Complex Manufacturing Systems Research Articles

A Partial Domain Generalization Method for Modeling Multiple Multistage Manufacturing Processes

In complex manufacturing systems, materials are processed by machines sequentially before final products are get, forming a multistage manufacturing process (MMP). In a modern massive production factory, it is common that multiple MMPs work simultaneously to fulfill productivity needs. Multiple MMPs may contain machines with different running time, processing the same types of products but with different specifications. In such a Multiple MMP(MMMP) system, it is critical for machines to learn from each other to gain optimal parameter settings of each. However, traditional machine learning methods usually fail to consider both similarities and unique features among multiple processes at the same time. To address this problem, a partial domain generalization method is proposed based on the thought of transfer learning to combine useful information from historical processes while maintaining features from the in-production process. The proposed method also suits for problems with the assumption that only partial input variables are available. Studies reveal that the proposed method has superior prediction performance over traditional machine learning methods and some widely-used transfer learning methods.

Mathematical optimization strategy for online scheduling of complex manufacturing systems based on thermal energy optimization and fuzzy mathematical model

With the rapid development of the manufacturing industry and the advancement of the intelligent process, the scheduling problem of complex manufacturing systems becomes more and more complicated, especially in the aspect of energy management and optimization. This study aims to propose an online scheduling mathematical optimization strategy based on thermal energy optimization and fuzzy mathematical model, so as to improve the scheduling efficiency and resource allocation rationality of complex manufacturing systems under different production conditions. A scheduling model considering thermal energy utilization rate, production priority and real-time demand is established by using fuzzy mathematics. The model deals with the uncertain factors by fuzzy logic and solves them by genetic algorithm to realize the dynamic adjustment and optimal scheduling of production resources. Through the experimental verification of a complex manufacturing system, the improvement of scheduling efficiency not only reduces the operating cost, but also improves the flexibility and response speed of the system. The fuzzy mathematical model based on thermal energy optimization provides an effective on-line scheduling strategy for complex manufacturing systems, which can realize efficient scheduling and energy management in dynamic environment.

Multi-agent reinforcement learning for integrated manufacturing system-process control

The increasing complexity, adaptability, and interconnections inherent in modern manufacturing systems have spurred a demand for integrated methodologies to boost productivity, improve quality, and streamline operations across the entire system. This paper introduces a holistic system-process modeling and control approach, utilizing a Multi-Agent Reinforcement Learning (MARL) based integrated control scheme to optimize system yields. The key innovation of this work lies in integrating the theoretical development of manufacturing system-process property understanding with enhanced MARL-based control strategies, thereby improving system dynamics comprehension. This, in turn, enhances informed decision-making and contributes to overall efficiency improvements. In addition, we present two innovative MARL algorithms: the credit-assigned multi-agent actor-attention-critic (C-MAAC) and the physics-guided multi-agent actor-attention-critic (P-MAAC), each designed to capture the individual contributions of agents within the system. C-MAAC extracts global information via parallel-trained attention blocks, whereas P-MAAC embeds system dynamics through permanent production loss (PPL) attribution. Numerical experiments underscore the efficacy of our MARL-based control scheme, particularly highlighting the superior training and execution performance of C-MAAC and P-MAAC. Notably, P-MAAC achieves rapid convergence and exhibits remarkable robustness against environmental variations, validating the proposed approach’s practical relevance and effectiveness.

MFRL-BI: Design of a model-free reinforcement learning process control scheme by using Bayesian inference

Design of the process control scheme is critical for quality assurance to reduce variations in manufacturing systems. Taking semiconductor manufacturing as an example, extensive literature focuses on control optimization based on certain process models (usually linear models), which are obtained by experiments before a manufacturing process starts. However, in real applications, pre-defined models may not be accurate, especially for a complex manufacturing system. To tackle model inaccuracy, we propose a Model-Free Reinforcement Learning (MFRL) approach to conduct experiments and optimize control simultaneously according to real-time data. Specifically, we design a novel MFRL control scheme by updating the distribution of disturbances using Bayesian inference to reduce their large variations during manufacturing processes. As a result, the proposed MFRL controller is demonstrated to perform well in a nonlinear chemical mechanical planarization process when the process model is unknown. Theoretical properties are guaranteed when disturbances are additive. The numerical studies also demonstrate the efficiency of our methodology.

Knowledge reuse for ontology modelling and application of maintenance motion state sequence

With the current digital transformation and the development of complex manufacturing systems, advanced maintenance is proposed to improve the competitiveness of complex products, generating a large amount of heterogeneous maintenance data and information. There is a lack of standardized representations of motion-centred maintenance knowledge which leads to semantic ambiguity and poor intertranslatability. In addition, it causes subjective deviations and human resource investments in related time prediction applications. Therefore, a knowledge reuse method for ontology modelling and the application of maintenance motion state sequences is proposed. First, a framework for reusing maintenance motion state sequence (MMSS) knowledge is established, which is defined as the state sets of time-sequence maintenance motion. Second, maintenance motion state sequence ontology (MMSSO) is constructed to standardize the definition of MMSS, as a supplement to the current maintenance ontologies. Third, an MMSSO application for automatic maintenance time prediction is proposed by incorporating the standardized specifications of MMSSO and improving the MODAPTS method. Finally, using aviation equipment as an example, the rationality and superiority of MMSSO in real applications are verified. MMSSO is a new practice of integrating multi-source information in advanced maintenance. It can also provide predicted time as an iterative reference for industrial practitioners in the digital design stage.

Digital twin-enabled robust production scheduling for equipment in degraded state

Technological advancements are leading to a world where digital twins will become integral to manufacturing operations management. While wide-ranging applications of digital twins are being researched, robust production scheduling remains an enduring challenge, especially considering the numerous sources of uncertainty in a complex manufacturing system that can affect the validity of the obtained solution. Thus, the article proposes a Prognostics and Health Management (PHM)-enabled digital twin framework to perform job scheduling for a flow shop scheduling problem considering real-time equipment health state. The framework combines the adoption of a Genetic Algorithm optimizer with data-driven modelling leveraging algorithms like Principal Component Analysis and models like Discrete Event Simulation with the purpose to solve the engineering task of scheduling at hand. Building on such a technological blend, the framework incorporates the degradation and fault detection and diagnosis of failure modes across multiple components. The effect of degradation and faults on job processing times is learned as a distribution from the field data. The proposed framework is then validated in a laboratory environment where degradation is produced by inducing degradation and faults in the equipment. By means of various experiments, the optimized makespan is compared for the output schedules in different configurations. When equipment is degraded, production scheduling with PHM-enabled field-synchronized digital twin results in better makespan estimation, if compared to the digital twin without PHM. This shows the superiority of the framework in terms of more realistic makespan estimations, which finally corresponds to improved production schedule optimization, sensitive also to degraded states.

A Novel Distributed Process Monitoring Framework of VAE-Enhanced with Deep Neural Network

Intelligent manufacturing process needs to adopt distributed monitoring scenario due to its massive, high-dimensional and complex data. Distributed process monitoring has been introduced into global monitoring and local monitoring to analyze the characteristic relationship between process data. However, the existing framework methods ignore or suppress the fault information and thus cannot effectively identify the local faults and the time sequence characteristics between units in the batch production system. This paper proposes a novel distributed process monitoring framework based on Girvan-Newman algorithm modular subunit partitioning and probabilistic learning model with deep neural networks. First, Girvan-Newman algorithm is used to divide the complex manufacturing system modularized to reduce the latitude of data processing. Second, variational autoencoder (VAE) is adopted to ensure the stability of local analysis, and long short-term memory is adopted to improve the VAE model to detect global multi-time scale anomalies. Finally, distributed process fault detection is carried out for each subunit in a separate and integrated manner, and the performance of the framework in distributed process monitoring is analyzed through two fault detection indicators T2 and SPE statistics. A case study of the Tennessee Eastman Process is used to demonstrate the performance and applicability of the proposed framework. Results show that the proposed VAE enhancement framework based on the DNN could accurately identify faults in distributed process monitoring and locate the specific sub-units where the fault occurs. Compared with VAE-DNN method and traditional process monitoring methods, the framework proposed in this paper has higher fault detection rate and lower false alarm rate, and the detection rate of some faults can reach 100%.

A novel minority sample fault diagnosis method based on multisource data enhancement

AbstractEffective fault diagnosis has a crucial impact on the safety and cost of complex manufacturing systems. However, the complex structure of the collected multisource data and scarcity of fault samples make it difficult to accurately identify multiple fault conditions. To address this challenge, this paper proposes a novel deep‐learning model for multisource data augmentation and small sample fault diagnosis. The raw multisource data are first converted into two‐dimensional images using the Gramian Angular Field, and a generator is built to transform random noise into images through transposed convolution operations. Then, two discriminators are constructed to evaluate the authenticity of input images and the fault diagnosis ability. The Vision Transformer network is built to diagnose faults and obtain the classification error for the discriminator. Furthermore, a global optimization strategy is designed to upgrade parameters in the model. The discriminators and generator compete with each other until Nash equilibrium is achieved. A real‐world multistep forging machine is adopted to compare and validate the performance of different methods. The experimental results indicate that the proposed method has multisource data augmentation and minority sample fault diagnosis capabilities. Compared with other state‐of‐the‐art models, the proposed approach has better fault diagnosis accuracy in various scenarios.

An adaptive Copula function-based framework for fault detection in semiconductor wafer fabrication

Wafer fabrication is a complex manufacturing system. Timely identification of the key influencing factors associated with the cause of defects is critical to wafer yield enhancement. However, the massive wafer fabrication process dataset has various data types, uncertain data distribution, and complex correlation relationships. These issues make the statistical sense of correlation association measures, and fault detection (FD) methods face many challenges. Therefore, this study proposes an adaptive Copula function-based framework for FD in semiconductor wafer fabrication. Firstly, the marginal distribution of the wafer fabrication process data was determined. After that, a joint distribution model based on the Copula function was designed for the nonlinear relationship and the nonnormal distribution characteristics. Based on the model mentioned above, the traditional Copula function selection method has a high-dimensional spatial failure problem based on the Euclidean distance theory. Therefore, a high-dimensional spatial distance measurement method based on improved kernel distance measurement (IKDM) is designed to realize the adaptive selection of Copula functions. Afterward, the key influencing factors associated with wafer yield are identified through feature sensitivity analysis and validated with multiple prediction models for comparison. Finally, a case study using actual data from a semiconductor wafer fabrication system is used to validate the effectiveness of the proposed methodological framework.

Supervised and unsupervised techniques in textile quality inspections

Quality inspection is a critical step in ensuring the quality and efficiency of textile production processes. With the increasing complexity and scale of modern textile manufacturing systems, the need for accurate and efficient quality inspection and defect detection techniques has become paramount. This paper compares supervised and unsupervised Machine Learning techniques for defect detection in the context of industrial textile production, in terms of their respective advantages and disadvantages, and their implementation and computational costs. We explore the use of an autoencoder for the detection of defects in textiles. The goal of this preliminary work is to find out if unsupervised methods can successfully train models with good performance without the need for defect labelled data.

Operator-integrated cluster analysis for production quality control

The paper introduces the Quality Clusters for Operators (QC4O) approach, aimed at improving quality control strategies in modern manufacturing. It identifies a dual challenge: the lack of communication between data analysts and operators, along with the insufficient integration of their respective methodologies, hindering the acceptance of novel control strategies. To address these challenges, the paper proposes integrating modern machine learning-based methods with methods used by operators, enhancing usability and acceptance. This integration aims to facilitate better communication and expedite quality decision-making. The approach is demonstrated through its application in hairpin stator production, representing complex manufacturing systems.

Expanding the boundaries of Zero Defect Manufacturing - A systematic literature review

With Industry 5.0 on the horizon, research and innovation is prioritising the transition to sustainable, human-centred and resilient manufacturing. In this context, Zero Defect Manufacturing (ZDM) strategies combine tools, resources and rules with the aim of avoiding defects and increasing the sustainable performance of complex manufacturing systems. Five distinct strategies for ZDM have been identified in the literature: (I) detection, (II) prediction, (III) prevention, (IV) repair, and (V) mitigation or compensation. The main motivation of this paper is to discuss an extension of these five existing dimensions by three more, which will enable the transformation of classical ZDM towards a more sustainable production. The main objective of this paper is to conduct a systematic literature review that covers the state of the art of ZDM and highlights the need to add the three (Zero3) dimensions: i) Zero Resource Loss (resource and emission improvement) ii) Zero Human Potential Loss (productivity and stability improvement) iii) Zero Data Gap (increase in efficiency of data use).

Digital twin and parameter correlation-enabled variant design of production lines

ABSTRACT The rapid transformation of production lines into a new design scheme is the key to improving the market competitiveness of enterprises. The production line is a complex manufacturing system with a complex structure. There are multidisciplinary correlation networks between different design dimensions, such as causality, mapping, and transfer. Clarifying these correlative relations is the key to the design of production line correlation. In this paper, a descriptive system is built for the production line configuration model, the motion model, the control model, and the optimization model, and the design content of production lines is clarified. A design framework of production line correlation based on the digital twin technology is proposed, and an optimization system of design schemes is built in the form of hierarchical iteration. Polychromatic sets are used to identify the relationship between different dimensions. The high-fidelity simulation ability of the digital twin technology is taken advantage of to verify the proposed four-in-one variant design method in the mobile phone welding assembly line.

A Copula network deconvolution-based direct correlation disentangling framework for explainable fault detection in semiconductor wafer fabrication

Wafer fabrication is a highly complex manufacturing system. Using complex network models to portray the correlation between parameters is an effective tool for finding the key influencing factors associated with the cause of wafer defects. However, the complex network in a wafer fabrication system has many nonlinearities, non-normal distributions, coupling, and spurious correlations. Quantitative clarification of direct and indirect correlations in the complex network is the prerequisite for achieving explainable fault detection in smart manufacturing. Therefore, a Copula network deconvolution-based direct correlation disentangling framework is proposed in the context of explainable fault detection in semiconductor wafer fabrication. Firstly, The complex network correlation diagram of the parameters in the wafer fabrication process is constructed with each parameter as a node and the correlation coefficients between parameters as connected edges. Then, a nonlinear correlation metric model based on adaptive Copula function selection is designed to deal with the nonlinear correlation of complex network models. The adaptive selection of the Copula function is realized by the goodness-of-fit test method based on Euclidean distance. After that, considering the coupling and spurious correlation in the complex network model, a network deconvolution-based fault detection method is designed to identify direct correlation. Finally, a case study using the actual data from semiconductor wafer fabrication systems is conducted to compare the existing mainstream fault detection methods and validate the effectiveness of the proposed method.

Modeling and Simulation of a Digital Twin of a Production System for Industry 4.0 with Work-in-Process Synchronization

One of the main problems of modern manufacturing systems is the increasing complexity related to modern Industry 4.0 technologies that are fundamentally changing manufacturing and logistics processes and operations. Industry 4.0 includes, e.g., flexible automation and robotization, which make complex manufacturing systems difficult to analyze. Some modeling and simulation methods are being used to solve industrial problems and can serve as an interface between the production level and management level. The new trend of the Digital Twin, creating simulation models as similar as possible to the real system, and a Digital Twin framework for a manufacturing line from the automotive industry, was considered. Simulation models typically start from the empty state and some warmup time is required to achieve the stable state. The Key Performance Indicators were also analyzed for the stable state. However, there are many stochastic parameters such as machinery failures, human errors, quality issues, etc., that make the real processes differ from simulated processes, and cause the instability of production throughput and changes in the Work in Process. To analyze the Work in Process in the model, initialization of the model with proper production data is required, as the Digital Twin uses data synchronization with the production database. In this paper, the digital model of a human-robot-operated manufacturing system with Work-in-Process data synchronization is analyzed, and the results of the statistical analysis of simulation experiments are presented. The obtained results show high variability of finished production, which is related to system instability due to random failures, especially when the system starts from an empty state. However, an increase in initial Work in Process results in better efficiency and stability for the whole system. The DT simulation of the manufacturing system can be very helpful, as it becomes a repository of knowledge about the real system and enables the analysis of its dynamics. However, for proper functionality, the model should include information about the current WIP state, which enables the start of the simulation with exactly the same number of queues as in the real system. The presented method can also be used in similar enterprises from other industries, especially for those with discrete processes or high WIP variability, and for further synchronization of other DT parameters.

Unrelated parallel batch processing machine scheduling with time requirements and two-dimensional packing constraints

In various complex manufacturing systems such as wafer fabrication, ceramic processes, and additive manufacturing, a single machine often performs multiple distinct jobs simultaneously, requiring non-overlapping positions in the 2D-plane. As the demand for manufacturing with two-dimensional (2D) packing constraints continues to rise, there is an urgent need to address the integrated scheduling of batch processing machines (BPMs) and 2D packing. However, only a limited number of studies have explored BPM scheduling problems with 2D packing constraints. In this study, we focus on the scheduling of unrelated parallel BPMs to process jobs with non-identical sizes, unequal release dates, and due dates. To model the machine’s capacity, we move beyond the traditional one-dimensional knapsack approach and consider it as a 2D rectangle, taking into account the 2D packing constraints. It is crucial to ensure that no overlapping or stacking occurs within the machine’s capacity under these constraints. To address this problem, we propose a mixed integer linear programming model as the initial approach. Additionally, we develop an adaptive large neighborhood search (ALNS) heuristic specifically designed for handling large instances. The ALNS incorporates eleven removal operators and seven insertion operators, offering a comprehensive exploration and improvement of solutions. To tackle the packing procedure, we adopt two distinct packing patterns, namely Skyline and Open Space. These patterns play a significant role in optimizing the packing of jobs within the machine’s capacity. Furthermore, we conduct extensive computational experiments, generating 48 categories of instances with varying job attributes. These experiments serve to compare the performance of the two packing patterns and validate the effectiveness of our ALNS approach. In conclusion, our research addresses the critical gap in BPM scheduling problems with 2D packing constraints. By introducing a mixed integer linear programming model and developing the ALNS heuristic with diverse operators, coupled with the adoption of different packing patterns, we present a comprehensive approach to tackle this complex problem. Computational experiments are conducted to compare packing patterns and verify the performance of our ALNS method.

A robust optimal scheduling system based on multi-performance driving for complex manufacturing systems

A robust optimal scheduling method driven by multi-objects is proposed for the collaborative optimization problem between dynamic scheduling, preventive maintenance of equipment, and robustness of scheduling schemes in a complex manufacturing system. Firstly, the equipment maintenance task is mapped to the process level, and composite dispatching rules with weight parameters are designed, which flexibly consider equipment maintenance and system processing status. Secondly, the performance-driven ideology is analyzed through two models based on the IWOA-MLP algorithm. Thirdly, the feedback mechanism ideology facilitates adaptive closed-loop optimizations. Finally, a series of experiments were carried out on the simulation platform of a semiconductor manufacturing enterprise in Shanghai. The experimental results show that the proposed robust optimal scheduling system can effectively deal with mixed uncertainty, improve production performances, and maintain highly robust measures.

Joint Design of Communication and Computing for Digital-Twin-Enabled Aircraft Final Assembly

Aircraft final assembly line (AFAL) is a typical complex manufacturing system with multiple installation and test processes operating simultaneously at each workstation. Lots of robots and sensors are connected and operated for heterogeneous processes by sharing limited communication and computing resources. How to manage devices and resources in a coordinated and efficient way is thus very challenging. Digital twin (DT) is a powerful technology for multiple objects management in the complex assembly system. It enables us to coordinate various devices and allocated communication and computing resources at workstations. In this paper, two main processes, i.e. vision-assisted installation and flight control system test, are considered in the AFAL. We introduce a DT-enabled AFAL system, and propose a DT-assisted heterogeneous processes coordinated (DT-HPC) framework to coordinate various devices and resources at each workstation. The wirelessly connected robots and sensors are applied for perception and information fusion. In order to minimize the total energy consumption and computing resources of all the wireless devices, joint design of the wireless channel allocation, transmission power and computing resource allocation are proposed to satisfy the diverse quality of service (QoS) requirements. Firstly, we propose a priority-aware channel assignment (PACA) algorithm to allocate channels for sensors and robots. Then, the optimal computing resource allocation strategy for two processes is derived while guaranteeing the processing latency requirements. Next, we derive the minimum transmission power of wireless sensors to guarantee the monitoring accuracy and calculate the transmission power of robots to obtain the satisfied transmission rate. Finally, we apply the DT-HPC framework in the DT-enabled AFAL system. The simulation results prove that our proposed algorithms can save energy while guaranteeing different QoS requirements.

A Hybrid Simulation and Reinforcement Learning Algorithm for Enhancing Efficiency in Warehouse Operations

The use of simulation and reinforcement learning can be viewed as a flexible approach to aid managerial decision-making, particularly in the face of growing complexity in manufacturing and logistic systems. Efficient supply chains heavily rely on steamlined warehouse operations, and therefore, having a well-informed storage location assignment policy is crucial for their improvement. The traditional methods found in the literature for tackling the storage location assignment problem have certain drawbacks, including the omission of stochastic process variability or the neglect of interaction between various warehouse workers. In this context, we explore the possibilities of combining simulation with reinforcement learning to develop effective mechanisms that allow for the quick acquisition of information about a complex environment, the processing of that information, and then the decision-making about the best storage location assignment. In order to test these concepts, we will make use of the FlexSim commercial simulator.

Multi-node system modeling and monitoring with extended directed graphical models

Complex manufacturing systems usually contain a large number of variables. Dominated by certain engineering mechanisms, these variables show complicated relationships that cannot be effectively expressed by simple correlation matrices or functions, thus increasing the difficulty of modeling and monitoring these systems. The directed graphical model (DGM) has been used as a flexible tool for describing the relationship among variables in complex systems. However, the DGM treats all variables equally and fails to consider the structural information among them that usually exists. To address this problem, an extended directed graphical model (EDGM) and related parameter estimation, monitoring, and structure learning methods are proposed in this work. Taking prior engineering knowledge into consideration, the EDGM assigns variables into groups and uses groups of variables as nodes in the graph model. By adding hidden state variables to each node, the EDGM can effectively represent the relationship within and between nodes and provide promising monitoring performance. Numerical experiments and a real-world case study of the monocrystalline silicon growth process are performed to verify the effectiveness of the proposed methods.