Journal of Manufacturing Systems最新文献

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.

Human-robot collaborative assembly (HRCA) is one of the current trends of intelligent manufacturing, and assembly action recognition is the basis of and the key to HRCA. A multi-scale and multi-stream graph convolutional network (2MSGCN) for assembly action recognition is proposed in this paper. 2MSGCN takes the temporal skeleton sample as input and outputs the class of the assembly action to which the sample belongs. RGBD images of the operator performing the assembly actions are captured by three RGBD cameras mounted at different viewpoints and pre-processed to generate the complete human skeleton. A multi-scale and multi-stream (2MS) mechanism and a feature fusion mechanism are proposed to improve the recognition accuracy of 2MSGCN. The 2MS mechanism is designed to input the skeleton data to 2MSGCN in the form of a joint stream, a bone stream and a motion stream, while the joint stream further generates two sets of input with rough scales to represent features in higher dimensional human skeleton, which obtains information of different scales and streams in temporal skeleton samples. And the feature fusion mechanism enables the fused feature to retain the information of the sub-feature while incorporating union information between the sub-features. Also, the improved convolution operation based on Ghost module is introduced to the 2MSGCN to reduce the number of the parameters and floating-point operations (FLOPs) and improve the real-time performance. Considering that there will be transitional actions when the operator switches between assembly actions in the continuous assembly process, a transitional action classification (TAC) method is proposed to distinguish the transitional actions from the assembly actions. Experiments on the public dataset NTU RGB+D 60 (NTU 60) and a self-built assembly action dataset indicate that the proposed 2MSGCN outperforms the mainstream models in recognition accuracy and real-time performance.

The manufacturing and remanufacturing sectors are increasingly embracing sustainability as a critical aspect of their operations. However, existing sustainability frameworks often fall short of capturing the multifaceted nature of sustainability and addressing uncertainties. To address these limitations, this paper proposes a novel holistic sustainability assessment framework specifically tailored for remanufacturing systems. By integrating economic, environmental, and social dimensions, the framework provides a comprehensive approach to decision-making under uncertainty. The framework incorporates a flexible weighting scheme, allowing customization based on organizational priorities, and addresses uncertainties through stochastic optimization techniques. The applicability and effectiveness of the framework are demonstrated through case studies in diverse industries, including consumer electronics, automotive, and industrial machinery remanufacturing. Sensitivity analyses provide insights into the robustness of the framework and the impact of varying sustainability indicator weights, uncertain parameter distributions, and environmental regulations. The proposed framework offers a valuable tool for remanufacturing companies, enhancing their sustainability performance and navigating the complexities of uncertain operating environments.

The concept of the Digital Twin, which in the context of this paper is the virtual representation of a production system or its components, can be used as a "digital playground" to master the increasing complexity of these assets. One of the central subcomponents of the Digital Twin are behavior models that can enable benefits over the entire machine life cycle. However, the creation, adaption and use of behavior models throughout the machine life cycle is very time-consuming, which is why approaches to improve the cost-benefit ratio are needed. Furthermore, there is a lack of specific use cases that illustrate the application and added benefit of behavior models over the machine life cycle, which is why the universal application of behavior models in industry is still lacking compared to research. This paper first presents the fundamentals, challenges and related work on Digital Twins and behavior models in the context of the machine life cycle. Then, concepts for low-effort creation and automatic adaption of Digital Twins are presented, with a focus on behavior models. Finally, the aforementioned gap between research and industry is addressed by demonstrating various realized use cases over the machine life cycle, in which the advantages as well as the application of behavior models in the different life cycle phases are shown.

Medical devices and products are a special type of manufactured object. Medical applications normally have higher requirements for quality, complexity, personalization, precision and low fault tolerance than other types of manufactured product. It is therefore especially important to develop smart systems to support all phases of medical-related manufacturing. However, in recent years, there is lack of a thorough literature survey for the smart system research in this area. Meanwhile, new technologies have been rapidly developed recently, but a comprehensive outlook of the future research trend is still missing. Thus, in this work we survey and analyse recent research achievements in detail. The first aim of this paper is to determine what smart manufacturing system research is important for the medical applications, as well as identifying the essential supporting technologies. Second, key research areas and challenges are identified and discussed to guide the future research in this area.

For the manufacture and assembly of the mechanical products, quality management is the key feature to improve the service performance, reduce the overall costs and enhance the sustainability of the manufacturing systems. While, with the emergence of advanced data-driven and digital twin technologies, the Zero-Defect Manufacturing (ZDM), which corrects, predicts, and prevents product defects based on multi-sources of data, is of great significance in improving assembly quality. As the specific application for the utilization of ZDM in product assembly, the critical performance index of the assembly results is predicted by taking into account the multi-source factors such as geometric deviation of the parts, material properties, assembly sequences and process boundary conditions during assembly. In this paper, we address the high computational cost and low computational efficiency of numerical simulation methods under multi-source factors, and propose a data-driven approach named DTA-VIT based on the fusion of heterogeneous variables for digital twin assembly modeling of products. Firstly, the geometric and performance variables of the assembly process are analyzed and modelled. Secondly, a multi-source assembly data fusion network under the Vision Transformer framework is developed. This network takes the parameter space, which fuses multi-source variables from the assembly process as input and the assembly result as output. Finally, a case study of the assembly process of composite bolted joint structures in aircraft assembly is conducted to verify the effectiveness and feasibility of the proposed method. The methodology provides a solid foundation for subsequent assembly quality control and prevent by predicting assembly performance efficiently, ultimately enabling the production of high-quality products.

The collection of large volumes of temporal data during the production process is streamlined in a cyber manufacturing environment. The ineluctable abnormal patterns in these time series often serve as indicators of potential manufacturing faults. Consequently, the presence of effective analytical methods becomes essential for monitoring and recognizing these abnormal manufacturing patterns. However, the extensive process data may contain various minor abnormal patterns, typically reflecting changes in production status influenced by multiple anomalous causes. This study introduces an approach for recognizing abnormal manufacturing patterns through multi-scale time series classification (TSC). Long-term process signals undergo slicing using dynamically sized observation windows and subsequent classification at multiple scales employing our proposed TSC model, the distance mode profile-multi-branch dilated convolution network (DMP-MDNet). DMP-MDNet comprises two key modules aimed at bypassing complicated feature engineering and enhancing generalization capability. The first module, DMP, uses similarity measurement to encode scale- and magnitude-invariant temporal properties. Subsequently, the MDNet, equipped with multi-receptive field sizes, effectively leverages multi-granularity data for accurate classification. The effectiveness of our method is demonstrated through the analysis of a real-world body-in-white production dataset and various widely used public TSC datasets, showing promising applicability in actual manufacturing processes.

Centrifugal blowers are easy to get faults due to the harsh working environment, and appropriate fault early warning is of great significance for predictive maintenance. Traditional fault early warning methods have poor resistance and feature learning ability in dealing with multivariate data with noise, and cannot achieve domain adaptation in different working environments. Aimed at solving these problems, this paper proposes a novel fault early warning method for centrifugal blowers based on stacked denoising autoencoder with sliding window (SW-SDAE) and transfer learning. The developed SW-SDAE model can effectively learn representative degradation features and temporal dependence from multivariate time-series data with noise. The reconstruction errors of SW-SDAE are used to construct the health indicators, which accurately characterizes the health status of the centrifugal blower. Meanwhile, transfer learning is employed to solve the problem of domain adaptation for different working environments. The established source domain warning model is successfully transferred to the target domain by minimizing the maximum mean discrepancy. When the health indicator exceeds the warning threshold, a fault early warning is performed. Experimental results demonstrate that the developed SW-SDAE warning model integrating transfer learning significantly resists the interference of noise and improves the domain adaptability for different working conditions. The proposed method achieves fault early warning 5.67 h without false alarms before failure and shows superior warning performance compared with traditional warning methods.

Knowledge-intensive production represents a primary trend in industrial manufacturing, which heavily relies on the production logs of large-scale, historically similar orders for enhancing production efficiency and process quality. These logs are essential for predicting resource allocation and identifying bottlenecks in throughput. As a result, root cause analysis of the production process state is crucial for supporting decision-making in these settings. However, current methodologies heavily depend on expert knowledge, making the analysis time-consuming and inefficient for large-scale, multivariable processes. Although the development of large language models and autonomous agents presents a potential solution, these models are limited in their direct interaction with event logs due to inadequate data representation, token constraints, and insufficient accuracy. Therefore, enabling the interactive capabilities of large language models to overcome these specific limitations in process event data and industrial domain illusions poses a significant challenge. To address these issues, this paper introduces the ProcessCarbonAgent framework, an autonomous agent empowered by large language models, designed to enhance decision-making within industrial processes. Initially, a process data agent combines predefined semantic text representation methods with process template prompting strategies to improve interaction capabilities. Subsequently, an intention agent utilizing self-information and large language models is developed to address context length limitations by identifying and eliminating redundancies. Finally, a two-stage confidence estimation method is implemented to refine the precision of decision-making assistance, thereby improving the accuracy of decisions supported by large language models. Experiments with textile industry carbon emission data reveal that the assisted decision-making scores employing a compression ratio of 0.5, closely align with scores from manually labeled evaluations, with a 98% overlap across scoring intervals. Moreover, in contrast to relying solely on the original evaluation method, the two-stage confidence estimation method has led to a 20% increase in accuracy performance. The ProcessCarbonAgent achieved scores of 16.64, 55.13, 26.32, and 34.17 on METEOR, BERTScore, NUBIA, and BLEURT, respectively. The results demonstrate that the ProcessCarbonAgent framework significantly enhances the decision-making process for high-carbon emission states in industrial production, providing technical support for the low-carbon transformation and intelligent upgrading of these processes.

Cognitive mass personalization (CMP) is a promising manufacturing paradigm; equipped with cognitive capabilities like reasoning, CMP satisfies changeable needs via configuring personalized products at scale. In CMP, knowledge graphs (KGs) are exploited by smart product-service systems (SPSS) to support cognitive configuration/reconfiguration processes. However, the extant KG-enabled SPSSs are built upon fixed configurations and hybrid frameworks due to lacking a graph embedding (GE) model to render cognitive configuration decisions. In fact, GE is scarcely used in SPSS configuration, because it is not only compromised by the heterogeneity of KGs entailed by content-related specifications and complex structures but also influenced by the feature randomness and feature drift problems, which are triggered by accumulative errors and inconsistent objectives due to noisy assignments and different configuration tasks, separately. To address these limitations, a Self-X Heterogeneous Attributed Graph Embedding (SXHAGE) model is proposed in a Self-X architecture, which includes 1) self-attention graph attention networks, 2) a self-adaptive autoencoder, and 3) self-optimizing training objectives, to present heterogeneous data through jointly optimizing heterogeneous attributed entities and relations. A systematic SXHAGE-based configuration framework, in which product family design and configuration recommending are enabled by graph clustering and link prediction, is developed as a continuous updating loop to proactively configure personalized products. A real-world case study, i.e., configure personalized electric clippers via a web-based sustainable configuration platform, is performed to validate the applicability of the proposed framework in the CMP context. Moreover, extensive experiments on the case study dataset demonstrate the superiority of SXHAGE over the state-of-the-art algorithms, e.g., surpassing Deep Neighbor-Aware Embedding (DNENC) by 18 % in F1-score for graph clustering and by 5 % in ROC-AUC for link prediction.