence (AI)-enabled technologies have been widely employed for complex industrial applications. AI technologies can be utilized to improve efficiency and reduce human labor in industrial applications. At the same time, fault diagnosis (FD) and detection in rotating machinery (RM) becomes a hot research field to assure safety and product quality. Numerous studies based on statistical, machine learning (ML), and mathematical models have been available in the literature for automated fault diagnosis. From this perspective, this study presents a novel sandpiper optimization with an artificial-intelligence-enabled fault diagnosis (SPOAI-FD) technique for intelligent industrial applications. The aim is to detect the existence of faults in machineries. The proposed model involves the design of a continuous wavelet transform (CWT)-based pre-processing approach, which transforms the raw vibration signal into a useful format. In addition, a bidirectional long short-term memory (BLSTM) model is applied as a classifier, and the Faster SqueezeNet model is applied as a feature extractor. In order to modify the hyperparameter values of the BLSTM model, the sandpiper optimization algorithm (SPOA) can be utilized, showing the novelty of the work. A wide range of simulation analyses were conducted on benchmark datasets, and the results highlighted the supremacy of the SPOAI-FD algorithm over recent approaches. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI), combined with the Internet of Things (IoT), plays a beneficial role in various fields, including intelligent surveillance applications. With IoT and 5G advancement, intelligent sensors, and devices in the surveillance environment collect large amounts of data in the form of videos and images. These collected data require intelligent information processing solutions, help analyze the recorded videos and images to detect and identify various objects in the scene, particularly humans. In this study, an automated human detection system is presented for a complex industrial environment, in which people are monitored/detected from a top view perspective. A top view is usually preferred because it can provide sufficient coverage and enough visibility of a scene. This study demonstrates the applications, efficiency, and effectiveness of deep learning architectures, that is, Faster Region Convolutional Neural Network (Faster R‐CNN), Single Shot MultiBox Detector (SSD), and You Only Look Once (YOLOv3), with transfer learning. Experimental results reveal that with additional training and transfer learning, the performance of all detection architectures is significantly improved. The detection results are also compared using the same data set. The deep learning architectures achieve promising results with maximum true‐positive rate of 93%, 94%, and 94% for Faster‐RCNN, SSD, and YOLOv3, respectively. Furthermore, a detailed study is performed on output results that highlight challenges and probable future trends. [ABSTRACT FROM AUTHOR]

The mutually beneficial blend of artificial intelligence with internet of things has been enabling many industries to develop smart information processing solutions. The implementation of technology enhanced industrial intelligence systems is challenging with the environmental conditions, resource constraints and safety concerns. With the era of smart homes and cities, domains like automated license plate recognition (ALPR) are exploring automate tasks such as traffic management and fraud detection. This paper proposes an optimized decision support solution for ALPR that works purely on edge devices at night‐time. Although ALPR is a frequently addressed research problem in the domain of intelligent systems, still they are generally computationally intensive and unable to run on edge devices with limited resources. Therefore, as a novel approach, we consider the complex aspects related to deploying lightweight yet efficient and fast ALPR models on embedded devices. The usability of the proposed models is assessed in real‐world with a proof‐of‐concept hardware design and achieved competitive results to the state‐of‐the‐art ALPR solutions that run on server‐grade hardware with intensive resources. [ABSTRACT FROM AUTHOR]

Cyber-physical systems (CPS) play an important role in the implementation of new Industry 4.0 solutions, acting as the backbone infrastructure to host distributed intelligence capabilities and promote the collective intelligence that emerges from the interactions among individuals. This collective intelligence concept provides an alternative way to design complex systems with several benefits, such as modularity, flexibility, robustness, and reconfigurability to condition changes, but it also presents several challenges to be managed (e.g., non-linearity, self-organization, and myopia). With this in mind, this paper discusses the factors that characterize collective intelligence, particularly that associated with industrial CPS, analyzing the enabling concepts, technologies, and application sectors, and providing an illustrative example of its application in an automotive assembly line. The main contribution of the paper focuses on a comprehensive review and analysis of the main aspects, challenges, and research opportunities to be considered for implementing collective intelligence in industrial CPS. The identified challenges are clustered according to five different categories, namely decentralization, emergency, intelligent machines and products, infrastructures and methods, and human integration and ethics. Although the research indicates some potential benefits of using collective intelligence to achieve the desired levels of autonomy and dynamic adaptation of industrial CPS, such approaches are still in the early stages, with perspectives to increase in the coming years. Based on that, they need to be further developed considering some main aspects, for example, related to balancing the distribution of intelligence by the vertical and horizontal dimensions and controlling the nervousness in self-organized systems. [ABSTRACT FROM AUTHOR]

The characteristic of material accumulation makes 3D printing competitive in remanufacturing and repairing. However, conventional repair methods require additional equipment and manual intervention to sequentially finish complicated processes such as global scanning and reverse modeling, which results in efficiency reduction and usage restriction. To address the existing shortcomings, an automatic repair system with artificial intelligence (AI) assistance is developed, which includes a semantic segmentation module, deep reinforcement learning (DRL) module, and composite printing device. The damaged part features are extracted by semantic segmentation from the captured real‐time images to establish DRL maps, where the print motion is simulated and transmitted to the printer. The results indicate that the applied bilateral segmentation network (BiSeNetV2) is 59.03% and 29.90% faster than pyramid scene parsing network (PSPNet) and DeepLabV3+ architecture with satisfying accuracy. The established DRL model based on actual printing achieves the optimization of agent learning speed and print quality. The automatic system improves the repair efficiency by 294% compared to the conventional methods, and enables both structural and electrical repair through high‐temperature polymer–metal printing. This intelligent system enables industrial robots to independently handle unexpected tasks in complex and changeable environments through interdisciplinary knowledge integration of advanced manufacturing and AI. [ABSTRACT FROM AUTHOR]

Predictive maintenance is a field of study whose main objective is to optimize the timing and type of maintenance to perform on various industrial systems. This aim involves maximizing the availability time of the monitored system and minimizing the number of resources used in maintenance. Predictive maintenance is currently undergoing a revolution thanks to advances in industrial systems monitoring within the Industry 4.0 paradigm. Likewise, advances in artificial intelligence and data mining allow the processing of a great amount of data to provide more accurate and advanced predictive models. In this context, many actors have become interested in predictive maintenance research, becoming one of the most active areas of research in computing, where academia and industry converge. The objective of this paper is to conduct a systematic literature review that provides an overview of the current state of research concerning predictive maintenance from a data mining perspective. The review presents a first taxonomy that implies different phases considered in any data mining process to solve a predictive maintenance problem, relating the predictive maintenance tasks with the main data mining tasks to solve them. Finally, the paper presents significant challenges and future research directions in terms of the potential of data mining applied to predictive maintenance. This article is categorized under:Application Areas > Industry Specific ApplicationsTechnologies > Internet of Things [ABSTRACT FROM AUTHOR]

AI methods to build AI methods. Keywords: artificial intelligence; machine learning; autonomous systems; systems engineering; Künstliche Intelligenz; maschinelles Lernen; autonome Systeme; systems Engineering EN artificial intelligence machine learning autonomous systems systems engineering DE Künstliche Intelligenz maschinelles Lernen autonome Systeme systems Engineering 805 814 10 09/06/22 20220901 NES 220901 1 Introduction Systems engineering became necessary at the beginning of the 1940s to develop increasingly complex systems from the different specialist domains. Because of the digitalization and the availability of additional cost-effective methods for Artificial Intelligence (AI), especially Machine Learning (ML), systems receive further potential for value creation. Next to the creation of a unified process of AI systems engineering, the operation of an AI solution also places new demands on existing standards. [Extracted from the article]

Artificial intelligence (AI) has been successfully applied in industry for decades, ranging from the emergence of expert systems in the 1960s to the wide popularity of deep learning today. In particular, inexpensive computing and storage infrastructures have moved data-driven AI methods into the spotlight to aid the increasingly complex manufacturing processes. Despite the recent proverbial hype, however, there still exist non-negligible challenges when applying AI to smart manufacturing applications. As far as we know, there exists no work in the literature that summarizes and reviews the related works for these challenges. This paper provides an executive summary on AI techniques for non-experts with a focus on deep learning and then discusses the open issues around data quality, data secrecy, and AI safety that are significant for fully automated industrial AI systems. For each challenge, we present the state-of-the-art techniques that provide promising building blocks for holistic industrial AI solutions and the respective industrial use cases from several domains in order to better provide a concrete view of these techniques. All the examples we reviewed were published in the recent ten years. We hope this paper can provide the readers with a reference for further studying the related problems. [ABSTRACT FROM AUTHOR]

[Display omitted] • Different percentages of chlorine in potassium chloride and potassium sulfate was detected using hyperspectral imaging. • Different features were extracted from effective hyperspectral image channels. • Effective features were classified using artificial neural network method. • The classification accuracies in potassium chloride and potassium sulfate were equal to 95.6% and 94.4%, respectively. Chlorine in potassium chloride and potassium sulfate must be detected due to its negative effect on soil. Although the laboratory-based chlorine measurement tests are reliable, they are time-consuming, expensive, and requires chemical agents and highly skilled operators. Therefore, the novelty of the present research is developing a fast, accurate, and cheap machine-based method to measure the amount of chlorine. The purpose of this research was to apply hyperspectral imaging and machine learning techniques to detect chlorine content in potassium chloride and potassium sulfate. Different percentages of chlorine in potassium chloride and potassium sulfate products were prepared with ranges of 53.1–50.05 and 1.47–2.13 %, respectively. Hyperspectral images were captured from the sample at the range of 400–950 nm. Mean, minimum, maximum, median, variance, and standard deviation features were extracted from the image channels corresponding to the effective wavelengths. The extracted features were classified using artificial neural network method and highest accuracy of the best models for potassium chloride and potassium sulfate were 95.6 and 94.4, respectively. The combination of hyperspectral imaging and machine learning promises reliable detection of chlorine content in potassium chloride and potassium sulfate in industrial systems with high speed and low cost. [ABSTRACT FROM AUTHOR]

Cybersecurity of the Internet of Things based complex safety–critical systems like the Industrial Internet of Things has gained considerable attention in recent years, focusing on accurate and timely detection of malicious traffic. In cybersecurity, deep learning-driven malicious traffic detection systems are usually used to identify malicious traffic, also called cyber-attacks, because of their capability to provide more accurate predictions from heterogeneous data. In most cases, existing malicious traffic detection systems based on deep learning are unable to detect zero-day attacks and mainly suffer from a high false positive rate, and its prediction is also challenging to understand, even by cybersecurity professionals. Thus, to overcome these limitations, this work proposes an explainable model of malicious traffic detection based on hybrid deep learning techniques. In this model, a lightweight residual network is designed for feature extraction, and a hybrid of Autoencoder and Bidirectional Gated Recurrent Unit-driven deep learning model is proposed for malicious traffic detection. Additionally, the Deep-SHAP-based eXplainable AI technique is employed to understand better how cyber-attacks is detected by the proposed model and which features are responsible for decision-making. A real-time Edge-IIoTset dataset is used to validate and compare the efficiency of a proposed approach with contemporary malicious traffic detection techniques. Results of experiments confirm that the proposed model outperforms existing models in terms of accuracy (94.94%), precision (98.43%), and false positive rate (0.07%) and explain its ability to defend Industrial Internet of Things networks against zero-day cyber-attacks. [ABSTRACT FROM AUTHOR]

• Developed a physics-informed probabilistic deep neural network (PIPDN) for fault diagnostics of mechanical system. • The PIPDN can provide trustworthy diagnosis while generating smart data for large-scale AI modelling.. • Developed a multi-scale (MS) diagnostic model based on the PIPDN. • Revealed diagnosis mechanism of MS-PIPDN model. • Proposed an Uncertainty Quantification-based decision-fusion module for improving diagnosis reliability and performance of MS-PIPDN. The application of data-driven models based on the neural network is pivotal to developing an intelligent fault diagnostic flowchart. However, the reliability and interpretability of these models for fault prediction have presented challenges in neural network-based diagnostic approach. Another challenge is data availability, which has also been a limiting factor in using artificial Intelligence for condition monitoring and fault assessment in industrial mechanical systems. Consequently, this study proposes a Physics Informed Probabilistic Deep Network (PIPDN) framework to overcome these challenges. The PIPDN comprises two main components: the physical labelling module, designed to enhance physical labels with mechanical failure information, and the main body of PIPDN, responsible for learning fault representative features and generating smart data guided by conditional and physical labels. Furthermore, a multi-scale PIPDN model is developed to integrate the proposed uncertainty quantification (UQ) with decision-fusion module for accurate interpretation and enhanced fault diagnosis. The applicability, effectiveness, and superiority of the proposed framework and approach are validated using an experimental bearing dataset. The results indicate that integrating physical labels significantly assists the PIPDN model in capturing more accurate fault characteristics. This increases the importance of latent space features for subsequent fault diagnosis and also enhances the diagnostic interpretability. Furthermore, the addition of UQ-based decision-making module improves the reliability of the MS-PIPDN model by reducing epistemic uncertainty in the predictions. [ABSTRACT FROM AUTHOR]

The design of real-world industrial systems is subject to a natural tendency towards modularization in order to manage complexity. In addition, this article considers that patterns of self-similarity in many problem domains have made many such solutions naturally representable as holarchies. Likewise, the increasing need for autonomous local decision making as well as the demand to produce solutions at scale has increased the relevance of the multi-agent paradigm to the creation of modern software systems. A variety of software development patterns are explored for their compatibility with holonic multi-agency. The current skill sets required by software development workers and concomitant training activities focus on instilling computational thinking abilities, a set of related cognitive competencies useful in the development of such systems. Intelligent systems play an increasingly important role in modern development and often benefit from computational intelligence techniques for the purpose of parameter tuning. This position paper explores the intersections between holonic multi-agency, modern information systems development, the computational intelligence which train them and the computational thinking skills those developers should be trained in. [ABSTRACT FROM AUTHOR]

In the era of big data, the pervasive use of artificial intelligence (AI) technology has revolutionized various industries. AI-powered systems, particularly those utilizing data-driven interpretable and reliable methods for accurate condition identification, have emerged as a crucial factor in achieving intelligent industrial systems. However, in real industrial sites, the labels of offline data often contain incorrect labels, i.e. label noise, due to human error, sensor failure, and other sources, which reduces the accuracy of the model and affects the performance and safety of the industrial system. To tackle the challenge of precarious performance caused by label noise, this paper proposes a robust method called Trusted Connection Dictionary Learning (TCDL) which effectively mitigates the adverse effects of label noise through interpretable constraints and guarantees the trustworthiness of the model for industrial applications. Specifically, to address the issue of data structure and label inconsistency arising from label noise, this paper presents a dynamic graph model that jointly optimizes data features and label information to obtain consistent representations of them. Subsequently, to effectively fit the labeled data, TCDL leverages the label information from the nearest neighbors through the optimized graph structure and facilitates the self-correction of label noise, leading to robust representations of process features and a reliable condition classifier. Finally, a novel iterative optimization algorithm that combines the Block Coordinate Descent (BCD) method and the Alternating Direction Multiplier Method (ADMM) is also developed to ensure the convergence of the algorithm. Due to simple constraints, it can obtain accurately optimized variables with few iterations. Numerical simulations and industrial experiments demonstrate the superiority of the proposed method compared to some state-of-the-art methods. • This paper proposes a robust condition identification method against label noise. • A dynamic graph is constructed to label noise correction and label propagation. • Experiments demonstrate the superiority and trustworthy of the proposed method. [ABSTRACT FROM AUTHOR]