Pub Date : 2024-11-23DOI: 10.1016/j.jmsy.2024.11.007
Shukai Fang , Shuguang Liu , Xuewen Wang , Jiapeng Zhang , Jingquan Liu , Qiang Ni
Real-time human-robot collision detection is crucial for ensuring the safety of operators during human-robot collaboration(HRC) and for improving the efficiency of such collaboration. It plays an important role in promoting the development of intelligent manufacturing. To address this issue, our team developed a multi-faceted collision detection system using eXtended Reality (XR) technology, specifically designed for complex and dynamic human-robot collaborative operations. The system integrates three different methods: a Virtual Reality (VR) detection method that enables robots to better perceive and detect human operators. An Augmented Reality (AR) detection method that enhances the operator’s perception of the robot. And a fusion detection and evaluation method. This detection and evaluation method assesses the effectiveness of collaboration by analyzing key performance indicators, such as real-time distance between human and robot, changes in the operator’s Heart Rate(HR), and overall task completion time. Through empirical research on the human-robot collaborative assembly task of T-series spiral bevel gear reducers, the effectiveness of the innovative method is verified. The research results show that this method significantly improves safety and operational efficiency, providing a novel solution detection in industrial manufacturing environments.
实时人机碰撞检测对于确保人机协作过程中操作人员的安全以及提高人机协作的效率至关重要。它在促进智能制造的发展方面发挥着重要作用。为了解决这个问题，我们的团队利用扩展现实（XR）技术开发了一种多方位碰撞检测系统，专门用于复杂和动态的人机协作操作。该系统集成了三种不同的方法：一种虚拟现实（VR）检测方法，可使机器人更好地感知和检测人类操作员。增强现实（AR）检测方法，可增强操作员对机器人的感知。以及一种融合检测和评估方法。这种检测和评估方法通过分析关键性能指标来评估协作的有效性，例如人与机器人之间的实时距离、操作员的心率变化以及总体任务完成时间。通过对 T 系列螺旋锥齿轮减速器的人机协作装配任务进行实证研究，验证了创新方法的有效性。研究结果表明，该方法显著提高了安全性和操作效率，为工业制造环境中的检测提供了新颖的解决方案。
{"title":"A multivariate fusion collision detection method for dynamic operations of human-robot collaboration systems","authors":"Shukai Fang , Shuguang Liu , Xuewen Wang , Jiapeng Zhang , Jingquan Liu , Qiang Ni","doi":"10.1016/j.jmsy.2024.11.007","DOIUrl":"10.1016/j.jmsy.2024.11.007","url":null,"abstract":"<div><div>Real-time human-robot collision detection is crucial for ensuring the safety of operators during human-robot collaboration(HRC) and for improving the efficiency of such collaboration. It plays an important role in promoting the development of intelligent manufacturing. To address this issue, our team developed a multi-faceted collision detection system using eXtended Reality (XR) technology, specifically designed for complex and dynamic human-robot collaborative operations. The system integrates three different methods: a Virtual Reality (VR) detection method that enables robots to better perceive and detect human operators. An Augmented Reality (AR) detection method that enhances the operator’s perception of the robot. And a fusion detection and evaluation method. This detection and evaluation method assesses the effectiveness of collaboration by analyzing key performance indicators, such as real-time distance between human and robot, changes in the operator’s Heart Rate(HR), and overall task completion time. Through empirical research on the human-robot collaborative assembly task of <em>T</em>-series spiral bevel gear reducers, the effectiveness of the innovative method is verified. The research results show that this method significantly improves safety and operational efficiency, providing a novel solution detection in industrial manufacturing environments.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 26-45"},"PeriodicalIF":12.2,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142699247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-23DOI: 10.1016/j.jmsy.2024.10.015
Filippo Sanfilippo , Muhammad Hamza Zafar , Timothy Wiley , Fabio Zambetta
Multi-modal human–machine interfaces have recently undergone a remarkable transformation, progressing from simple human–robot interaction (HRI) to more advanced human–robot collaboration (HRC) and, ultimately, evolving into the concept of human–robot teaming (HRT). The aim of this work is to delineate a progressive path in this evolving transition. A structured, position-oriented review is proposed. Rather than aiming for an exhaustive survey, our objective is to propose a structured approach in a field that has seen diverse and sometimes divergent definitions of HRI/C/T in the literature. This conceptual review seeks to establish a unified and systematic framework for understanding these paradigms, offering clarity and coherence amidst their evolving complexities. We focus on integrating multiple sensory modalities — such as visual, aural, and tactile inputs — within human–machine interfaces. Central to our approach is a running use case of a warehouse workflow, which illustrates key aspects including modelling, control, communication, and technological integration. Additionally, we investigate recent advancements in machine learning and sensing technologies, emphasising robot perception, human intention recognition, and collaborative task engagement. Current challenges and future directions, including ethical considerations, user acceptance, and the need for explainable systems, are also addressed. By providing a structured pathway from HRI to HRT, this work aims to foster a deeper understanding and facilitate further advancements in human–machine interaction paradigms.
{"title":"From caged robots to high-fives in robotics: Exploring the paradigm shift from human–robot interaction to human–robot teaming in human–machine interfaces","authors":"Filippo Sanfilippo , Muhammad Hamza Zafar , Timothy Wiley , Fabio Zambetta","doi":"10.1016/j.jmsy.2024.10.015","DOIUrl":"10.1016/j.jmsy.2024.10.015","url":null,"abstract":"<div><div>Multi-modal human–machine interfaces have recently undergone a remarkable transformation, progressing from simple human–robot interaction (HRI) to more advanced human–robot collaboration (HRC) and, ultimately, evolving into the concept of human–robot teaming (HRT). The aim of this work is to delineate a progressive path in this evolving transition. A structured, position-oriented review is proposed. Rather than aiming for an exhaustive survey, our objective is to propose a structured approach in a field that has seen diverse and sometimes divergent definitions of HRI/C/T in the literature. This conceptual review seeks to establish a unified and systematic framework for understanding these paradigms, offering clarity and coherence amidst their evolving complexities. We focus on integrating multiple sensory modalities — such as visual, aural, and tactile inputs — within human–machine interfaces. Central to our approach is a running use case of a warehouse workflow, which illustrates key aspects including modelling, control, communication, and technological integration. Additionally, we investigate recent advancements in machine learning and sensing technologies, emphasising robot perception, human intention recognition, and collaborative task engagement. Current challenges and future directions, including ethical considerations, user acceptance, and the need for explainable systems, are also addressed. By providing a structured pathway from HRI to HRT, this work aims to foster a deeper understanding and facilitate further advancements in human–machine interaction paradigms.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"78 ","pages":"Pages 1-25"},"PeriodicalIF":12.2,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142699297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-22DOI: 10.1016/j.jmsy.2024.11.012
Nathaly Rea Minango , Mikael Hedlind , Antonio Maffei
The early stages of product design are critical for incorporating manufacturing perspectives. Recognizing the significance of assembly in discrete product manufacturing, the study emphasizes the need to consider the intricacies of assembly early in the design stages. While existing research has addressed assembly features, especially for insertion, this study focuses on handling features, seeking to bridge the gap in their comprehensive representation within the product model. Based on a relational analysis, product characteristics relevant for handling were identified and represented by using a modelling strategy that facilitates their timely addition to the product model. A case study was developed to demonstrate its application. The main contributions of this work comprise an extensive list of product characteristics related to handling processes, a proposal for integrating these characteristics into the product model, and a collaborative way to define product features during product design. Future research directions point to the establishment of a model-based definition for assembly processes, paving the way for enhanced cross-disciplinary communication in the fields of product design and assembly planning.
{"title":"Handling features in assembly: Integrating manufacturing considerations early in design discussions","authors":"Nathaly Rea Minango , Mikael Hedlind , Antonio Maffei","doi":"10.1016/j.jmsy.2024.11.012","DOIUrl":"10.1016/j.jmsy.2024.11.012","url":null,"abstract":"<div><div>The early stages of product design are critical for incorporating manufacturing perspectives. Recognizing the significance of assembly in discrete product manufacturing, the study emphasizes the need to consider the intricacies of assembly early in the design stages. While existing research has addressed assembly features, especially for insertion, this study focuses on handling features, seeking to bridge the gap in their comprehensive representation within the product model. Based on a relational analysis, product characteristics relevant for handling were identified and represented by using a modelling strategy that facilitates their timely addition to the product model. A case study was developed to demonstrate its application. The main contributions of this work comprise an extensive list of product characteristics related to handling processes, a proposal for integrating these characteristics into the product model, and a collaborative way to define product features during product design. Future research directions point to the establishment of a model-based definition for assembly processes, paving the way for enhanced cross-disciplinary communication in the fields of product design and assembly planning.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 1077-1100"},"PeriodicalIF":12.2,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-21DOI: 10.1016/j.jmsy.2024.10.025
Rômulo César Cunha Lima , Leonardo Adriano Vasconcelos de Oliveira , Suane Pires Pinheiro da Silva , José Daniel de Alencar Santos , Rebeca Gomes Dantas Caetano , Francisco Nélio Costa Freitas , Venício Soares de Oliveira , Andreyson de Freitas Bonifácio , Pedro Pedrosa Rebouças Filho
This research presents a novel methodology for enhancing energy efficiency in industrial manufacturing systems through machine learning techniques. Specifically, the study focuses on the automatic classification of five steel types — ABNT SAE 1020, 1045, 4140, 4340, and VC — based on electrical and mechanical characteristics observed during turning operations. The methodology includes the prediction of energy consumption for these steel types, applying regression models, under various machining conditions, including different rotation speeds and feed rates. To the best of the authors’ knowledge, this study is the first to address this issue using this specific approach. The proposed method was validated through computational experiments using multiple machine learning algorithms, with the Multilayer Perceptron (MLP) neural network achieving the highest classification accuracy of 95.52%. In terms of energy consumption prediction, MLP models demonstrated superior performance in 13 out of 15 turning scenarios. The regression analysis further confirmed the effectiveness of these models, achieving low Root Mean Squared Error (RMSE) values across different configurations. The results indicate that integrating machine learning into machining processes can significantly improve energy efficiency, leading to more sustainable industrial practices.
{"title":"A new proposal for energy efficiency in industrial manufacturing systems based on machine learning techniques","authors":"Rômulo César Cunha Lima , Leonardo Adriano Vasconcelos de Oliveira , Suane Pires Pinheiro da Silva , José Daniel de Alencar Santos , Rebeca Gomes Dantas Caetano , Francisco Nélio Costa Freitas , Venício Soares de Oliveira , Andreyson de Freitas Bonifácio , Pedro Pedrosa Rebouças Filho","doi":"10.1016/j.jmsy.2024.10.025","DOIUrl":"10.1016/j.jmsy.2024.10.025","url":null,"abstract":"<div><div>This research presents a novel methodology for enhancing energy efficiency in industrial manufacturing systems through machine learning techniques. Specifically, the study focuses on the automatic classification of five steel types — ABNT SAE 1020, 1045, 4140, 4340, and VC — based on electrical and mechanical characteristics observed during turning operations. The methodology includes the prediction of energy consumption for these steel types, applying regression models, under various machining conditions, including different rotation speeds and feed rates. To the best of the authors’ knowledge, this study is the first to address this issue using this specific approach. The proposed method was validated through computational experiments using multiple machine learning algorithms, with the Multilayer Perceptron (MLP) neural network achieving the highest classification accuracy of 95.52%. In terms of energy consumption prediction, MLP models demonstrated superior performance in 13 out of 15 turning scenarios. The regression analysis further confirmed the effectiveness of these models, achieving low Root Mean Squared Error (RMSE) values across different configurations. The results indicate that integrating machine learning into machining processes can significantly improve energy efficiency, leading to more sustainable industrial practices.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 1062-1076"},"PeriodicalIF":12.2,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-20DOI: 10.1016/j.jmsy.2024.11.001
Zi Wang , Likun Wang , Giovanna Martínez-Arellano , Joseph Griffin , David Sanderson , Svetan Ratchev
Photogrammetry is extensively used in manufacturing processes due to its non-contact nature and rapid data acquisition. Positioning photogrammetry cameras requires knowledge of the manufacturing process and time in manual field-of-view (FoV) adjustment. Such a lengthy and labour-intensive process is not suitable for modern manufacturing systems, where automation, robotics and dynamic reconfigurable layout are used to shorten production time and adapt to demand changes. Hence, there exists the need for a fast layout planning approach ensuring manufacturing process feasibility and maximising camera FoV effectiveness. This paper introduces a digital twin based FoV evaluation method and a computationally efficient 3D layout optimisation framework for reconfigurable manufacturing systems. The framework computes optimal layout for photogrammetry cameras and the object of interest (OOI). The automated nature of the proposed framework can speed up planning processes and shorten dynamic system commissioning time. At a technical level, the framework takes advantage of a 3D digital twin, and uses point clouds to represent the camera FoV. Iterative Closest Point (ICP) registration and K-Dimensional Tree (KDTree) intersection techniques are applied to calculate OOI visibility and target coverage ratio. Experimental validation attested to a digital-physical similarity exceeding 93%, indicating a high level of fidelity and the feasibility of station-level 3D layout design in digital twin environments. Feeding into the 3D layout planning, the optimisation framework considers robot reachability, FoV effectiveness, and estimated uncertainty. Given characteristics of the objective function, genetic algorithm, simulated annealing, and Bayesian optimisation were evaluated within a computational budget (100 function calls). The optimised results are compared against a baseline best obtained through brute force grid search. All tested algorithms achieved results within 98% of the grid search’s best solution within 5 min. Genetic algorithm and simulated annealing outperformed the baseline best by 0.16% and 0.25% respectively for OOI visibility, and Bayesian optimisation exceeded the baseline best by 0.12% for target coverage. These findings emphasise the feasibility of the proposed approach and the efficiency of the overall framework, highlighting its applicability across various development stages from design to execution in a dynamic manufacturing environment.
{"title":"Digital twin based photogrammetry field-of-view evaluation and 3D layout optimisation for reconfigurable manufacturing systems","authors":"Zi Wang , Likun Wang , Giovanna Martínez-Arellano , Joseph Griffin , David Sanderson , Svetan Ratchev","doi":"10.1016/j.jmsy.2024.11.001","DOIUrl":"10.1016/j.jmsy.2024.11.001","url":null,"abstract":"<div><div>Photogrammetry is extensively used in manufacturing processes due to its non-contact nature and rapid data acquisition. Positioning photogrammetry cameras requires knowledge of the manufacturing process and time in manual field-of-view (FoV) adjustment. Such a lengthy and labour-intensive process is not suitable for modern manufacturing systems, where automation, robotics and dynamic reconfigurable layout are used to shorten production time and adapt to demand changes. Hence, there exists the need for a fast layout planning approach ensuring manufacturing process feasibility and maximising camera FoV effectiveness. This paper introduces a digital twin based FoV evaluation method and a computationally efficient 3D layout optimisation framework for reconfigurable manufacturing systems. The framework computes optimal layout for photogrammetry cameras and the object of interest (OOI). The automated nature of the proposed framework can speed up planning processes and shorten dynamic system commissioning time. At a technical level, the framework takes advantage of a 3D digital twin, and uses point clouds to represent the camera FoV. Iterative Closest Point (ICP) registration and K-Dimensional Tree (KDTree) intersection techniques are applied to calculate OOI visibility and target coverage ratio. Experimental validation attested to a digital-physical similarity exceeding 93%, indicating a high level of fidelity and the feasibility of station-level 3D layout design in digital twin environments. Feeding into the 3D layout planning, the optimisation framework considers robot reachability, FoV effectiveness, and estimated uncertainty. Given characteristics of the objective function, genetic algorithm, simulated annealing, and Bayesian optimisation were evaluated within a computational budget (100 function calls). The optimised results are compared against a baseline best obtained through brute force grid search. All tested algorithms achieved results within 98% of the grid search’s best solution within 5 min. Genetic algorithm and simulated annealing outperformed the baseline best by 0.16% and 0.25% respectively for OOI visibility, and Bayesian optimisation exceeded the baseline best by 0.12% for target coverage. These findings emphasise the feasibility of the proposed approach and the efficiency of the overall framework, highlighting its applicability across various development stages from design to execution in a dynamic manufacturing environment.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 1045-1061"},"PeriodicalIF":12.2,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-19DOI: 10.1016/j.jmsy.2024.11.006
Longxue Guo , Tianliang Hu , Lili Dong , Songhua Ma
With advancements in manufacturing, knowledge engineering has become important in supporting intelligent decision-making within manufacturing systems. However, existing process knowledge bases, integral to knowledge engineering, and essential for machining efficiency, product cost, and production cycles by integrating multi-source knowledge, are limited to generality, scalability, and adaptability to real production environments. These constraints undermine the application and reliability of process knowledge bases in decision-making. To overcome these challenges, an approach to constructing a dynamic machining process knowledge base (DMPKB) utilizing ontology and production rules is proposed. Firstly, a machining process knowledge model is developed by reorganizing concepts and relations to restructure process cases and experiences, thereby building a comprehensive knowledge base. Secondly, different update strategies are devised to fulfill the requirements of various components within the knowledge base. Finally, the effectiveness is validated by constructing a DMPKB for CNC boring machine bearing seats. Meanwhile, application verification is performed by generating process plans for a CNC boring machine bearing seat, showcasing the feasibility and utility of the developed knowledge base.
{"title":"Ontology and production rules-based dynamic knowledge base construction methodology for machining process","authors":"Longxue Guo , Tianliang Hu , Lili Dong , Songhua Ma","doi":"10.1016/j.jmsy.2024.11.006","DOIUrl":"10.1016/j.jmsy.2024.11.006","url":null,"abstract":"<div><div>With advancements in manufacturing, knowledge engineering has become important in supporting intelligent decision-making within manufacturing systems. However, existing process knowledge bases, integral to knowledge engineering, and essential for machining efficiency, product cost, and production cycles by integrating multi-source knowledge, are limited to generality, scalability, and adaptability to real production environments. These constraints undermine the application and reliability of process knowledge bases in decision-making. To overcome these challenges, an approach to constructing a dynamic machining process knowledge base (DMPKB) utilizing ontology and production rules is proposed. Firstly, a machining process knowledge model is developed by reorganizing concepts and relations to restructure process cases and experiences, thereby building a comprehensive knowledge base. Secondly, different update strategies are devised to fulfill the requirements of various components within the knowledge base. Finally, the effectiveness is validated by constructing a DMPKB for CNC boring machine bearing seats. Meanwhile, application verification is performed by generating process plans for a CNC boring machine bearing seat, showcasing the feasibility and utility of the developed knowledge base.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 1027-1044"},"PeriodicalIF":12.2,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the increasing demand for personalized and diversified products, manufacturing industries are in urgent need of taking measures to reduce the differences among products and enhance flexibility and reconfigurability so as to accommodate these personalized and diversified products. Consequently, this research focuses on the reconfigurable flexible job shop scheduling problem with order splitting taken into consideration. A mixed-integer linear programming model is proposed with the aim of minimizing tardiness costs, reconfiguration costs and energy costs. To solve this problem efficiently, a co-evolution differential evolution algorithm is developed, which is enhanced by an AdaBoost-inspired multiple mutation strategies ensemble mechanism (AMMSE), an AdaBoost-inspired adaptive crossover mechanism (AAC), rule-based initialization, and variable neighborhood search. Among them, AMMSE can effectively ensemble the advantages of different mutation strategies by adaptively selecting a proper number of chromosomes to train mutation strategies with different performance weights. AAC can adaptively control the crossover rate of each gene by evaluating the average importance score of each gene based on the performance weight distribution of chromosomes. Experimental results demonstrate that combining the above improvements can significantly boost the performance of the differential evolution algorithm. As a result, the enhanced algorithm outperforms other state-of-the-art algorithms by a large margin. By using the enhanced algorithm to solve the studied problem, nearly 1.1 times of production costs can be saved.
{"title":"AdaBoost-inspired co-evolution differential evolution for reconfigurable flexible job shop scheduling considering order splitting","authors":"Lixin Cheng , Shujun Yu , Qiuhua Tang , Liping Zhang , Zikai Zhang","doi":"10.1016/j.jmsy.2024.11.003","DOIUrl":"10.1016/j.jmsy.2024.11.003","url":null,"abstract":"<div><div>With the increasing demand for personalized and diversified products, manufacturing industries are in urgent need of taking measures to reduce the differences among products and enhance flexibility and reconfigurability so as to accommodate these personalized and diversified products. Consequently, this research focuses on the reconfigurable flexible job shop scheduling problem with order splitting taken into consideration. A mixed-integer linear programming model is proposed with the aim of minimizing tardiness costs, reconfiguration costs and energy costs. To solve this problem efficiently, a co-evolution differential evolution algorithm is developed, which is enhanced by an AdaBoost-inspired multiple mutation strategies ensemble mechanism (AMMSE), an AdaBoost-inspired adaptive crossover mechanism (AAC), rule-based initialization, and variable neighborhood search. Among them, AMMSE can effectively ensemble the advantages of different mutation strategies by adaptively selecting a proper number of chromosomes to train mutation strategies with different performance weights. AAC can adaptively control the crossover rate of each gene by evaluating the average importance score of each gene based on the performance weight distribution of chromosomes. Experimental results demonstrate that combining the above improvements can significantly boost the performance of the differential evolution algorithm. As a result, the enhanced algorithm outperforms other state-of-the-art algorithms by a large margin. By using the enhanced algorithm to solve the studied problem, nearly 1.1 times of production costs can be saved.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 1009-1026"},"PeriodicalIF":12.2,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-14DOI: 10.1016/j.jmsy.2024.10.018
Xueyan Sun , Weiming Shen , Jiaxin Fan , Birgit Vogel-Heuser , Chunjiang Zhang
Distributed manufacturing is a new trend to accommodate the economic globalization, which means multiple geographically-distributed factories can collaborate to meet urgent delivery requirements. However, such factories may vary due to layout adjustments and equipment aging, thus the production efficiency greatly depends on the allocation of orders. This scenario is frequently found in energy-intensive process industries, e.g., chemical and pharmaceutical and industries, where the lack of buffers usually results in extra non-blocking constraints and makes the production scheduling even harder. Therefore, this paper investigates a distributed heterogeneous hybrid blocking flow-shop scheduling problem (DHHBFSP) for minimizing the makespan and total energy consumption simultaneously, and proposes an improved non-dominated sorting genetic algorithm II (INSGA-II) to address the problem. First, two heuristic algorithms, i.e., bi-objective considered heuristic (BCH) and similarity heuristic (SH), are developed for the population initialization. Then, to speed-up the local search, a comparison method for non-dominated solutions is proposed to reserve more solutions that are likely to be further improved. Afterwards, a probabilistic model is developed to eliminate unnecessary operations during local search processes. Finally, the proposed INSGA-II is tested on benchmark instances and a real-world case for the validation. Numerical experiments suggest that the SH can generates high-quality solutions within a very short period of time, and the BCH has significantly improved average IGD and HV values for the initial population. Besides, the probabilistic model saves considerable computational time for the local search without compromising the solution quality. With the help of these strategies, the proposed INSGA-II improves average IGD and HV values by 68 % and 57 % for the basic NSGA-II respectively, and obtains better Pareto fronts compared to existing multi-objective algorithms on the majority of test instances. Moreover, the industrial case study shows that the proposed INSGA-II is capable of providing solid scheduling plans for a pharmaceutical enterprise with large-scale orders.
{"title":"An improved non-dominated sorting genetic algorithm II for distributed heterogeneous hybrid flow-shop scheduling with blocking constraints","authors":"Xueyan Sun , Weiming Shen , Jiaxin Fan , Birgit Vogel-Heuser , Chunjiang Zhang","doi":"10.1016/j.jmsy.2024.10.018","DOIUrl":"10.1016/j.jmsy.2024.10.018","url":null,"abstract":"<div><div>Distributed manufacturing is a new trend to accommodate the economic globalization, which means multiple geographically-distributed factories can collaborate to meet urgent delivery requirements. However, such factories may vary due to layout adjustments and equipment aging, thus the production efficiency greatly depends on the allocation of orders. This scenario is frequently found in energy-intensive process industries, e.g., chemical and pharmaceutical and industries, where the lack of buffers usually results in extra non-blocking constraints and makes the production scheduling even harder. Therefore, this paper investigates a distributed heterogeneous hybrid blocking flow-shop scheduling problem (DHHBFSP) for minimizing the makespan and total energy consumption simultaneously, and proposes an improved non-dominated sorting genetic algorithm II (INSGA-II) to address the problem. First, two heuristic algorithms, i.e., bi-objective considered heuristic (BCH) and similarity heuristic (SH), are developed for the population initialization. Then, to speed-up the local search, a comparison method for non-dominated solutions is proposed to reserve more solutions that are likely to be further improved. Afterwards, a probabilistic model is developed to eliminate unnecessary operations during local search processes. Finally, the proposed INSGA-II is tested on benchmark instances and a real-world case for the validation. Numerical experiments suggest that the SH can generates high-quality solutions within a very short period of time, and the BCH has significantly improved average IGD and HV values for the initial population. Besides, the probabilistic model saves considerable computational time for the local search without compromising the solution quality. With the help of these strategies, the proposed INSGA-II improves average IGD and HV values by 68 % and 57 % for the basic NSGA-II respectively, and obtains better Pareto fronts compared to existing multi-objective algorithms on the majority of test instances. Moreover, the industrial case study shows that the proposed INSGA-II is capable of providing solid scheduling plans for a pharmaceutical enterprise with large-scale orders.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 990-1008"},"PeriodicalIF":12.2,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1016/j.jmsy.2024.10.026
Chao Zhang , Max Juraschek , Christoph Herrmann
Dynamic scheduling plays a pivotal role in smart manufacturing by enabling real-time adjustments to production schedules, thereby enhancing system resilience and promoting sustainability. By efficiently responding to disruptions, dynamic scheduling maintains productivity and stability, while also reducing resource consumption and environmental impact through optimized operations and the potential integration of renewable energy. Deep Reinforcement Learning (DRL), a cutting-edge artificial intelligence technique, shows promise in tackling the complexities of production scheduling, particularly in solving NP-hard combinatorial optimization problems. Despite its potential, a comprehensive study of DRL's impact on dynamic scheduling, especially regarding system resilience and sustainability, has been lacking. This paper addresses this gap by presenting a systematic review of DRL-based dynamic scheduling focusing on resilience and sustainability. Through an analysis of two decades of literature, key application scenarios of DRL in dynamic scheduling are examined, and specific indicators are defined to assess the resilience and sustainability of these systems. The findings demonstrate DRL's effectiveness across various production domains, surpassing traditional rule-based and metaheuristic algorithms, particularly in enhancing resilience. However, a significant gap remains in addressing sustainability aspects such as energy flexibility, resource utilization, and human-centric social impacts. This paper also explores current technical challenges, including multi-objective and multi-agent optimization, and proposes future research directions to better integrate resilience and sustainability in DRL-based dynamic scheduling, with an emphasis on real-world application.
{"title":"Deep reinforcement learning-based dynamic scheduling for resilient and sustainable manufacturing: A systematic review","authors":"Chao Zhang , Max Juraschek , Christoph Herrmann","doi":"10.1016/j.jmsy.2024.10.026","DOIUrl":"10.1016/j.jmsy.2024.10.026","url":null,"abstract":"<div><div>Dynamic scheduling plays a pivotal role in smart manufacturing by enabling real-time adjustments to production schedules, thereby enhancing system resilience and promoting sustainability. By efficiently responding to disruptions, dynamic scheduling maintains productivity and stability, while also reducing resource consumption and environmental impact through optimized operations and the potential integration of renewable energy. Deep Reinforcement Learning (DRL), a cutting-edge artificial intelligence technique, shows promise in tackling the complexities of production scheduling, particularly in solving NP-hard combinatorial optimization problems. Despite its potential, a comprehensive study of DRL's impact on dynamic scheduling, especially regarding system resilience and sustainability, has been lacking. This paper addresses this gap by presenting a systematic review of DRL-based dynamic scheduling focusing on resilience and sustainability. Through an analysis of two decades of literature, key application scenarios of DRL in dynamic scheduling are examined, and specific indicators are defined to assess the resilience and sustainability of these systems. The findings demonstrate DRL's effectiveness across various production domains, surpassing traditional rule-based and metaheuristic algorithms, particularly in enhancing resilience. However, a significant gap remains in addressing sustainability aspects such as energy flexibility, resource utilization, and human-centric social impacts. This paper also explores current technical challenges, including multi-objective and multi-agent optimization, and proposes future research directions to better integrate resilience and sustainability in DRL-based dynamic scheduling, with an emphasis on real-world application.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 962-989"},"PeriodicalIF":12.2,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1016/j.jmsy.2024.11.004
Ming Wang , Jie Zhang , Peng Zhang , Wenbin Xiang , Mengyu Jin , Hongsen Li
In the process industries, where orders arrive at irregular intervals, inappropriate maintenance frequency often leads to unplanned shutdowns of high-speed parallel machines, resulting in unnecessary material consumption and a significant decline in the performance of the dynamic parallel machines scheduling. To address this issue, this paper proposes a generative deep reinforcement learning method that investigates the dynamic parallel machines scheduling problems with adaptive maintenance activities. Specifically, an enhanced Double DQN algorithm is proposed to schedule the dynamically arriving orders and maintenance activities, aiming to maximize average reliability while minimize the production costs. Additionally, a global exploration strategy is incorporated to enhance the scheduling and maintenance agent's global exploration capability, particularly in complex solution spaces with conflicting objectives. Furthermore, recognizing the difficulty of accurately capturing crucial scheduling and maintenance attributes within a predefined state space in a time-varying production environment, a guided Actor-Critic algorithm is introduced to autonomously generate the state space. Moreover, to tackle the unstable learning process caused by sparse rewards, a self-imitation learning is employed to guide the state space generation agent toward achieving rapid learning and convergence. Finally, simulation experiments validate that the proposed method not only autonomously enables state space generation but also exhibits superior performance for the investigated problem.
{"title":"Generative deep reinforcement learning method for dynamic parallel machines scheduling with adaptive maintenance activities","authors":"Ming Wang , Jie Zhang , Peng Zhang , Wenbin Xiang , Mengyu Jin , Hongsen Li","doi":"10.1016/j.jmsy.2024.11.004","DOIUrl":"10.1016/j.jmsy.2024.11.004","url":null,"abstract":"<div><div>In the process industries, where orders arrive at irregular intervals, inappropriate maintenance frequency often leads to unplanned shutdowns of high-speed parallel machines, resulting in unnecessary material consumption and a significant decline in the performance of the dynamic parallel machines scheduling. To address this issue, this paper proposes a generative deep reinforcement learning method that investigates the dynamic parallel machines scheduling problems with adaptive maintenance activities. Specifically, an enhanced Double DQN algorithm is proposed to schedule the dynamically arriving orders and maintenance activities, aiming to maximize average reliability while minimize the production costs. Additionally, a global exploration strategy is incorporated to enhance the scheduling and maintenance agent's global exploration capability, particularly in complex solution spaces with conflicting objectives. Furthermore, recognizing the difficulty of accurately capturing crucial scheduling and maintenance attributes within a predefined state space in a time-varying production environment, a guided Actor-Critic algorithm is introduced to autonomously generate the state space. Moreover, to tackle the unstable learning process caused by sparse rewards, a self-imitation learning is employed to guide the state space generation agent toward achieving rapid learning and convergence. Finally, simulation experiments validate that the proposed method not only autonomously enables state space generation but also exhibits superior performance for the investigated problem.</div></div>","PeriodicalId":16227,"journal":{"name":"Journal of Manufacturing Systems","volume":"77 ","pages":"Pages 946-961"},"PeriodicalIF":12.2,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号