Computers & Industrial Engineering最新文献

{"title":"A game theory approach for optimizing job shop scheduling problems with transportation in common shared human–robot environments","authors":"Kader Sanogo ,&nbsp;Abdelkader Mekhalef Benhafssa ,&nbsp;M’hammed Sahnoun","doi":"10.1016/j.cie.2025.111366","DOIUrl":"10.1016/j.cie.2025.111366","url":null,"abstract":"<div><div>The Job Shop Scheduling Problem with Transportation (JSSPT) is a critical challenge in modern industrial systems, particularly in environments where human operators and Autonomous Intelligent Vehicles (AIVs) interact. Traditional scheduling approaches often fail to address the dynamic and unpredictable nature of these shared human–robot environments. In response, this paper introduces a game theory-based scheduling algorithm that optimizes transportation tasks in Industry 5.0 settings, where human–robot collaboration is essential. By modeling AIVs as rational agents within a potential game framework, we reformulate JSSPT as a Multi-robot task allocation problem (MRTA), applying iterative best-response strategies to reach a Nash equilibrium that minimizes the overall makespan. Our approach uniquely integrates human movements into the scheduling process, enabling real-time adaptation to fluctuating production environments. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art methods, namely the VNS and entropy-based approaches, particularly in settings where human unpredictability significantly impacts performance. On average, the game-theory-based algorithm reduces the makespan by 7 s compared to the entropy-based algorithm and by 17 s compared to the VNS algorithm. Despite the restrictive assumptions regarding human movement, this study underscores the significance of dynamic scheduling approaches in highly variable settings, contributing to more resilient and efficient production systems in line with Industry 5.0’s vision.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111366"},"PeriodicalIF":6.7,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653061","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}

{"title":"AI-based hybrid knowledge extraction method in complex engineering scenarios: A case study of drill-and-blast tunnelling excavation","authors":"Zinan Wang ,&nbsp;Baoguo Liu ,&nbsp;Xiaomeng Shi ,&nbsp;Zhiyun Deng ,&nbsp;Jinglai Sun","doi":"10.1016/j.cie.2025.111375","DOIUrl":"10.1016/j.cie.2025.111375","url":null,"abstract":"<div><div>The explosive rise of generative AI models is reshaping both the technological trajectory and developmental landscape of industrial intelligence. However, these large language models demonstrate significant limitations when processing specialized engineering knowledge due to intricate knowledge systems and domain expertise fragmented across various unstructured sources. An AI-based hybrid knowledge extraction method (AHKEM) is proposed to address these challenges in complex engineering scenarios. The method integrates AI techniques and large language models into a systematic framework: TF–IDF analysis is combined with word vector semantics for entity identification across extensive textual corpora, Bert-BiLSTM-CRF is employed for entity recognition, and a novel two-stage hierarchical clustering-GPT relationship mining method (HC-GPT RMM) is utilized for relationship extraction. The approach was demonstrated through a case study of drill-and-blast tunnelling excavation, a typical engineering scenario with complex data characteristics, using a corpus that comprised 13 specifications and standards, 4 professional books, and 343 academic papers, resulting in a knowledge graph containing 1,607 entities and 1,582 relationships that effectively supports various intelligent applications in construction practice. The advantages of AHKEM in handling complex domain knowledge are further validated through comparative experiments with joint extraction approaches. Both a practical framework for knowledge extraction in engineering domains is provided by this study and its application value is demonstrated through a specific construction scenario.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111375"},"PeriodicalIF":6.7,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144671080","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}

{"title":"A branch-and-cut algorithm for the integrated employee timetabling and hybrid job-shop scheduling problem with time lags and setup times","authors":"Mohamed Frihat ,&nbsp;Atidel B. Hadj-Alouane","doi":"10.1016/j.cie.2025.111351","DOIUrl":"10.1016/j.cie.2025.111351","url":null,"abstract":"<div><div>This paper addresses a real-world manufacturing scheduling problem that integrates employee timetabling with production scheduling. The employee timetabling problem considers skill requirements, employee availability, and legislative regulations. The production scheduling problem is modeled as a re-entrant hybrid job-shop, where jobs may revisit machines multiple times. The problem includes further complexities such as time lags, sequence-dependent setup times, and machine availability constraints. To address these challenges, a novel time period-based modeling approach is introduced. By discretizing the planning horizon into work periods, the proposed formulation ensures that each employee is assigned to a single machine per period, thereby reducing frequent transitions, improving workforce stability, and enhancing operational feasibility. Furthermore, we develop an enhanced decomposition and cut generation method, which goes beyond conventional single-cut strategies by applying multiple problem-specific cuts per iteration. These cuts are designed to exploit the hybrid structure and inherent symmetries of the problem, significantly refining the solution space and accelerating convergence. This approach is embedded within a newly developed Branch-and-Cut algorithm, leading to substantial gains in computational efficiency, especially for large-scale instances where classical MILP and CP methods underperform. Overall, the proposed formulation and algorithmic framework provide a scalable, efficient, and practically viable solution to complex integrated scheduling problems in hybrid job-shop environments.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111351"},"PeriodicalIF":6.5,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738348","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}

{"title":"Optimizing carbon emission allocation for liner shipping companies","authors":"Yidan Shangguan ,&nbsp;Xuecheng Tian ,&nbsp;Yong Jin ,&nbsp;Shuaian Wang","doi":"10.1016/j.cie.2025.111348","DOIUrl":"10.1016/j.cie.2025.111348","url":null,"abstract":"<div><div>Maritime shipping accounts for approximately 3% of all annual carbon dioxide (<span><math><msub><mrow><mtext>CO</mtext></mrow><mrow><mn>2</mn></mrow></msub></math></span>) emissions worldwide. To address this, the EU Emissions Trading System (ETS) mandates that shipping companies pay for every ton of <span><math><msub><mrow><mtext>CO</mtext></mrow><mrow><mn>2</mn></mrow></msub></math></span> they emit. In response to this regulation, liner shipping companies have passed the cost of carbon emissions onto their customers. These companies typically levy an emissions surcharge per twenty-foot equivalent unit (TEU) container and calculate the surcharge based on individual trades, which typically encompass multiple origin–destination (od) pairs within a region. However, this surcharge structure fails to account for variations in distance between od pairs within the same trade. To address this limitation, we propose a carbon emissions allocation policy using an optimization method to allocate emissions per TEU for each od pair. This method incorporates both the shortest sailing distance and the actual traveling distance of the od pair, combining these into a harmonic distance. The harmonic factor represents the chosen carbon emissions allocation policy. Considering that carbon emission allocation should be tailored to specific shipping routes, this study constructs an augmented shipping network of multiple routes. Based on this network, we develop two od-link-based models: one with transshipment and the other without transshipment. Both models aim to maximize the profits of liner shipping companies. The models are validated through experiments conducted using real-world and synthetic shipping networks. The results show that the model with transshipment yields higher profits than the model without. In the model without transshipment, the carbon emission allocation policy has little impact on the profits of shipping companies. However, in the model with transshipment, selecting an appropriate carbon emission allocation policy is critical.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111348"},"PeriodicalIF":6.7,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653057","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}

{"title":"A neural network adaptation on neutrosophic triplets for robotic assembly line optimization in smart manufacturing","authors":"Amirhossein Nafei ,&nbsp;Zhi Li ,&nbsp;S. Pourmohammad Azizi","doi":"10.1016/j.cie.2025.111398","DOIUrl":"10.1016/j.cie.2025.111398","url":null,"abstract":"<div><div>The decision-making process in smart manufacturing often involves complex, multi-criteria scenarios characterized by uncertainty and conflicting objectives. Traditional decision-making approaches face inherent limitations in managing indeterminacy, ensuring robustness, and addressing computational complexity, which compromise their reliability in dynamic manufacturing environments. This study introduces an innovative framework that integrates the VIKOR method, neural networks, and Neutrosophic Triplets (NTs) to address these challenges. The proposed approach is specifically designed to optimize robotic assembly line configurations by balancing key objectives such as cost, operational efficiency, and sustainability. VIKOR’s compromise solution methodology is leveraged to evaluate trade-offs between group utility and individual regret, while Neutrosophic Triplets enhance the management of indeterminate information. Neural networks provide scalability and adaptability, enabling dynamic ranking refinement and reducing computational overhead. Additionally, a ranking strategy based on occurrence pattern analysis ensures robust and reliable decision-making outcomes. Validated through a case study on robotic assembly line optimization in a smart manufacturing environment, the framework demonstrates its effectiveness in improving productivity, adaptability, and sustainability. These results position the smart VIKOR method as a powerful and scalable solution for addressing the complexities of modern manufacturing systems.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111398"},"PeriodicalIF":6.7,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144654251","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}

{"title":"Research on cooperative control model of power grid equipment manufacturing quality risk under blockchain","authors":"Yunfeng Chen ,&nbsp;Jicheng Liu ,&nbsp;Yanan Song ,&nbsp;Bingfan Duan ,&nbsp;Xian Meng","doi":"10.1016/j.cie.2025.111400","DOIUrl":"10.1016/j.cie.2025.111400","url":null,"abstract":"<div><div>Power grid equipment is a major infrastructure for constructing a new power system and promoting the rapid development of new quality productivity. The reliability of power grid equipment manufacturing quality is particularly important. In order to improve the quality risk management capability of power grid equipment, this study firstly identifies and evaluates the quality risk factors based on text mining technology, complex network theory and machine learning algorithm. Secondly, it constructs a blockchain-based cloud supervision manufacturing model for real-time quality risk control. It analyses the gaming behaviours and strategy choices of grid company, manufacturer and quality inspector in the blockchain environment for realizing the collaborative control. Thirdly, with the above three-party game strategy, a multi-objective quality risk control model is further presented under the blockchain. It considers the quality traceability, quality consistency, and customer satisfaction, for controlling the grid equipment manufacturing quality risk. Finally, the improved particle swarm algorithm (IPSO) is used to solve the case study. The results show that the blockchain technology can help to reduce the equipment manufacturing quality risk, and improve the equipment manufacturing quality performance. This study provides a theoretical basis and practical guidance for the management and control of quality risk in the grid equipment manufacturing.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111400"},"PeriodicalIF":6.7,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653062","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}

{"title":"A new component depolymerization method for selective assembly optimization of complex products with parallel structures","authors":"Sheng Liu,&nbsp;Haidong Yu,&nbsp;Zitong Yu","doi":"10.1016/j.cie.2025.111397","DOIUrl":"10.1016/j.cie.2025.111397","url":null,"abstract":"<div><div>The advancement of intelligent manufacturing technologies is driving production toward higher precision and efficiency, pushing traditional quality control methods to their limits. Selective assembly enables high-precision products to be assembled from low-precision components, which shows great potential for application in smart assembly lines powered by digital measurement and augmented reality technologies. However, existing selective assembly methods are only applicable to simple linear assemblies and fail to address complex products with numerous tolerance information and intricate assembly connections. Two immature approaches can be used to address the challenges, both of which have significant limitations. One overlooks intricate tolerance information, leading to large deviations, while the other indiscriminately groups all tolerance information, resulting in exponential group proliferation. In this paper, a new component depolymerization method for the selective assembly of complex products is proposed to address the challenges, which integrates the assembly connection separation model, the component precision aggregation model, and the optimization algorithm. The proposed assembly connection separation model comprehensively considers all tolerance information in serial and parallel connections without any omission. The established component precision aggregation model efficiently consolidates the tolerance information of each component, overcoming the problem of exponential growth in group numbers. The genetic algorithm is also developed to provide an excellent solution. Two typical cases with parallel structures are used to demonstrate the superior performance of the component depolymerization method for the selective assembly of complex products compared to traditional methods.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111397"},"PeriodicalIF":6.5,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738249","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}

{"title":"Navigating the sustainable supply chain realm: Revolutionizing from 3.0 to 5.0","authors":"Arij Lahmar ,&nbsp;Kamar Zekhnini ,&nbsp;Malek Masmoudi ,&nbsp;Areej Aftab Siddiqui","doi":"10.1016/j.cie.2025.111380","DOIUrl":"10.1016/j.cie.2025.111380","url":null,"abstract":"<div><div>The evolution of Supply Chain Management (SCM) has been shaped by successive industrial revolutions, each characterized by distinct operational objectives and technological advancements. This paper examines the transition of SCM from Industry 3.0 to Industry 5.0, with a particular focus on sustainable digital transformation. Throughout this progression, SCM has continuously adapted to shifting business and environmental imperatives, leveraging emerging technologies to enhance resilience and efficiency. Through a comprehensive literature review and bibliometric analysis, this study develops a structured framework that maps the evolution of SCM across these industrial phases. It explores the integration of sustainable practices and technological advancements, offering valuable insights for both academic researchers and industry professionals. Furthermore, this research highlights how Industry 5.0 fosters a socially sustainable approach to SCM by emphasizing human-centric strategies. By analyzing the interplay between technological innovation, sustainability objectives, and managerial paradigms, this study synthesizes diverse strategies for building more innovative, resilient, and sustainable supply chains in an increasingly complex global landscape.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111380"},"PeriodicalIF":6.7,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144665456","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}

{"title":"IRS-guided policy search in model based reinforcement learning for virtually coupled train sets control","authors":"Li Zhu ,&nbsp;Jia Miao ,&nbsp;Cheng Chen ,&nbsp;Baicheng Yan ,&nbsp;Taiyuan Gong ,&nbsp;F.Richard Yu ,&nbsp;Tao Tang","doi":"10.1016/j.cie.2025.111372","DOIUrl":"10.1016/j.cie.2025.111372","url":null,"abstract":"<div><div>Virtually Coupled Train Set (VCTS) is a railway operation concept that allows shorter train intervals. However, the complex dynamic model of train convoy in urban rail transit systems (URTS) makes it challenging to achieve efficient cooperative controller for VCTS. Existing methods for VCTS control assume accurate train dynamics models are available, which is difficult to achieve in real-world VCTS scenarios. In this paper, we present a framework that employs model-based reinforcement learning (MBRL) to control VCTS. In comparison with classical methods and model-free reinforcement learning (MFRL), MBRL can learn more efficiently with limited data, making it particularly useful in situations where interactions with the real environment are costly or dangerous, such as in VCTS. Guided Policy Search (GPS) is used in the MBRL framework to derive the VCTS control policy while ensuring stability, punctuality, and safe distance protection of trains, due to its remarkable ability to quickly learn from the environment. We construct a deep neural network (DNN) based train convoy model to approximate train convoy dynamics. An iterative random shooting (IRS) based optimization method is applied to generate a set of candidate policies, which are then used to train the GPS to obtain the target policy for VCTS. Our experiments show that the proposed IRS-guided policy search (IRS-GPS) in MBRL can provide effective VCTS cooperative control. Our proposed IRS-GPS in MBRL for VCTS cooperative control ensures that virtually coupled trains operate safely, stably, and on time at short intervals.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111372"},"PeriodicalIF":6.7,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144679642","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}

{"title":"Edge–cloud collaborative predictive auto-scaling for industrial IoT: A multi-objective optimization approach considering equipment health status","authors":"Chunmao Jiang ,&nbsp;Wei Wu ,&nbsp;Tengfei Fan ,&nbsp;Wendi Jiang","doi":"10.1016/j.cie.2025.111365","DOIUrl":"10.1016/j.cie.2025.111365","url":null,"abstract":"<div><div>This paper presents an innovative edge–cloud collaborative predictive auto-scaling framework for Industrial Internet of Things (IIoT) environments, specifically addressing resource management challenges in equipment health monitoring and predictive maintenance scenarios. Traditional autoscaling approaches often fail to consider the equipment’s health status and its impact on resource demands, leading to suboptimal resource allocation and potential equipment risks. We propose a three-tier framework that integrates equipment health monitoring, workload prediction, and multi-objective optimization. First, we develop a novel deep learning-based workload prediction model incorporating equipment degradation indicators to accurately forecast resource demands. Second, we formulate a multi-objective optimization problem that simultaneously considers resource utilization, energy consumption, and equipment health risk. Third, we design an adaptive edge–cloud collaboration mechanism that dynamically adjusts resource allocation based on immediate equipment health status and predicted maintenance requirements. Through extensive experiments using real-world data from multiple manufacturing facilities, our approach demonstrates significant improvements over the baseline methods: 25% reduction in energy consumption, 30% increase in resource utilization, and 20% decrease in equipment health risk (<span><math><mrow><mi>p</mi><mo>&lt;</mo><mn>0</mn><mo>.</mo><mn>05</mn></mrow></math></span>). Furthermore, the framework shows robust performance under various industrial scenarios, including sudden equipment degradation and maintenance events. These results validate the effectiveness of our approach in managing IIoT resources while maintaining equipment reliability.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"208 ","pages":"Article 111365"},"PeriodicalIF":6.7,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144631840","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}