Search

In the course of manufacturing excellence, decision makers are consistently confronted with the task of making choices that will enhance and meet industrial plant's requirements. To this end, it is essential to maintain machines and equipment in a timely manner, which can prove to be one of the primary challenges. Predictive maintenance (PdM) strategy can enable real-time maintenance, providing numerous benefits such as reduced downtime, lower costs, and improved production quality. This article tries to demonstrate efficient physical parameters used in PdM field. The paper presents a case study operated in industrial production process to compare between the most used algorithm in predicting equipment failures. Future research can improve prediction accuracy with other artificial intelligence tools. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence, big data, Internet of Things, and other technologies, digital twin has gained great attention and become a current research topic. Using digital twin technology, the digital twin model can be constructed in the cyber space that is fully equivalent to the physical entity. It is always consistent with the physical entity in the operation process, which greatly improves the dynamic perception and prediction ability of the real world. After the development in recent years, digital twin has gradually changed from the initial concept discussion to the study of model framework and implementation method. However, because the research objects in different industries have great differences in their own composition, service conditions, and application scenarios, they have personalized characteristics in modeling strategies and usage methods. Therefore, based on different industries, this paper reviews the current articles on digital twins and distinguishes the focus of digital twin modeling research; subsequently, the relevant supporting techniques and methods are summarized according to their different importance for digital twin modeling. Based on the review in this paper, future researchers can conduct targeted research on digital twin technology in term of the characteristics of the objects in their industry. [ABSTRACT FROM AUTHOR]

This paper aims to develop an effective sensor fusion model for turning processes for the detection of tool wear. Fusion of sensors' data combined with novelty detection algorithm and learning vector quantisation (LVQ) neural networks is used to detect tool wear and present diagnostic and prognostic information. To reduce the number of sensors required in the monitoring system and support sensor fusion, the ASPS approach (Automated Sensor and Signal Processing Selection System) is used to select the most appropriate sensors and signal processing methods for the design of the condition monitoring system. The experimental results show that the proposed approach has demonstrated its efficacy in the implementation of an effective solution for the monitoring tool wear in turning. The results prove that the fusion of sensitive sensory characteristic features and the use of AI methods have been successful for the detection and prediction of the tool wear in turning processes and show the capability of the proposed approach to reduce the complexity of the design of condition monitoring systems and the development of a sensor fusion system using a self-learning method. [ABSTRACT FROM AUTHOR]

With the increasing complexity of CNC machine tools and other rotating machinery, it becomes more and more important to improve the reliability of such machines. It is necessary to estimate the remaining useful life (RUL) of the important parts such as bearings of these devices. However, the operating conditions of such parts are often very complicated, and there is a great difference between different devices. Therefore, it is difficult to use the traditional mechanism analysis method, which not only is very hard, but also generally has low prediction accuracy. In order to solve the above problems, this paper proposes a feature-transferred prediction network (FTPN), which can adapt to various working conditions, combining with the neural network method in the field of artificial intelligence, and effectively realizes RUL prediction. Since the existing neural network methods were originally proposed to solve the problems in other fields, such as semantic recognition, this paper uses the feature transfer method to improve them. Firstly, the source network based on convolutional neural network (CNN) is pre-trained for fault recognition, and the fault feature information extracted after training is stored in the fault feature layer. Second, CNN and gate recurrent unit (GRU) are used to build target networks and fit the relationship between time series and remaining longevity. Finally, a special loss function is designed to transfer the features extracted from the source network to the target network to help the target network learn fault features and better predict the mechanical RUL. In order to verify the effectiveness of the proposed method, experiments are carried out using the public data set of accelerated life of bearings, and high prediction accuracy is obtained, which proves that the proposed method has certain generalization. The comparison with the existing methods on the same data set shows that the proposed method has a broad industrial application prospect. [ABSTRACT FROM AUTHOR]

The digital industrial revolution calls for smart manufacturing plants, i.e. plants that include sensors and vision systems accompanied with artificial intelligence and advanced data analytics in order to meet the required accuracy, reliability and productivity levels. In this paper, we introduce a surface analysis and classification approach based on a deep learning algorithm. The approach is intended to let machining centres recognise the adequacy of process parameters adopted for the milling operation performed, based on the phenomenological effects left on the machined surface. Indeed, the operator will be able to understand how to change process parameters to improve workpiece quality of subsequent parts by a reverse engineering procedure that reconstructs the process parameters that generated the analysed surface. A shallow convolutional neural network was proposed to work on surface image patches based on a limited training dataset of optimal and undesired cutting conditions. The architecture consists of a series of 3 stacked convolutional blocks. The performance of the proposed solution was validated through 5-fold cross-validation, measuring the mean and standard deviation of the f1-score metric. The algorithm arrived at outperformed the best state-of-the-art approach by 4.8% when considering average classification performance. [ABSTRACT FROM AUTHOR]

Metal additive manufacturing (AM) has the advantages of novel part morphology, new material property, and short production cycle, attracting significant attention in automobile, aerospace, and other fields. Nevertheless, the repeatability and stability of part quality are difficult to guarantee in the current metal AM process, hindering the development of metal AM technology. Vital process variables such as molten pool characteristics, spatter characteristics, surface morphology, and radiation temperature are directly related to the quality of parts. Monitoring the dynamic changes vital variables is critical. Image processing techniques such as image transformation, recognition, segmentation, and enhancement are introduced to obtain manufacturing process information through processing and analyzing rich image features. The monitoring system's processing results are usually collected in real time to help solve the repeatability and stability problems of the metal AM process. Presently, in situ and real-time monitoring methods are the most popular, and unfortunately, the literature lacks a comprehensive report. Thus, this paper thoroughly describes in situ and real-time process monitoring on the basis of image processing for metal AM. This paper reviews the in situ and real-time monitoring on the basis of traditional image processing to analyze monitoring objects, process classifications, and image processing carriers. Then, the advantages and disadvantages of in situ and real-time monitoring of metal AM based on artificial intelligence are discussed and compared. Finally, image processing algorithm generalization, quality, small samples, and image labeling problems are analyzed and discussed. A technical route for metal AM real-time feedback control is proposed by combining image processing with other technologies. [ABSTRACT FROM AUTHOR]

In the age of Industry 4.0 and smart manufacturing, traditional production processes are undergoing significant changes due to the integration of advanced technologies like automation, robotics, big data analytics, and machine learning, which are enhancing productivity and manufacturing efficiency. The center of this evolution is the introduction of the digital twin (DT), the digital replicas of physical assets that blend real-time data with advanced analytics and simulations. Ensuring synchronization between the digital replica and its physical counterpart is crucial for successfully implementing digital twins. This paper addresses the challenge of achieving and quantifying synchronization within DTs, focusing on replicating physical system behavior and measuring deviations or delays. The study delves into the critical aspects of synchronization within digital twin applications, focusing on its implications for a robotic assembly system. The research successfully harnessed YOLOv8 to facilitate real-time event tracking and synchronization characterization, highlighting the potential of object detection deep-learning models in enhancing synchronization accuracy and, consequently, the efficiency and reliability of manufacturing processes. [ABSTRACT FROM AUTHOR]

Rapid tool wear is a major concern of the machining operation, affecting the tooling cost and dimensional tolerance of the components. In line with Industry 4.0, rapid tool failure can be avoided by applying cyber-physical tool condition monitoring (TCM), which detects in-process tool wear evolution using sensors or machine vision systems, determining the actual time for tool replacement. Although sensor-based TCM is quick and adaptive in monitoring tool wear progression online, it cannot detect the failure modes to show the extent of wear severity on the tool's cutting edge. On the other hand, machine vision systems effectively detect wear mechanisms that accelerate tool failure during machining. Therefore, this paper presents the practical application of machine vision systems in TCM and tool performance optimization (TPO). The findings in this research show that digital microscopes are used to monitor wear mechanisms, complementing TPO techniques in selecting the best cutting parameters that optimize tool performance. However, such techniques are time intensive and inefficient for real-time applications. With recent advances in imaging technology and artificial intelligence, an in-process machine vision-based TCM (MV-TCM) system is receiving more attention in intelligent manufacturing due to its efficient predictive capability. However, it is still in its infancy stage, relying on classical machine learning models, which are ineffective to extract high-level features on the tool wear images for in-process failure modes detection. Therefore, this paper highlights the significance of applying artificial intelligence to enhance MV-TCM capability for online failure modes detection and classification. [ABSTRACT FROM AUTHOR]

The potential benefits of Industry 4.0 have led to an increased interest in smart manufacturing. To facilitate the self-diagnosis and adaptive ability in smart milling system, a digital twin–driven intelligent algorithm for monitoring in-process milling parameters is proposed here. The algorithm can extract the radial width of cut, axial depth of cut, cutter runout parameters, and cutting constants in the end milling process at the same time only by using force sensor. It is an important breakthrough in this paper to converge two different force models to realize cyber-physical fusion for identifying milling parameters in the milling process. By using the convolution force model, digital twin technology can extract the approximate solution of milling parameters in the machining process in advance, so as to narrow the range of solution. Furthermore, the subsequent artificial intelligence algorithm can find the accurate solution of the current milling parameters in a short calculation time by cyber-physical fusion with the numerical force model considering cutter runout effect. Milling experiments are carried out to validate the proposed algorithm. It is shown that due to the complementary advantages of the convolution force model and numerical force model, the algorithm proposed in this paper can give consider to the identification accuracy and calculation efficiency. [ABSTRACT FROM AUTHOR]

Disassembly of e-waste has received significant attention over the past decades to extract value-added parts or components for recovery or reuse. It is imperative to develop automatic disassembly to replace human workers thus safeguarding them against the hazardous environment. Most scholars investigate the disassembly of e-waste from a technical perspective on laboratory scale. Few types of research related to its development track and scaled application are completed. This paper attempts to fill this gap by analyzing the disassembly of Waste Electrical and Electronic Equipment (WEEE) in a strategic perspective from manual operation, (semi)-automation to intelligent disassembly through a systematic literature review. The main barriers to automating the recycling industry lie in the high complexity and uncertainty of end-of-life (EOL) products that perplex the automatic handling and planning. Intelligent systems integrated in cognitive robots are helpful to handle the uncertainty through learning and revision processes. This work has three objectives: first, to map out what research has been carried out in the field of WEEE disassembly and the necessity for disassembly automation; second, to conduct a systematic literature review for the state of the art of automatic disassembly and discuss the barriers to its industrial application; third, to propose a perspective for integrating Industry 4.0 technologies with disassembly automation to promote flexibility and efficiency, providing a new scheme for future treatment of WEEE. [ABSTRACT FROM AUTHOR]

The selection of appropriate cutting tool (CT) is a critical part of machining. Selecting the right tool for the right job will enable customers to achieve economic machining, saving time and cost while delivering high-quality products. Nowadays, the complexity of CT and workpiece is increasing; this changes the input and output requirements for cutting tool selection paving way to automation. There are two types of CT selection methods, manual and automated CT selection. This article focuses on automated CT selection, which has different inputs and outputs based on the algorithm/AI technique used. The potential and promising aspects of CT selection could enhance the machining in terms of productivity, time, cost, and quality aspects. A comprehensive review of automated CT selection methods has been presented in this paper. The review surveys different automated CT selection methods in terms of inputs, outputs, and artificial intelligence (AI) techniques/different algorithms since most of the researchers have not focused on this perspective. It outlines the current status of research and application, which has the potential to improve the automated CT selection methods for the benefit of the manufacturing industry. [ABSTRACT FROM AUTHOR]

Sensors are the main equipment of the data-based enterprises for diagnosis of the health of system. Offering time- or frequency-dependent systemic information provides prognosis with the help of early-warning system using intelligent signal processing systems. Therefore, a chain of data-based information improves the efficiency especially focusing on the determination of remaining useful life of a machine or tool. A broad utilization of sensors in machining processes and artificial intelligence–supported data analysis and signal processing systems are prominent technological tools in the way of Industry 4.0. Therefore, this paper outlines the state of the art of the mentioned systems encountered in the open literature. As a result, existing studies using sensor systems including signal processing facilities in machining processes provide important contribution for error minimization and productivity maximization. However, there is a need for improved adaptive control systems for faster convergence and physical intervention in case of possible problems and failures. On the other hand, sensor fusion is an innovative new technology that makes decisions using multi-sensor information to determine tool status and predict system stability. It is currently not a fully accepted and practiced method. In a nutshell, despite their numerous advantages in terms of efficiency, time saving, and cost, the current situation of sensors used in the industry is not a sufficient level due to the investment cost and its increase with additional signal acquisition hardware and software equipment. Therefore, more studies that can contribute to the literature are needed. [ABSTRACT FROM AUTHOR]

Welding monitoring technology based on machine vision has been widely researched in academic and industry, especially in the background of Industry 4.0, in that it can contribute to welding quality and productivity improvement. This paper outlines the technical points of welding status monitoring based on machine vision, including hardware and software. First of all, in the hardware part, the active and passive vision systems are briefly introduced, as well as the key steps in experimental deployment, such as the configuration of optical sensors and optical filters based on different detection objects. Secondly, some related image processing techniques in welding monitoring are also comprehensively reviewed. Additionally, the observed objects and their morphological characteristics of vision-based welding process monitoring are enumerated. On this basis, a series of intelligent models as well as optimization methods for recognition and classification in visual monitoring are considered in detail. Finally, potential research challenges and open research issues of welding visual monitoring are discussed to present an insight into future research opportunities. The main purpose of this paper is to provide a reference source for the researchers involved in intelligent robot welding. [ABSTRACT FROM AUTHOR]

In the context of Industry 4.0, condition-based maintenance (CBM) for complex systems is essential in order to identify failures and mitigate them. After the identification of a sensor set that guarantees the system monitoring, three main problems must be addressed for effective CBM: (i) collection of the right data; (ii) choice of the optimal technique to identify the specific dataset; (iii) correct classification of the results. The solutions currently used are typically data driven and, therefore, the results are variable, as it is sometimes challenging to identify a pattern for all specific failures. This paper presents a solution that combines a data driven approach with an in-depth knowledge of the mechanical system's behaviour. The choice of the right sensor set is calculated with the aid of the software MADe (Maintenance Aware Design environment), whereas the optimal dataset identification technique is pursued with a second tool called Syndrome Diagnostics. After an overview of such methodology, this work also presents RSGWPT (redundant second-generation wavelet packaged transform) analysis to show different possible outcomes depending on the available sensor data and to tailor a detection technique to a given dataset. Supervised and unsupervised learning techniques are tested to obtain either an anomaly detection or a failure identification depending on the chosen sensor set. By using the described method, it is possible to identify potential failures in the system so to awarely implement the optimal maintenance actions. [ABSTRACT FROM AUTHOR]

With the development and application of advanced technologies such as Cyber Physical System, Internet of Things, Industrial Internet of Things, Artificial Intelligence, Big Data, Cloud Computing, Blockchain, etc., more manufacturing enterprises are transforming to intelligent enterprises. Smart manufacturing systems (SMSs) have become the focus of attention of some countries and manufacturing enterprises. At present, there are some applications of SMSs in different industrial fields. However, there is still a lack of a unified definition of SMSs and a unified analysis of requirements. In order to have a comprehensive understanding of SMSs, this paper summarized the evolution, definition, objectives, functional requirements, business requirements, technical requirements, and components of SMSs. At the same time, it points out the current development status and level. Based on above, an autonomous SMSs model driven by dynamic demand and key performance indicators is proposed. Through the review of this paper, the reference can be provided for the transformation of more manufacturing enterprises from the traditional to the intellectualized ones. [ABSTRACT FROM AUTHOR]

Recently, artificial intelligence (AI) technology receives extensive attention in the manufacturing field. As the core technology, it generates considerable interest among smart manufacturing and Industry 4.0 strategy. Product lifecycle management (PLM) copes with various kinds of engineering, business, and management activities concerning a product throughout its whole lifecycle—from the inception of an intangible concept through the recycling of a finished product. In the context of smart manufacturing, this paper reviews various theories, algorithms, and technologies of AI to different stages of PLM (i.e., product design, manufacturing, and service). A structured roadmap is presented to navigate the future research and application of AI in PLM. This paper also discusses the opportunities and challenges of applying AI for PLM. [ABSTRACT FROM AUTHOR]

The manufacturing sector is a fundamental pillar of worldwide economies, contributing markedly to global economic growth. However, the manufacturing industry is persistently confronted with issues impeding its development and expansion, such as manpower shortages, safety concerns, high initial investment for installation, and long return on investment. Within this context, machine tending has become a crucial component of the manufacturing process and potentially serves as a viable solution to the afore-mentioned predicaments. Over the past 5 years, implementing automated machine-tending systems has widely extended from simulation or laboratory environments to practical applications in manufacturing workshops as robotics and artificial intelligence develop rapidly. To fully benefit from the potential of machine-tending applications, it is necessary to comprehend and tackle its associated challenges. Therefore, this paper aims to contribute to the evolution of machine-tending applications by investigating the impacts of emerging trends of advanced technologies, such as autonomous mobile robots, computer vision, machine learning, and deep learning. This systematic literature review is based on the Protocol of Preferred Reporting Items for Systematic Review and Meta-Analyses to analyze the 50 scientific literature related to machine tending in the last five years. [ABSTRACT FROM AUTHOR]

Industry 4.0 promotes highly automated mechanisms for setting up and operating flexible manufacturing systems, using distributed control and data-driven machine intelligence. This paper presents an approach to reconfiguring distributed production systems based on complex product requirements, combining the capabilities of the available production resources. A method for both checking the "realisability" of a product by matching required operations and capabilities, and adapting resources is introduced. The reconfiguration is handled by a multi-agent system, which reflects the distributed nature of the production system and provides an intelligent interface to the user. This is all integrated with a self-adaptation technique for learning how to improve the performance of the production system as part of a reconfiguration. This technique is based on a machine learning algorithm that generalises from past experience on adjustments. The mechanisms of the proposed approach have been evaluated on a distributed robotic manufacturing system, demonstrating their efficacy. Nevertheless, the approach is general and it can be applied to other scenarios. [ABSTRACT FROM AUTHOR]

Real-time health condition monitoring of bearings plays a significant role in the functionality of the rotary machinery. Multi-channel sensor fusion can be more robust for identifying diverse bearing fault diagnosis scenarios. However, the high-dimensional data and complex fault scenarios that can occur in the system pose significant challenges for effective fault diagnosis. State-of-the-art artificial intelligence-based bearing fault diagnosis system involves multi-channel sensor fusion, which usually leverages time–frequency analysis, feature extraction, and supervised learning. Nevertheless, those methods usually require a large training dataset for the machine learning model development. This paper proposes a new multi-channel sensor fusion methodology, named frequency-domain multilinear principal component analysis (FDMPCA), by integrating acoustics and vibration signals with different sampling rates and limited training data. Frequency analysis is firstly leveraged to transform the original signals from time to frequency domain, and the frequency responses of heterogeneous channels form a tensor structure named the frequency-domain (FD) tensor. Subsequently, the FD tensor is decomposed by multilinear principal component analysis (MPCA), resulting in low-dimensional process features for fault diagnosis. Finally, the extracted features can be used to train a Neural Network (NN) model for fault diagnosis. To validate the effectiveness of the proposed method, the bearing fault experiments were conducted on a machinery fault simulator while multiple vibration and acoustic signals were collected. Experimental results demonstrated that the proposed approach can effectively identify the machine fault conditions and outperform the benchmark methods given the limited training data. [ABSTRACT FROM AUTHOR]

With the in-depth integration of intelligent manufacturing and energy-efficient manufacturing, energy consumption should be taken as an important indicator to meet the development philosophy of low-carbon manufacturing while continuously pursuing manufacturing efficiency. The intelligent estimation of energy consumption for machined parts is the basis for establishing an energy-efficient intelligent manufacturing system. STEP-NC is one of the practical schemas to implement an intelligent manufacturing mode in the CNC machining field. Hence, this paper proposed an estimation methodology of energy consumption based on the STEP-NC program to realize the estimation of the staged and overall energy consumption for parts. Firstly, the influencing factors of energy consumption are analyzed in detail and the data model of energy consumption is extended to the STEP-NC standard accordingly. Secondly, the energy consumption estimation methodology based on the machining feature was constructed, and the mapping relationship between STEP-NC program and the estimation method was established. Finally, the energy consumption estimation framework with the STEP-NC program as input is developed while the validity of the methodology is verified by practical machining experiments. By comprehensive analysis, the methodology shows promising results in efficiency and application prospect, which lays a foundation for further intelligent energy-efficient research. [ABSTRACT FROM AUTHOR]

The industrial domain is undergoing a major transformation, pushed forward by emerging technologies originating from research or industry. The resulting trend, better known by the term Industry 4.0, advances automation within these manufacturing companies by providing ubiquitous interconnection. This enables the integration of technologies mainly used in the Industrial Internet of Things (IIoT), Cyber-physical Systems (CPS) or Big Data with the goal to optimize production processes or facilitate intelligent decision-making. While those processes are progressively supported by methodologies coming from the area of artificial intelligence (AI) like machine learning algorithms, sustainable and consistent storing of production data becomes increasingly important. Concluding, production systems engineering and information engineering are correlating with each other, as the respective results could be used to the advantage of the respective other discipline. In order to address these issues while developing such flexible production systems, the Reference Architecture Model Industrie 4.0 (RAMI 4.0) has been introduced. However, practical applications are lacking as this standard is mainly described in theory, which makes it difficult to actually apply this framework. Thus, the main goal of this paper is to specify a detailed architecture description of the Information Layer to ensure the practical application of RAMI 4.0, which allows stakeholders to utilize model-based Systems Engineering (MBSE) for developing data aspects of industrial systems on the one hand and enable Information Engineering on the other hand. Supported by the concept of the Zachman Framework, the resulting architecture is applied and validated with the help of a real-world case study. [ABSTRACT FROM AUTHOR]

The selection of a non-traditional machining (NTM) process is often observed to be a multi-criteria decision-making problem with conflicting and diverse objectives. This paper presents a systematic methodology for selecting the best or optimal non-traditional machining process under constrained material and machining conditions. The paper also includes the design of an analytic-hierarchy-process-based expert system with a graphical user interface to ease the decision-making process. The developed expert system relies on the priority values for different criteria and sub-criteria, as related to a specific non-traditional machining process selection problem. It also depends on the logic table to discover the non-traditional machining processes that lie in the acceptability zone, and then selects the optimal process having the highest acceptability index value. The proposed expert system can automate the selection of a non-traditional machining process and provide artificial intelligence in the multi-criteria decision-making process. [ABSTRACT FROM AUTHOR]

The visual path–following technology is widely used in cutting, laser welding, painting, gluing, and other fields, which is a crucial content of robotics studies. As an important algorithm of artificial intelligence (AI), reinforcement learning provides a new insight for robots to learn path-following skills which has the ability of machine vision and decision making. In order to build a robotic agent with path-following skills, this paper proposes a visual path–following algorithm based on artificial intelligence deep reinforcement learning double deep Q-network (DDQN). The proposed approach allows the robot to learn path-following skill by itself, using a visual sensor in the Robot Operating System (ROS) simulation environment. The robot can learn paths with different textures, colors, and shapes, which enhances the flexibility for different industrial robot application scenarios. Skills acquired in simulation can be directly translated to the real world. In order to verify the performance of the path-following skill, a path randomly hand-drawn on the workpiece is tested by the six-joint robot Universal Robots 5 (UR5). The simulation and real experiment results demonstrate that robots can efficiently and accurately perform path following autonomously using visual information without the parameters of the path and without programming the path in advance. [ABSTRACT FROM AUTHOR]

The manufacturing precisions of machine tools are seriously affected by high-speed spindle thermal error, especially the axial thermal deformation. A thermal error prediction model is an effective and economical approach to enhance the accuracy of machine tools, which is based on various artificial intelligence algorithms. This paper puts forward a novel optimal effective composite model (OM) for spindle thermal error prediction, which integrates the advantages of both gray model (GM(1,n)) and least squares support vector machine (LS-SVM) in terms of the experiment sample data. In the first place, the GM(1,n) and the LS-SVM are borrowed to establish the spindle thermal error prediction model, respectively. Then, the OM model is built by optimizing and adjusting the weighting coefficient of GM(1,n) and LS-SVM model, which is predicted by practical thermal error sample data. Finally, the prediction accuracy of the OM model is better than GM(1,n) model and LS-SVM by comparing the above models. After compensation, the maximum spindle thermal error, dropping from 16.4 to 3.5 μm, is significantly reduced with a droop rate of 78.7%. Therefore, the results show that, comparing with traditional GM(1,n) and LS-SVM method, the OM presented in this paper is more accurate and robust for thermal error prediction and compensation under complex machining conditions, which has preliminarily industrial application prospect. [ABSTRACT FROM AUTHOR]

Industry 4.0 is characterized by a modular structure of the production process that consists of cyber-physical systems. These cyber-physical systems provide interoperability, information transparency, and decentralization of decisions. The modular structure, according to Industry 4.0 principle, creates intelligent networks of machines, work pieces, and systems that can predict failures, self-organize themselves, and react to unexpected events. In this paper, we consider the complexity of assembly processes and propose modular structures for assembly processes based on probabilistic formulation. Despite the reliability and precisions that the use of cyber-physical systems such as robotics and automation in assembly processes have introduced, and because of the increasing complexity, there is a need for probabilistic process characterization models for smart assembly planning purposes. First, a new framework for assembly complexity measurement based on processes' probabilistic and Markovian characters is suggested. Then, two effects of modularization, namely stabilization of components by boundary creation and application modular interfaces, are analyzed. For each case, a probabilistic formulation for assembly formation and analysis is presented. The effect of task sequencing and component modularization on assembly time and cost is considered simultaneously by the Bayesian formulation of the assembly problem. Several heuristics are derived from simulation examples, and the modularization cost is studied through utilization of design structure matrix. [ABSTRACT FROM AUTHOR]

Ball screw feed-drive system (BSFDS) is the precision transmission mechanism widely used in micron-scale positioning or motion trajectory control. Its desired specifications including high acceleration, speed, accuracy, and stability are challenged by vibration, friction, thermal error, uncertainty, etc. Inspired by these challenges, the modeling and control issues have been widely studied and discussed for decades. This paper presents an overview of modeling and control approaches, including identification, linear parameter varying, thermal error modeling and control, nonlinear control, and robust control. In particular, it reviews the emerging control issues and approaches, such as artificial intelligence, learning control, and data-driven control, which have increased in recent years. [ABSTRACT FROM AUTHOR]

The manufacturing process of semiconductors has become complex due to the ultra-fine chemical process technologies, and a large amount of testing process is also needed to find out yield-reducing defects of wafers. In order to utilize the cost of visual inspection, several artificial intelligence techniques have been proposed to detect systematic defects. Despite these efforts, semiconductor process still relies on time-consuming manual inspections carried out by quality engineers to detect and classify defects because of lack of efficiency and reliability for AI technologies. In this paper, we propose a morphological feature transformation for 3D wafer bin maps and an automatic embedding technique based on simultaneous optimization. Since proposed technique removes unnecessary features and embeds them into feature vectors related to more meaningful WBM patterns, high cluster quality can be obtained only with the similarity of feature vectors, enabling classification without labels. Proposed idea provides a solution for open set recognition problems and a quicker and more efficient method of the detection and classification of wafer defects in commercial manufacturing processes. [ABSTRACT FROM AUTHOR]

Additive manufacturing (AM) is an advanced near net shape manufacturing technology that facilitates the formation of complex shaped products from a digital 3D design. Freedom of design, minimal scrap formation, and mass customization make AM technology dominant over conventional methods. Recently, metal additive manufacturing (MAM) gained ambience owing to the ever-increasing demand for complex and customized metallic parts/components in aerospace, biomedical, automotive and marine industries. However, the parts/components produced by MAM cannot be directly employed in practical applications due to the poor surface integrity and loss of dimensional accuracy. Metallic AM surfaces are characterized by staircase effect, balling phenomena, lack of fusion defects, porosities and cracks. In order to overcome the aforementioned problems, several post-processing methods have been introduced by researchers over the years. These include laser polishing, abrasive finishing, chemical and electrochemical polishing, conventional finishing, electrical discharge polishing, and some other hybrid methods. The principle of operation, significant outcomes in terms of surface modification as well as pros and cons of each of these methods are discussed in detail in this review article. The comprehensive outlook of the paper establishes a foundation of reference for future research works in the area of post-processing metallic AM components. Moreover, the future path of research ahead in the domain of post-processing methods has been discussed with special attention on automation of finishing methods using machine learning and artificial intelligence. [ABSTRACT FROM AUTHOR]

Rapid developments in artificial intelligence and image processing have presented many new opportunities for defect detection in manufacturing processes. In this work, an intelligent image processing system has been developed to monitor inter-layer deposition quality during a wire arc additive manufacturing (WAAM) process. This system reveals the feasibility and future potential of using computer vision knowledge in WAAM. Information produced from this system is to be used in conjunction with other quality monitoring systems to verify the quality of fabricated components. It is tailored to identify the presence of defects relating to lack of fusion and voids immediately after the deposition of a given layer. The image processing system is built upon the YOLOv3 architecture and through moderate changes on anchor settings and achieves 53% precision on surface anomaly detection and 100% accuracy in identifying the fabricated components' location, providing a prerequisite for high-precision assessment of welding quality. The work presented in this paper presents an inter-layer vision-based defect monitoring system in WAAM and serves to highlight the feasibility of developing such intelligent computer vision systems for monitoring the WAAM process for defects. [ABSTRACT FROM AUTHOR]

Industrial systems resources are capable of producing large amount of data. These data are often in heterogeneous formats and distributed, yet they provide means to mine the information which can allow the deployment of intelligent management tools for production activities. For this purpose, it is necessary to be able to implement knowledge extraction and prediction processes using Artificial Intelligence (AI) models, but the selection and configuration of intended AI models tend to be increasingly complex for a non-expert user. In this paper, we present an approach and a software platform that may allow industrial actors, who are usually not familiar with AI, to select and configure algorithms optimally adapted to their needs. Hence, the approach is essentially based on automated machine learning. The resulting platform effectively enables a better choice among the combination of AI algorithms and hyper-parameters configurations. It also makes it possible to provide features of explainability of the resulting algorithms and models, thus increasing the acceptability of these models in practicing community of the users. The proposed approach has been applied in the field of predictive maintenance. Current tests are based on the analysis of more than 360 databases from the subjected field. [ABSTRACT FROM AUTHOR]

Many advances have been made in stereo-vision-based tube measurement. This approach is characterised by its accuracy, level of automation, non-contact nature, reliability, simplicity of operation and speed. Many studies have indicated that multi-stereo-vision technology can solve the occlusion problem and be used to efficiently and accurately measure complicated tubes. Increasing demand for fast and accurate quality control of tubes has significantly improved the confidence of users of this technology. The purpose of this paper is to review the research papers published in the tube measurement based on stereo-vision research area. Following a detailed introduction, this paper first discusses the measurement problem and requirements and then reviews the current state of academic research on the key techniques, including three-dimensional (3D) reconstruction, parameter calculation and accuracy verification. This is followed by a summary and conclusion. This paper's aim is to help interested researchers find the suitable and accurate 3D reconstruction method of different kinds of tubes in the literature and set up a tube measurement system quickly. [ABSTRACT FROM AUTHOR]

The industrial Internet of Things (IIoT) has grown to empower advantages of advanced manufacturing machinery and smarter control. The cloud-based technology of remote data collection, intelligent machine interconnectivity, and sensor monitoring provide the opportunity for a pattern modification across all manufacturing divisions including the latest and rapidly growing technology of additive manufacturing (AM) or 3D printing. AM is a type of direct manufacturing and revolutionary technology that enables complicated production and a formation which can shorten manufacturing processes and supply chain procedures. Data is a key factor in the age of big data, embedded IIoT solutions, and services in the new machinery and mechanism that bring an additional capability to integrate and manage data streams within the Internet of Things (IoT) cloud-based platform. Movement and merging conventional (legacy) manufacturing technology into the shared and modern machinery required for the state-of-the-art manufacturing technology such as AM is complex and challenging, but it needs to be organized and fixed resourcefully, while it remains linked, flexible, and scalable. AM is an advanced manufacturing system and technology involving the new era of complex machinery and operating systems. AM has been identified as a special value to the industry which has many applications in the different industries such as aerospace, medical and healthcare, energy, and automotive. Hence, high-performance computation and processing will be very important in AM. This research takes an overview of the cloud-based model and concept of cloud computing (CC), cloud manufacturing (CM), IoT, and their relations and influences in the AM industry 4.0 era. This study contributes as a theoretical basis and as a comprehensive framework for AM integration. Furthermore, this paper presents CM applications and integration with AM and proposes an integrated AM cloud platform. [ABSTRACT FROM AUTHOR]

Aircraft structural parts are important and high-value parts used to constitute the frame of the aircraft, and are usually produced by NC machining, where the machining parameters are significant for the machining quality, efficiency, and cost. In the process planning, there are hundreds or even thousands of machining operations that require separate machining parameters, which is a huge task for the existing optimization-based methods that rely on iterative optimizations. Due to the complex structures and high requirements, the existing expert system-based methods require plenty of additional modifications. Recently, with the development of artificial intelligence, data-driven methods are used in machining parameter planning, which mines the knowledge and rules hidden in the historical data. However, the existing data-driven models require a large amount of training data and lack interpretability. To address this issue, this paper proposes an informed machine learning method for machining parameter planning, which introduces multiple prior constraints into the data-driven model. First, the part model is represented as an attribute graph, and the cutting area of each machining operation is correlated to a subgraph, which is used to obtain the vectorized representation of machining operation that covers cutting area and process information. Then, by fitting the mapping between the vectorized machining operation and the machining parameters, the knowledge and rules are learned. Next, to introduce prior constraints into the data-driven model, the constraint loss is designed and incorporated into the original loss function. The proposed method can generate machining parameters for all the machining operations in batch, thereby greatly reducing the human interactions. In the case study, the historical processing files of aircraft structural parts are used to train the proposed model for planning cutting width, cutting depth, spindle speed, and machining feedrate. The results show that the demand for training data is reduced and the prediction accuracy is improved with prior constraints. [ABSTRACT FROM AUTHOR]

With the development of the virtual reality technology, users can perform interactive assembly tasks by direct manipulation in virtual environment. However, most of the current studies mainly focus on the function of virtual assembly system without fully considering the interaction efficiency and user experience. As a result, users usually feel depressed in performing complex assembly tasks. A novel framework for interactive assembly task simulation is proposed to address this problem in this paper. The framework is implemented from three aspects: (1) the interaction information related to the assembly operations is integrated into virtual environment; (2) the user's intentions are captured according to the gestures and movements of users and the integrated interaction information of components assembled; and (3) the interaction behaviors of components intelligently and automatically are simulated in accordance with the user's intentions. According to the analysis of the assembly process, dynamic and static interaction behaviors are designed. The object's dynamic behavior containing a series of standard actions is used to assist users in performing interaction tasks. The user completes an assembly task by establishing the connection relationship between objects, which can be implemented based on the object's static interaction behavior. A virtual assembly task is constructed to evaluate the performance of the method, and the results of usability test confirm that the method proposed in this paper can improve the efficiency of human-computer interaction and user experience in a virtual assembly environment. [ABSTRACT FROM AUTHOR]

As the need for quickly exploring a textile manufacturing process is increasingly costly along with the complexity in the process. The development of manufacturing process modeling has attracted growing attention from the textile industry. More and more researchers shift their attention from classic methods to the intelligent techniques for process modeling as the traditional ones can hardly depict the intricate relationships of numerous process factors and performances. In this study, the literature investigating the process modeling of textile manufacturing is systematically reviewed. The structure of this paper is in line with the procedure of textile processes from yarn to fabrics, and then to garments. The analysis and discussion of the previous studies are conducted on different applications in different processes. The factors and performance properties considered in process modeling are collected in comparison. In terms of inputs' relative importance, feature selection, modeling techniques, data distribution, and performance estimations, the considerations of the previous studies are analyzed and summarized. It is also concluded the limitations, challenges, and future perspectives in this issue on the basis of the summaries of more than 130 related articles from the point of views of textile engineering and artificial intelligence. [ABSTRACT FROM AUTHOR]

This paper presents the cognitive module of the Cognitive Architecture for Artificial Intelligence (CAAI) in cyber-physical production systems (CPPS). The goal of this architecture is to reduce the implementation effort of artificial intelligence (AI) algorithms in CPPS. Declarative user goals and the provided algorithm-knowledge base allow the dynamic pipeline orchestration and configuration. A big data platform (BDP) instantiates the pipelines and monitors the CPPS performance for further evaluation through the cognitive module. Thus, the cognitive module is able to select feasible and robust configurations for process pipelines in varying use cases. Furthermore, it automatically adapts the models and algorithms based on model quality and resource consumption. The cognitive module also instantiates additional pipelines to evaluate algorithms from different classes on test functions. CAAI relies on well-defined interfaces to enable the integration of additional modules and reduce implementation effort. Finally, an implementation based on Docker, Kubernetes, and Kafka for the virtualization and orchestration of the individual modules and as messaging technology for module communication is used to evaluate a real-world use case. [ABSTRACT FROM AUTHOR]

Data-driven methods provided smart manufacturing with unprecedented opportunities to facilitate the transition toward Industry 4.0–based production. Machine learning and deep learning play a critical role in developing intelligent systems for descriptive, diagnostic, and predictive analytics for machine tools and process health monitoring. This paper reviews the opportunities and challenges of deep learning (DL) for intelligent machining and tool monitoring. The components of an intelligent monitoring framework are introduced. The main advantages and disadvantages of machine learning (ML) models are presented and compared with those of deep models. The main DL models, including autoencoders, deep belief networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs), were discussed, and their applications in intelligent machining and tool condition monitoring were reviewed. The opportunities of data-driven smart manufacturing approach applied to intelligent machining were discussed to be (1) automated feature engineering, (2) handling big data, (3) handling high-dimensional data, (4) avoiding sensor redundancy, (5) optimal sensor fusion, and (6) offering hybrid intelligent models. Finally, the data-driven challenges in smart manufacturing, including the challenges associated with the data size, data nature, model selection, and process uncertainty, were discussed, and the research gaps were outlined. [ABSTRACT FROM AUTHOR]

Intelligent optimization algorithm (IOA) has been widely studied and applied to solve various optimization problems. When scholars improve IOA with mathematical methods, they also want to seek an effective method to implement algorithms with higher real time, especially for a complex problem. Parallel design is an effective method to improve the real time of IOA. Currently, the parallel programming based on open multi-processing (OpenMP) and compute unified device architecture (CUDA) are two popular methods. To find and develop a new IOA parallel method, in this paper, a parallel design and implementation method based on field programmable gate array (FPGA) is explored. In order to validate the proposed method, parallel genetic algorithm (GA) and parallel particle swarm optimization (PSO) algorithm are realized by the proposed method. Furthermore, the performance and advantage of the proposed FPGA-based parallel IOA method are tested by comparing with OpenMP-based parallel programming and CUDA-based parallel programming, the final results show that the proposed method with highest real-time performance in IOA parallel implementation. A case study by using FPGA-based parallel simulate annealing (SA) to address job shop scheduling problem (JSSP) to illustrate the proposed method has high potential in industrial applications. [ABSTRACT FROM AUTHOR]

This paper presents an artificial intelligence (AI) method for the evolution prediction of surface scratching in sheet metals subjected to contact sliding. Ball-on-disk sliding was employed, and ball diameter, normal load, surface roughness, sliding cycles and the maximum scratching depth in the metal sheet were taken as the fuzzy variables to assess the contributions of individual variables to the surface damage. To improve the prediction accuracy, the quantum-behaved particle swarm optimisation (QPSO) algorithm was further developed and utilised to refine the fuzzy model by optimising the membership functions of the fuzzy variables. It was found that this AI technique, which integrates the fuzzy set theory with the improved QPSO algorithm, can accurately, reliably and efficiently predict the surface scratching evolution, which is otherwise impossible to be implemented. [ABSTRACT FROM AUTHOR]

This paper introduces CAAI, a novel cognitive architecture for artificial intelligence in cyber-physical production systems. The goal of the architecture is to reduce the implementation effort for the usage of artificial intelligence algorithms. The core of the CAAI is a cognitive module that processes the user's declarative goals, selects suitable models and algorithms, and creates a configuration for the execution of a processing pipeline on a big data platform. Constant observation and evaluation against performance criteria assess the performance of pipelines for many and different use cases. Based on these evaluations, the pipelines are automatically adapted if necessary. The modular design with well-defined interfaces enables the reusability and extensibility of pipeline components. A big data platform implements this modular design supported by technologies such as Docker, Kubernetes, and Kafka for virtualization and orchestration of the individual components and their communication. The implementation of the architecture is evaluated using a real-world use case. The prototypic implementation is accessible on GitHub and contains a demonstration. [ABSTRACT FROM AUTHOR]

The use of welded lightweight steels in structural applications is increasing due to the greater design possibilities offered by such materials and the lower costs compared to conventional steels. Ultra-high-strength steels (UHSS) having tensile strength of up to 1700 MPa with a high strength-to-weight ratio offer a unique combination of qualities for diverse industrial applications. For productivity and quality reasons, gas metal arc welding (GMAW) is usually utilized for welding of UHSS. However, for full penetration fillet welded joints, the need for high heat input to gain acceptable weld penetration is problematic when welding UHSS. This is due to UHSS sensitivity to heat input and possible heat-affected zone (HAZ) softening. In this paper, an attempt is made, on the basis of analysis of experimental reviews, to identify and define relationships between nonlinear weldability factors to enable creation of an artificial intelligence model to predict full penetration in robotic GMAW fillet welded joints of UHSS S960QC. Welding variables and parameters associated with GMAW are first evaluated by reviewing scientific literature. The possibility of employing an artificial neural network (ANN) to predict full penetration fillet weld characteristics is then examined. It is noted that nonlinear variables associated with the GMAW process, such as heat input, contact tip to work distance (CTWD), and torch angle, and their related parameters, which pose weldability challenges, can be modeled by applying artificial intelligence systems. Ensuring full penetration in fillet welded joints of UHSS using artificial intelligence is thus feasible. Further, an optimized control system could potentially be developed by incorporating adaptive robotic GMAW with an artificial intelligence-based system to guarantee sound structural integrity that conforms to EN ISO 5817. The paper increases awareness of welding aspects of UHSS S960QC and presents an approach for overcoming existing limits to GMAW via adaptive robotic welding and artificial intelligence systems. [ABSTRACT FROM AUTHOR]

Assembly line balancing (ALB) is concerned with assigning tasks within an assembly line to meet the required production rate for optimization purposes. On the other hand, two-sided ALB performs double-sided assembly operation on a single assembly line. In this paper, we have focused the survey on two-sided assembly line balancing (2S-ALB) research problems. The numerous factors mentioned in 2S-ALB literature were actually based on problem resolutions, and this paper will quote any preferred literature considering the frequent citation. In particular, this review explores in detail the ALB problems, optimization methods, objective functions, and specific constraints used in solving 2S-ALB problems. Among the purposes of ALB problems is that it traditionally focuses on simple ALB with various engaging approaches. General ALB comes second because of its complexity and nondeterministic polynomial (NP)-hard-classified problems. However, due to the current manufacturing issues, GALB problems, such as 2S-ALB, are forced to be examined and this comprehensive literature will specify anything necessary for the optimization purposes. Finally, future research direction has been discovered and put forward as the suggestion. [ABSTRACT FROM AUTHOR]

This paper presents a systematic methodology to enable environmental sustainability and productivity performance assessment for integrated process and operation plans at the machine cell level of a manufacturing system. This approach determines optimal process and operation plans from a range of possible alternatives that satisfy the objectives and constraints. The methodology provides a systematic procedure to highlight parameters that have significant impact on both sustainability and productivity performance metrics. We developed models and applied them to analyze manufacturing life cycle scenarios for collecting and categorizing key concepts towards building a material information model for sustainability. Integration of process and operation plans allows globalized assessment of sustainability and productivity, while development of a multi-criteria decision-making method leads to optimization of process planning activities based on the impact of conflicting sustainability and productivity metrics. A case study is detailed to demonstrate the sustainability-focused methodology, wherein integrated simulation and optimization techniques are used to support analysis of candidate scenarios and selection of preferred alternatives from a finite set of alternate process and operation plans. A discrete event simulation tool is used to model evolution of sustainability metrics (e.g., energy consumption) and productivity metrics (e.g., production time, cost) of a shop floor. The outcomes of this work include determination of optimized feature sequence plans which optimize various key performance indicators depending on stakeholder interest based on time, sustainability and production cost. [ABSTRACT FROM AUTHOR]

In made-to-order (MTO) manufacturing enterprises (ME), product architectures are usually modularised and components standardised. Product configuration is a key technology for order realisation in MTO-ME and is a typical knowledge-based application. Through a configuration process, product modules or components are selected and assembled according to customer requirements. Product configuration relates to a great deal of knowledge that represents complexity relations among components or modules, such as configuration rules and assembly constraints. Traditional product modelling techniques are focused mainly on physical product modelling and geometric representation, which makes them insufficient to help in the product configuration process. This paper discusses configuration-oriented product modelling and knowledge management for MTO-ME. A general process of product configuration modelling is proposed. The configuration model represents a product family from which a specific configuration solution or product variant can be derived. Actually, configuration modelling is a process which captures and represents product knowledge. In this paper, product knowledge is organised and managed through a knowledge component (KCOM) that includes configuration rules and constraints. A KCOM-based product knowledge representation model is presented. Finally, a PDM system is extended to support product modelling and knowledge management for MTO configurable products . [ABSTRACT FROM AUTHOR]

This paper proposes a new AI-assisted predictive maintenance framework for hybrid R2R manufacturing that combines multi-sensor data and self-supervised learning. It equips a multi-sensor Internet of Things (IoT) infrastructure to measure various conditions, such as temperature, vibration, and pressure, from the production line and employs Contrastive Predictive Coding (CPC) (a self-supervised learning model) for multi-sensor data representations without the scarce labelled data. This framework was tested on a lab-scale roll-to-roll chemical vapour deposition (R2R CVD) reactor system, and we show that the CPC model accurately predicts the underlying process dynamics and is capable of anomaly detection and failure prediction. Our system was able to acxshieve 96.2% accuracy in failure prediction with an AUC-ROC of 0.94 and an F1 score of 0.88. Our method was able to predict a process anomaly 12 min in advance, which could potentially be used to pre-empt a possible shutdown given enough time to intervene. Therefore, our framework not only predicts the failure before it occurs but also optimises the maintenance schedule, thereby improving robotic manufacturing efficiency and reducing downtime. The comparison between our method and the traditional predictive maintenance method shows that our method can predict failure earlier and give more advance notice when compared with the former in most cases. Finally, this study enriches the body of research on smart manufacturing by showing that integrating multi-sensor data with self-supervised learning can boost the effectiveness of predictive maintenance in hybrid R2R processes. It can be further expanded to achieve highly accurate predictions for other R2R manufacturing applications, which will help to improve production efficiency, reduce maintenance costs, and enhance product quality. [ABSTRACT FROM AUTHOR]

In this paper, an AI (artificial intelligence) approach to the design and control of an integrated maintenance management system is reported. The research work has been done on two levels. At the managerial level, the overall maintenance management system is designed by the GRAI method. This system is designed as an integrated system which makes decisions on maintenance activity scheduling and control, taking into consideration not only equipment working conditions but also maintenance cost, product quality, and production efficiency. At the decision support level, a number of intelligent decision support systems (IDSSs) are developed based on Bayesian theory or causal probabilistic networks (CPNs). In this paper, a generic CPN for the maintenance of open-end spinning mills is reported. [ABSTRACT FROM AUTHOR]

Towards the fourth industrial revolution or Industry 4.0 with intelligence as the soul, and data as the key, product manufacturing is facing new challenges in the ever-changing dynamic and competitive environment, and process data-driven intelligent NC machining process planning has become an enabling technology for high efficiency and quality manufacturing. However, existing methods are mainly based on static machining feature for the description of the process data, and they are difficult to represent the embedded multi-granularity process knowledge and experience of designers. In this paper, a multilevel structured NC machining process model based on dynamic machining feature for process reuse is proposed. First, the dynamic machining feature is introduced to make up the deficiency of process design intent capture based on static machining feature. Then, the interactions between 3D CAD model and CAM model are revealed to realize the association in the process data. Finally, the multilevel structured NC machining process model embodying multi-granularity process design intent is established to overcome the sematic gap between high-level macro-technological process and low-level micro-process parameters. A prototype system based on UG NX has been developed to verify the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

With the increasing of the process data, process data-driven intelligent machining process planning is becoming more and more important in manufacturing industries. In the process data, the macro process contains abundant process design intent, which has important reuse value. However, existing 3D CAD model retrieval methods for macro process reuse are mainly on the premise of geometric similarity, which make them difficult to guarantee the reusability of the macro process associated with the similar results. In this paper, an effective retrieval approach of 3D CAD models for macro process reuse is presented. First, a process skeleton model is introduced to guide the structuralization of process data based on the macro process of existing parts. Then, a probability statistics approach is presented to map machining features of query part onto the macro process of existing part. Finally, process design intent-driven accessible machining region extraction is proposed, and then the part similarity assessment model based on the machining region is established to calculate the macro process similarity between query part and existing part. A prototype system has been developed to verify the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

With the breakthroughs in artificial intelligence technology and the rapid development of intelligent manufacturing, industry and artificial intelligence (AI) are gradually being deeply integrated. On the basis of artificial intelligence, we systematically expounded the generation, definition, characteristics, classification, technical system, and current situation of industrial artificial intelligence (I-AI). Combining existing research and industrial projects, we propose a detailed framework and a reference model for I-AI in industry. The framework contains seven dimensions: objects of I-AI, domain of I-AI, application stages of I-AI, application requirements of I-AI, intelligent technology of I-AI, intelligent function of I-AI, and solutions of I-AI. Secondly, based on the application scenarios of artificial intelligence and industrial convergence, we propose a detailed overall planning for I-AI. Finally, five typical industrial fields are selected, and the I-AI solutions based on TFV (technology and function integration in industrial value chain) unit and 6W1H method are used for new application scenarios of the proposed framework. In addition, a detailed case of implementing for I-AI in port equipment industry is given. The research results of this paper have achieved good results in the related industrial field and can provide some reference for other industrial enterprises to plan, design, implement, and apply artificial intelligence. [ABSTRACT FROM AUTHOR]

The safety of industrial installations requires real-time monitoring of the occurrence of defects in induction machines that are widely used in this field. The implementation of this type of system typically needs to process a large amount of data provided by sensors and thus necessitates high computing mass, which complicates sensor utilization in real time. In this paper, we propose a hierarchical recurrent neural network by stacking two long short-term memory layers to form a single end-to-end network. Trained to establish complex temporal relations in raw time series signals. Those signals are directly provided by the sensors without any preprocessing or hand engineered features extraction. To train the network, we use the stator currents of a three-phase induction motor captured in a steady state. The currents represent several operation modes, which comprise the healthy and failed states with several types of mechanical defects, electrical defects, and combinations thereof. The experimental results were obtained using data from a real test bed to demonstrate the robustness and speed of the proposed approach for real-time monitoring of the operating status of an induction motor. [ABSTRACT FROM AUTHOR]