Intelligent Manufacturing Systems Research Articles

Advantages of Big Data Analysis and AI Technology in Data Collecting And Processing of Preventive Maintenance

In recent years, the emergence of Cyber-Physical systems (CPS), big data, cloud computing, and industrial wireless networks have promoted the development of Industry 4.0. Intelligent manufacturing systems are the leaders of this change. In smart manufacturing, the emphasis will be placed on using technologies such as big data analytics, cloud computing, edge computing, and artificial intelligence (AI). The advantages of new technologies are significantly reflected in the comparison of preventive maintenance and traditional maintenance based on intelligent technology: preventive maintenance significantly reduces the cost of prevention and, at the same time, dramatically improves the accuracy and timeliness of maintenance, bringing inestimable value to intelligent manufacturing. This paper will analyze new technologies’ innovative advantages and technical prospects through big data analysis and specific application scenarios of AI technology in preventive maintenance. Firstly, in data acquisition, this paper examines the architecture of preventive maintenance systems based on big data. Then, it analyzes the composition of the data pipeline: in the realization of data collection and processing in the field of cloud computing and edge computing, and the aspect of data processing, it discusses the participation of AI technology in data understanding and processing and the unprecedented changes it brings.

Learning-based production, maintenance, and quality optimization in smart manufacturing systems: A literature review and trends

With the introduction of manufacturing paradigms, including Industry 4.0, production research has shifted its focus to enabling intelligent manufacturing systems within industrial environments. These systems can efficiently schedule and control processes and operations using artificial intelligence methods, including machine learning and deep learning. Since 1995, relevant literature has presented several examples of such implementations, addressing topics, for example equipment fault diagnosis and quality inspections. To this end, the present paper strives to present a state-of-the-art review of the learning-based scheduling and control frameworks, which are exploited in the production research. The review is limited to the relevant research between the years 1995 and 2024, surveying approaches in the domains of manufacturing, maintenance, and quality control. To this end, the paper follows a meta-analysis method for the selection and evaluation of relevant research articles. Moreover, research questions are formulated to analyze the obtained findings and seek out insights on aspects of the relevant research, including the inclusion of decision-making models and dissemination of literature. The provided answers, among others, reveal trends and limitations of the state-of-the art research in relation to learning-based scheduling and control.

Intelligent manufacturing, auditor selection and audit quality

PurposeThe purpose of this paper is to examine the influence of intelligent manufacturing on audit quality and its underlying mechanism as well as the variation in this influence across different types of organizations.Design/methodology/approachThis research utilizes a difference-in-differences (DID) method to examine how enterprises that apply intelligent manufacturing choose auditors and impact their audit work. The study is based on 15,228 observations of Chinese-listed A-shares from 2011 to 2020.Findings(1) There is a strong correlation between intelligent manufacturing and audit quality. (2) This positive correlation is statistically significant only in state-owned enterprises (SOEs), those that have steady institutional investors and where the roles of the CEO and chairman are distinct. (3) Enterprises that have implemented intelligent manufacturing are more inclined to employ auditors who possess extensive industry expertise. The auditor's industry expertise plays a crucial role in ensuring audit quality. (4) The adoption of intelligent manufacturing also leads to higher audit fees and longer audit delay periods.Practical implicationsThis paper validates the beneficial impact of intelligent manufacturing on improving corporate governance. In addition, it is recommended that managers prioritize the involvement of skilled auditors with specialized knowledge in the industry to ensure the high audit quality and the transparency of information in intelligent manufacturing enterprises.Originality/valueThis study builds upon previous research that has shown the importance of artificial intelligence in enhancing audit procedures. It contributes to the existing body of knowledge by examining how enterprise intelligent manufacturing systems (IMS) enhance audit quality. Additionally, this study provides valuable information on how to improve audit quality in the field of intelligent manufacturing by strategically selecting auditors based on resource dependency theory.

Heterogeneous Graph Neural Network for Modeling Intelligent Manufacturing Systems

Abstract Currently, manufacturing systems have become more and more complex, often involving multiple machines, systems and processes to produce workpieces. In order to facilitate comprehensive analysis and control of manufacturing processes, the integration of connections between machine level, system level, and process level in manufacturing process modeling is needed. However, traditional graph deep learning models are unable to take into account the heterogeneity of different machines in the system when modeling manufacturing systems. To address this problem, this paper proposes a new approach: modeling manufacturing systems using the Heterogeneous Graph SAmple and aggreGatE algorithm (HGNN) based on cutting-edge Bayesian neural networks and graph deep learning. This method considers the connection between different manufacturing system levels, treats machine operations as nodes, and connects different nodes through material flow and operational similarity. The effectiveness of the method is demonstrated through its application to model an aero-engine blade production line. Extensive numerical experiments show that the proposed graph modeling method is effective in expressing the heterogeneity of different machines and multi-level manufacturing processes. By integrating machine heterogeneity into the modeling of a manufacturing system, it not only facilitates comprehensive analysis and control of the manufacturing process, but also lays the foundation for cost savings and productivity improvements in the manufacturing system.

On-line recognition of mixture control chart patterns using hybrid CNN and LSTM for auto-correlated processes

Statistical process control (SPC), designed to detect and identify process disturbances, is an effective quality control method for ensuring process stability. Owing to the growing automation of the industry, the manufacturing process can be autocorrelated. Engineer process control (EPC) is typically used to address autocorrelation. However, process disturbances can be offset by feedback compensation, making control chart patterns (CCPs) difficult to identify. Most studies on control chart pattern recognition (CCPR) techniques are based on a single abnormal control chart pattern (CCP). However, a mixture of CCPs can occur during real-world manufacturing processes. With the development of intelligent manufacturing systems, early detection of abnormal concurrent CCPs has become an important issue. In this study, a hybrid model combining a convolutional neural network (CNN) and long short-term memory (LSTM) in an online detection system was used to recognize the concurrent CCPR problem in SPC-EPC processes. The results showed that the average accuracy of the deep learning CNN-LSTM method was 99.83%, which was significantly better than that of the machine learning method. In addition, the running time of the CNN-LSTM model was shortened. In a comparison of online monitoring between the deep learning method and the machine learning method, the CNN-LSTM model for an online monitoring system identified abnormal concurrent patterns faster. Therefore, the proposed CNN-LSTM online monitoring scheme can be applied confidently and successfully to identify mixture CCPs in an SPC-EPC process.

A Comprehensive Review of Theories, Methods, and Techniques for Bottleneck Identification and Management in Manufacturing Systems

With the advancement in global market integration, manufacturing enterprises face increasingly fierce competition, making the development of intelligent manufacturing systems a key factor in enhancing market competitiveness. However, manufacturing systems are characterized by varying characteristics of manufacturing resources and strong interdependencies, which make production control more complex. A bottleneck refers to the issue where the manufacturing system’s actual production capacity is less than or equal to the demand placed on a resource. After extensive research, scholars have concluded that the definition, identification methods, and related studies on bottlenecks are not fixed but depend on the specific research subject and the type of bottleneck. Therefore, scholars suggest that only by accurately defining the bottlenecks within a system can appropriate models be employed for prediction, thereby avoiding issues such as inefficient resource allocation and delivery delays, or implementing measures to minimize these negative impacts. Particularly under unstable production conditions, dynamic bottlenecks are likely to occur, making the prediction and identification of bottlenecks under dynamic environmental conditions crucial. Currently, there is still a lack of research in real-time state sensing and integration, as well as a lack of systematic review of related research. To fill this research gap, this review comprehensively introduces the current state and achievements in bottleneck research within manufacturing systems, focusing on bottleneck categories, identification, shifting, and management. It also provides an outlook on future research trends and directions in the study of manufacturing system bottlenecks.

SPM-SeCTIS: Severity Pattern Matching for Secure Computable Threat Information Sharing in Intelligent Additive Manufacturing

Sharing Cyber Threat Intelligence (CTI) enables organisations to work together to defend against cyberattacks. However, current methods often fail to adequately protect sensitive information, leading to security risks, especially in Intelligent Additive Manufacturing (IAM) systems. In these systems, the security and privacy of incident data collected by IoT devices are essential, as revealing threat information, such as types, impacts, and organisational interests, could be harmful. To address these challenges, we propose the Severity Pattern Matching for a Secure Computable Threat Information Sharing System (SPM-SeCTIS). This system is designed to maintain privacy by allowing intermediaries to pass along threat information without accessing sensitive details, such as the type or severity of the threats. SPM-SeCTIS ensures that attackers cannot determine which incidents organisations are interested in or what specific threats they monitor. The system employs Homomorphic Encryption (HE) to conduct threat pattern matching on encrypted data, keeping sensitive information confidential even during analysis. Our performance tests indicate that SPM-SeCTIS operates efficiently, requiring minimal time for encryption and decryption processes. Additionally, the system scales effectively, handling a large number of subscribers and incidents with ease. Compared to existing methods, SPM-SeCTIS provides improved security measures and better overall performance, making it a robust solution for protecting sensitive threat information.

A double-layer Q-learning driven memetic algorithm for integrated scheduling of procurement, production and maintenance with distributed resources

The existing research on integrated production scheduling typically focuses on activities related to both production and post-production (e.g., operation and maintenance), with limited consideration for simultaneously integrating pre-production activities (e.g., raw material procurement). However, achieving the equilibrium between the manufacturer and the demander for intelligent manufacturing systems requires the optimal scheduling solution that integrates both pre-production and post-production activities. Inspired by this, we investigate a novel integrated scheduling problem that concurrently considers raw material procurement, production scheduling and equipment maintenance (abbreviated as SIPPM). A mixed-integer linear programming model is developed to simultaneously minimize the total costs for the manufacturer and the demander. Furthermore, a double-layer Q-learning driven memetic algorithm (DQMA) is proposed to solve the SIPPM. In DQMA, a well-tailored three-layer hybrid encoding method is presented for chromosome representation. The global search of DQMA employs three crossover and three mutation operators. Moreover, a knowledge-based local search operator with six methods, guided by an effective double-layer Q-learning structure, is devised to enhance local exploitation capabilities. The superiority of DQMA is verified through comparison with three popular multi-objective optimization algorithms on 108 newly established benchmark instances. The proposed integrated scheduling mode is proven to be more effective than two separated scheduling modes without considering raw material procurement.

An Effective Local Search Algorithm for Flexible Job Shop Scheduling in Intelligent Manufacturing Systems

As one of the most classical scheduling problems, flexible job shop scheduling problems (FJSP) find widespread applications in modern intelligent manufacturing systems. However, the majority of meta-heuristic methods for solving FJSP in the literature are population-based evolutionary algorithms, which are complex and time-consuming. In this paper, we propose a fast effective single-solution based local search algorithm with an innovative adaptive weighting technique (AWLS) for solving FJSP. The adaptive weighting technique assigns weights to each operation and adaptively updates them during the exploration. AWLS integrates a Tabu Search strategy and the adaptive weighting technique to smooth the landscape of the search space and enhance the exploration diversity. Computational experiments on 313 well-known benchmark instances demonstrate that AWLS is highly competitive with state-of-the-art algorithms in terms of both solution quality and computational efficiency, despite of its simplicity. Specifically, AWLS improves the previous best-known results in the literature on 33 instances and match the best-known results on the remaining ones except for only one under the same time limit of up to 300 s. As a strongly Non-deterministic Polynomia (NP)-hard problem which has been extensively studied for nearly half a century, breaking the records on these classic instances is an arduous task. Nevertheless, AWLS establishes new records on 8 challenging instances whose previous best records were established by a state-of-the-art meta-heuristic algorithm and a famous industrial solver.

Advances in Research on Tool Wear Online Monitoring Method

Background: With the continued advancement of industrial internet technology, mechanical manufacturing is increasingly developing towards automation and intelligence. As a result, monitoring the manufacturing process has become an essential requirement for intelligent manufacturing. As one of the fundamental components of cutting processes, tools are inevitably subject to wear and damage during use. Therefore, tool wear monitoring plays a crucial role in modern manufacturing. Introduction: With the development of the manufacturing industry, the requirement for automation manufacturing is higher and higher. In the process of automatic processing, unmanned processing and adaptive processing, it is not only required to be able to know the accurate wear state of the tool in the process real-time but also required to change the milling parameters according to the wear state of the tool, in order to optimize the productivity and processing quality. The tool monitoring system can effectively reduce the operating cost of workshop production and improve the reliability of intelligent workshop and flexible production lines. Method: This article summarizes commonly used online monitoring methods mentioned by articles and patents, such as cutting force, vibration, acoustic emission, temperature, current, and power signals. Each monitoring method is analyzed in terms of its principles, advantages and disadvantages, signal acquisition equipment, and research status. The article also identifies current issues and future development directions. Results: As modern manufacturing technology continues to develop rapidly, unmanned factories have become a significant feature of the manufacturing industry. Consequently, the need for tool wear condition monitoring technology is becoming increasingly urgent. Although tool condition monitoring technology has made significant progress over the past twenty years and has been applied in actual production, several issues need to be addressed to make tool wear condition monitoring systems mo. Conclusion: This serves as a reference for theoretical research and application of online monitoring of tool wear in intelligent manufacturing systems.

Machine learning-based 3D scan coverage prediction for smart-control applications

Automatic control of a workpiece being manufactured is a requirement to ensure in-line correction and thus move towards a more intelligent manufacturing system. There is therefore a need to develop control strategies which are capable of taking precise account of real working conditions and enabling first-time-right control. As part of such a smart-control strategy, this paper introduces a machine learning-based approach capable of accurately predicting a priori the 3D coverage of a part according to a scan configuration given as input, i.e. predicting before scanning it which areas of the part will be acquired for real. This corresponds to a paradigm shift, where coverage estimation no longer relies on theoretical visibility criteria, but on rules learned from a large amount of data acquired in real-life conditions. The proposed 3D Scan Coverage Prediction Network (3DSCP-Net) is based on a 3D feature encoding and decoding module, which is capable of taking into account the specifics of the scan configuration whose impact on the 3D coverage is to be predicted. To take account of real working conditions, features are extracted at various levels, including geometric ones, but also features characterising the way structured-light projection behaves. The method is thus able to incorporate inter-reflection and overexposure issues into the prediction process. The database used for the training was built using an ad-hoc platform specially designed to enable the automatic acquisition and labelling of numerous point clouds from a wide variety of scan configurations. Experiments on several parts show that the method can efficiently predict the scan coverage, and that it outperforms conventional approaches based on purely theoretical visibility criteria.

A Review and Prospects of Manufacturing Process Knowledge Acquisition, Representation, and Application

The evolution of knowledge acquisition and representation in manufacturing technologies is vital for translating complex manufacturing data into actionable insights and advancing a comprehensive knowledge framework. This framework is pivotal in driving innovation and efficiency in intelligent manufacturing. This review aggregates recent research on knowledge acquisition and representation within the manufacturing process, addressing existing challenges and mapping potential future developments. It includes an analysis of 123 papers that focus on harnessing advanced intelligent analytics to extract operationally relevant knowledge from the extensive datasets typical in manufacturing environments. The narrative then examines the methodologies for constructing models of knowledge in manufacturing processes and explores their applications in manufacturing principles, design, management, and decision-making. This paper highlights the limitations of current technologies and projects emerging research avenues in the acquisition and representation of process knowledge within intelligent manufacturing systems, with the objective of informing future technological breakthroughs.

Integrated scheduling of production and material delivery for the intelligent manufacturing system

This paper addresses the issue of integrated scheduling of production and material delivery in an intelligent manufacturing system. The system includes multiple flexible flowlines and a fleet of automated guided vehicles (AGVs), whose capacity is shared among the flowlines. Multiple orders from different customers are processed on the flowlines, with AGVs delivering materials in different batch sizes based on varying product quantities of orders and limited load capacity. The problem is formulated as a mixed-integer linear programming model to minimise total order delays and the number of used AGVs. To handle the complexity caused by the uneven temporal coupling relationship between production and material delivery, a bi-level neighbourhood search solution algorithm is proposed. This algorithm uses variable neighbourhood search for production scheduling and adaptive large neighbourhood search for material delivery scheduling. Extensive numerical experiments using real-case-based instances are conducted to demonstrate the satisfactory performance of our proposed algorithm. Furthermore, we emphasise the advantages of integrated scheduling compared to traditional sequential scheduling across various problem settings.

An explainable machine learning-based web attack detection system for industrial IoT web application security

ABSTRACT Within Industry 4.0, the integration of Industrial IoT (IIoT) marks a transformative phase for modern industries, fostering the development of smart factories and intelligent manufacturing systems. Despite the substantial growth of IIoT, a critical research gap persists in web security within IIoT environments. This paper addresses this gap by proposing an explainable and robust machine learning-based web attack detection system to ensure IIoT web application security using ToN-IoT and NF-ToN-IoTv2 datasets that accurately reflects IIoT traffic. Given eXplainable Artificial Intelligence’s (XAI) capability to instill trustworthiness and transparency in learning models, the authors opted for the SHAP technique for feature selection, leveraging its global insights to explain feature contributions to the system’s decision-making. Compared to the existing works, the system demonstrated strong performance across various metrics, including accuracy, recall, precision, specificity, F-value, FPR, FNR, AUC-ROC curve, MCE, training, and prediction times, in binary and multi-classification scenarios.

Toward sustainable process industry based on knowledge graph: a case study of papermaking process fault diagnosis

Process industry suffers from production management in terms of efficiency promotion and waste reduction in large scale manufacturing due to poor organization of the intricate relational databases. In order to enhance the suitability of intelligent manufacturing systems in process industry, this study proposed an innovative top-down structure Knowledge Graph (KG) for process fault diagnosis, and papermaking was taken as a case study. The KG consists of a normalized seven-step-built ontology, which extracted instances of papermaking knowledge via Protégé software. The exported OWL file was imported into Neo4j software for visualization of the KG. The application in papermaking drying process for fault diagnosis shows that it can depict the material and energy flows throughout the process with a clearer relationship visualization than traditional measures. They also enable rationale search for faults and identification of their potential causes. The built KG efficiently manages the vast knowledge of the process, stores unstructured data, and promotes the intelligent development of process with high reusability and dynamicity that can rapidly import new production knowledge as well as flexibly self-updating.

Sequential Optimal Trajectory Planning Scheme for Robotic Manipulators along Specified Path Based on Direct Collocation Method

Robotic manipulators play a pivotal role in modern intelligent manufacturing and unmanned production systems, often tasked with executing specific paths accurately. However, the input of the robotic manipulators is trajectory which is a path with time information. The resulting core technology is trajectory planning methods which are broadly classified into two categories: maximum velocity curve (MVC) methods and multiphase direct collocation (MPDC) methods. This paper concentrates on addressing challenges associated with the latter methods. In MPDC methods, the solving efficiency and accuracy are greatly influenced by the number of discretization nodes. When dealing with systems with complex dynamics, such as robotic manipulators, striking a balance between solving time and path discretization errors becomes crucial. We use a mesh refinement (MR) algorithm to find a suitable number of nodes under the premise of ensuring the path discretization error. So, the actual device can effectively implement the planned solutions. Nonetheless, the conventional application of the MR algorithm requires solving the original problem in each iteration; these processes are extremely time-consuming and may fail to solve when dealing with a complex dynamic system. As a result, we propose a sequential optimal trajectory planning scheme to solve the problem efficiently by dividing the original optimal control (OC) problem into two stages: path planning (PP) and trajectory planning (TP). In the PP stage, we employ a DC method based on arc length and an MR algorithm to identify key nodes along the specified path. This aims to minimize the approximation error introduced during discretization. In the TP stage, the identified key nodes serve as boundary conditions for an MPDC method based on time. This facilitates the generation of an optimal trajectory that maximizes motion performance, considering constant velocity in Cartesian space and dynamic constraints while keeping the path discretization error. Simulation and experiment are conducted with a six-axis robotic manipulator, ROCR6, and show significant potential for a wide range of applications in robotics.

Efficient Predictive Regulation Algorithms for AGV System in Industrial Internet

<p>In recent years, the industrial Internet has developed rapidly. In order to improve the reliability, real-time, and economy, Automated Guided Vehicle (AGV) in intelligent manufacturing system becomes an indispensable technology. However, the current AGV system relies too much on the fixed network bandwidth environment in information transmission and management. When the traffic demand changes frequently, this form of network configuration lacks network resource management mechanism. Further, it leads to the problems of delay, waste of network flow, and inability to dynamically allocate network resources. So it is vital to improve the AGV system. Therefore, this paper proposes three predictive control algorithms and a Network Cable Scheduling algorithm to manage the network resources. They are Markov Chain Linear Programming Regulation (MCLPR) algorithm, Prophet Linear Programming Regulation (PLPR) algorithm, and Machine Learning Linear Programming Regulation (MLLPR) algorithm. The experimental results show that PLPR and MLLPR algorithm have high efficiency in the aspect of regulation. MLLPR algorithm has the lowest cost. MLLPR algorithm has the strongest leakage limitation ability, followed by PLPR algorithm. The balance regulation efficiency of MLLPR in none “4 + 1” mode is the highest in different network cable modes.</p> <p> </p>

A novel hexagonal grid map model and regenerated heuristic factor based strategy for intelligent manufacturing system’s AGV path planning problem solving

In modern industry, flexible manufacturing systems play an indispensable role, and the precision and connectivity of map modeling are crucial for improving the efficiency and flexibility of AGV (Automated Guided Vehicle) transportation systems. Facing challenges such as spatial constraints, equipment failures, and unexpected task changes in real manufacturing environments, this paper proposes an innovative AGV path planning method based on hexagonal grid map modeling. This method significantly enhances the connectivity, sampling frequency, and safety of AGV path planning by replacing traditional square grids with hexagonal ones. Additionally, this study employs an improved ant colony algorithm combined with the hexagonal grid map for AGV path planning. The algorithm incorporates heuristic factors to effectively avoid local optima. Furthermore, by dividing the ant colony into odd and even groups and implementing a bidirectional search strategy, the comprehensive exploration capability of the algorithm is further enhanced. Experimental results show that compared to traditional square grids, the hexagonal grid reduces the optimal path length by 11.1%, and the application of heuristic factors further shortens the path length by 18.6%. The bidirectional search strategy also significantly reduces the number of iterations required by the algorithm, with a maximum reduction of 46.46%. In summary, this paper provides a new, efficient, stable, and energy-saving solution for AGV path planning systems, with thorough optimizations and improvements made in every aspect from map modeling to path planning algorithms.

A data and knowledge driven autonomous intelligent manufacturing system for intelligent factories

The non-ferrous metal industry is encountering several challenges, including production efficiency, manufacturing information fragmentation, and human health problems, which highlights the importance of implementing autonomous intelligent manufacturing systems (AIMS). Recently, the foundation model like GPT-4, has garnered attentions due to its exceptional capabilities and proficiency in diverse domains and tasks, facilitating the realization of AIMS. However, the existing foundation models can only address basic general-purpose tasks and are difficult to use for industrial applications. In this paper, we propose a data and knowledge driven AIMS with industrial-generative pretrained Transformer (Industrial-GPT) for intelligent factories. The paradigms and architecture of autonomous intelligent factories are firstly defined. Then, we explore the mechanism with knowledge graph, digital twin, and Industrial-GPT, including multi-level autonomous perception, cross layer and domain cognition, and event-driven collaborative decision-making. Finally, the detailed case study is based on the cooperation with a zinc smelting intelligent factory to achieve networked collaborative manufacturing, and explores the theory and realization mechanism of AIMS on a small scale. We explore the experimental analyses, evaluation mechanisms and platform applications of AIMS at the workshop level. We believe this will help to realize larger scale AIMS in the future.

Reliability analysis of intelligent manufacturing systems based on improved FMEA combined with machine learning

Along with the booming of intelligent manufacturing, the reliability management of intelligent manufacturing systems appears to be becoming more significant. Failure mode and effects analysis (FMEA) is a prospective reliability management instrument extensively utilized to manage failure modes of systems, products, processes, and services in various industries. However, the conventional FMEA method has been criticized for its inherent limitations. Machine learning can handle large amounts of data and has merits in reliability analysis and prediction, which can help in failure mode classification and risk management under limited resources. Therefore, this paper devises a method for complex systems based on an improved FMEA model combined with machine learning and applies it to the reliability management of intelligent manufacturing systems. First, the structured network of failure modes is constructed based on the knowledge graph for intelligent manufacturing systems. Then, the grey relation analysis (GRA) is applied to determine the risk prioritization of failure modes. Hereafter, the k-means algorithm in unsupervised machine learning is employed to cluster failure modes into priority classes. Finally, a case study and further comparative analysis are implemented. The results demonstrate that failure modes in system security, production quality, and information integration are high-risk and require more resources for prevention. In addition, recommendations for risk prevention and monitoring of intelligent manufacturing systems were given based on the clustering results. In comparison to the conventional FMEA method, the proposed method can more precisely capture the coupling relationship between the failure modes compared with. This research provides significant support for the reliability and risk management of complex systems such as intelligent manufacturing systems.