Computers & Industrial Engineering最新文献

{"title":"Multi-level task network scheduling and electricity supply collaborative optimization under time-of-use electricity pricing","authors":"Guodong Yu ,&nbsp;Bo Cheng ,&nbsp;Taiyu Xu ,&nbsp;Junliang Pan ,&nbsp;Yunlong Chen","doi":"10.1016/j.cie.2025.110952","DOIUrl":"10.1016/j.cie.2025.110952","url":null,"abstract":"<div><div>This paper examines intricate Multi-level Task Network Scheduling and Electricity Supply Collaborative Optimization (MTNS &amp; ESCO) in the context of time-of-use electricity pricing. It investigates three distinct models aimed at minimizing completion time and energy costs, accommodating multi-level task networks, inter-level constraints, and task precedence. Model I addresses collaborative planning for production task scheduling and electricity supply under time-of-use pricing. Model II integrates Distributed Energy Resources (DERs) and Energy Storage Systems (ESS) to mitigate conflicts between normal production and high electricity costs during peak periods, building upon Model I. Model III extends this by incorporating feedback to the main grid, maximizing DERs’ power generation potential while reducing costs. To tackle these models, the paper proposes a hybrid algorithm merging Particle Swarm Optimization (PSO) with Tabu Search. This algorithm is customized for the problem’s complexities, employing tailored strategies for encoding, decoding, workstation selection, particle updating, and Tabu Search. The study offers theoretical insights beneficial for equipment manufacturing enterprises seeking to implement distributed energy systems and optimize production and energy management under time-of-use electricity pricing policies. Numerical experiments based on real cases show the performance of our method on reducing the energy consumptions and manufacturing cost.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 110952"},"PeriodicalIF":6.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463450","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":"An integrated model for coordinating adaptive platoons and parking decision-making based on deep reinforcement learning","authors":"Jia Li ,&nbsp;Zijian Guo ,&nbsp;Ying Jiang ,&nbsp;Wenyuan Wang ,&nbsp;Xin Li","doi":"10.1016/j.cie.2025.110962","DOIUrl":"10.1016/j.cie.2025.110962","url":null,"abstract":"<div><div>Improving transportation efficiency is a key challenge in operating automated container terminals (ACTs), particularly in managing yard intersections and optimizing parking resources. However, existing studies often treat these two aspects independently, failing to consider their combined impact on vehicle operation efficiency. To this end, this study proposes a hierarchical control framework, named CAP-PDM, to integrate intersection platoon strategy and parking resource management for Intelligent Autonomous Vehicles (IAVs). The CAP-PDM comprises two layers: (1) the adaptive platoon layer leverages real-time traffic data to determine optimal platoon sizes at intersections, addressing localized congestion and reducing delays; (2) the parking strategy optimization layer achieves dynamic IAV scheduling and task allocation within the horizontal transportation network by considering multiple objectives (i.e., the current efficiency of IAVs and task completion). The Dual Deep Deterministic Policy Gradient (DDPG) algorithm is employed to determine platoon sizes and manage real-time IAV assignments to parking areas. Simulation results demonstrate that compared with other control methods, CAP-PDM demonstrates superior adaptability to varying traffic conditions, minimizes delays, and significantly enhances the operational efficiency of IAVs in ACTs. This study highlights the importance of integrating traffic control with resource optimization to improve the efficiency of automated port operations. The findings provide port managers with innovative insights for optimizing horizontal transportation systems.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 110962"},"PeriodicalIF":6.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463363","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 deep learning method for assessment of ecological potential in traffic environments","authors":"Lixin Yan,&nbsp;Yating Gao,&nbsp;Junhua Guo,&nbsp;Guangyang Deng","doi":"10.1016/j.cie.2025.110958","DOIUrl":"10.1016/j.cie.2025.110958","url":null,"abstract":"<div><div>To further enhance the energy efficiency of the road traffic system, this study comprehensively considered various factors such as road conditions, traffic situations, and weather environments, extracting a total of 34 feature variables affecting the ecological nature of traffic scenarios. A feature selection method combining Random Forest, Permutation Importance, and Sequential Backward Selection algorithms was used to determine the optimal set of features, which includes 12 variables. Subsequently, a traffic scenario ecological characteristic assessment model based on the Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) algorithm was constructed to improve the overall performance of the road transport system. By testing and comparing eight deep learning algorithms, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and CNN-LSTM, the effectiveness of the constructed model was verified. The results indicate that the CNN-LSTM algorithm performs best in the ecological assessment of traffic scenarios, capable of accurately classifying all features, with Accuracy, Precision, Recall, F1-score, Micro AUC score, and Macro AUC score reaching 0.83, 0.826, 0.83, 0.825, 0.945, and 0.904, respectively. Additionally, this study employed the SHapley Additive exPlanations (SHAP) method for interpretability analysis of the model and used violin plots to demonstrate the distribution of various features across different scenario categories. The results show that the type of functional zoning to which the road geographical location belongs, visibility, and various traffic condition features have significant correlations with the ecological category of road traffic scenarios. Therefore, appropriate traffic energy-saving and emission reduction control strategies can be adopted for different functional zones, weather conditions, and traffic situations to promote the road traffic sector towards a zero-carbon goal.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"202 ","pages":"Article 110958"},"PeriodicalIF":6.7,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143445944","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":"Adaptive manufacturing control with Deep Reinforcement Learning for dynamic WIP management in industry 4.0","authors":"Silvestro Vespoli,&nbsp;Giulio Mattera,&nbsp;Maria Grazia Marchesano,&nbsp;Luigi Nele,&nbsp;Guido Guizzi","doi":"10.1016/j.cie.2025.110966","DOIUrl":"10.1016/j.cie.2025.110966","url":null,"abstract":"<div><div>In the context of Industry 4.0, manufacturing systems face increased complexity and uncertainty due to elevated product customisation and demand variability. This paper presents a novel framework for adaptive Work-In-Progress (WIP) control in semi-heterarchical architectures, addressing the limitations of traditional analytical methods that rely on exponential processing time distributions. Integrating Deep Reinforcement Learning (DRL) with Discrete Event Simulation (DES) enables model-free control of flow-shop production systems under non-exponential, stochastic processing times. A Deep Q-Network (DQN) agent dynamically manages WIP levels in a CONstant Work In Progress (CONWIP) environment, learning optimal control policies directly from system interactions. The framework’s effectiveness is demonstrated through extensive experiments with varying machine numbers, processing times, and system variability. The results show robust performance in tracking the target throughput and adapting the processing time variability, achieving Mean Absolute Percentual Errors (MAPE) in the throughput – calculated as the percentage difference between the actual and the target throughput – ranging from 0.3% to 2.3% with standard deviations of 5. 5% to 8. 4%. Key contributions include the development of a data-driven WIP control approach to overcome analytical methods’ limitations in stochastic environments, validating DQN agent adaptability across varying production scenarios, and demonstrating framework scalability in realistic manufacturing settings. This research bridges the gap between conventional WIP control methods and Industry 4.0 requirements, offering manufacturers an adaptive solution for enhanced production efficiency.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"202 ","pages":"Article 110966"},"PeriodicalIF":6.7,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427946","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}

{"title":"Dynamic reliability evaluation of multi-performance sharing and multi-state systems with interdependence","authors":"Heping Jia ,&nbsp;He Lu ,&nbsp;Rui Peng ,&nbsp;Kaiye Gao","doi":"10.1016/j.cie.2025.110965","DOIUrl":"10.1016/j.cie.2025.110965","url":null,"abstract":"<div><div>Numerous engineering systems are designed to be performance sharing systems with multiple interdependent performances. Motivated by practical engineering systems, in this study, a multi-performance sharing and multi-state system (MPSMS) with performance interdependence was modeled. The model includes a feasible operating region (FOR) considering the interdependent operation constraints of the components. Moreover, a multi-performance sharing mechanism including performance sharing limits and performance conversion efficiency was developed. Furthermore, an approach combining Markov process model and extended <em>Lz</em>-transform technique was adopted to develop unified representations of the dynamic reliability models of the considered MPSMSs. Dynamic reliability indices including the time-varying reliability and the expected instantaneous performance deficiency (EIPD) were evaluated through four case studies to validate the developed model and approach.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"202 ","pages":"Article 110965"},"PeriodicalIF":6.7,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427945","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":"AS-IS representation and strategic framework for the design and implementation of a disassembly system","authors":"Thibault Hervouet,&nbsp;Sotirios Panagou,&nbsp;Fabio Sgarbossa","doi":"10.1016/j.cie.2025.110975","DOIUrl":"10.1016/j.cie.2025.110975","url":null,"abstract":"<div><div>Disassembly is a critical process in circular manufacturing models for end-of-life (EOL) products, enabling the recovery of components for reuse or repurposing, and reducing the reliance on raw material extraction. However, disassembly systems (DS) face significant barriers and uncertainties. Key challenges include the uncertainty of volume of returned EOL products, the variability of product variants due to mass customization, and the uncertain condition of these products. These factors complicate decision-making in DS design and implementation, impacting resource allocation and sustainability efforts. Moreover, the lack of reliable industrial case studies adds up to these challenges and highlights a gap in the literature. Apart from the low number of available resources and solutions, there is a fundamental need for a deeper understanding of the systematic barriers and strategic challenges facing DS. This work addresses these issues by providing both practitioners and researchers with a methodology for the AS-IS representation of disassembly system design and implementation (DSDI). Additionally, it offers a strategic level framework for DSDI, tested through a case study of a Norwegian electronics company.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"202 ","pages":"Article 110975"},"PeriodicalIF":6.7,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427948","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}

{"title":"Semiconductor probe card proactive maintenance using graph self-supervised learning and an empirical study","authors":"Tran Hong Van Nguyen ,&nbsp;Chen-Fu Chien","doi":"10.1016/j.cie.2025.110955","DOIUrl":"10.1016/j.cie.2025.110955","url":null,"abstract":"<div><div>Semiconductor probe cards for wafer testing are increasingly challenging owing to the high density of bonding pads on the surface of integrated circuits (IC), the growing complexity of IC device features, and the extensive customization required for various IC products. Early fault detection and resolution are crucial for proactive maintenance to maintain the optimal operational performance and overall equipment effectiveness of wafer probing test equipment. Furthermore, the increasing number of possible corrective solutions for probe cards and the lack of concatenated labels for model training, along with the heterogeneity of domain knowledge for similar problems, has made it increasingly difficult for the engineers to find effective solutions for abnormal symptoms. Most of the existing studies focus on fault diagnosis, failure detection and classification, and advanced equipment control. As part of a continuous effort to fill the gaps, this study aims to develop a UNISON framework for graph self-supervised learning that integrates knowledge graph (KG), graph convolutional neural networks (GCN), and self-supervised learning to predict the conditions and effectively recommend the optimal list of corrective actions for early detection and resolution of the detected abnormal symptoms. To validate the proposed approach, an empirical study was conducted in a leading semiconductor testing company in Taiwan. The results have shown practical viability of the developed solution that can effectively assist the engineers in selecting the corrective actions for proactive maintenance to reduce machine downtime and enhance customer satisfaction.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 110955"},"PeriodicalIF":6.7,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143552266","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 real-time A* algorithm for trajectories generation and collision avoidance in uncertain environments for assembly applications","authors":"Ahmed Nhouchi ,&nbsp;Salma Ben Said ,&nbsp;Mohamed Amine Ben Abdallah ,&nbsp;Nizar Aifaoui","doi":"10.1016/j.cie.2025.110959","DOIUrl":"10.1016/j.cie.2025.110959","url":null,"abstract":"<div><div>In assembly processes, generating paths and avoiding collisions are crucial for efficiency and safety. This paper presents a novel approach that integrates the A* pathfinding (PF) algorithm into FreeCAD, an open-source Computer-Aided Design (CAD) platform. The main contribution of this work is enabling PF and collision detection directly within the CAD environment during the design phase, helping detect potential collisions early and improving the design process. The A* algorithm has been adapted to handle both static and dynamic obstacles inside FreeCAD. This integration allows for better planning of paths in complex assembly environments. The integration process, algorithm modifications and system functionality are described in detail. A case study simulating an assembly line demonstrates the algorithm’s effectiveness in generating collision-free trajectories while adapting to dynamic changes in the environment. This work paves the way for further advancements in AI-driven CAD systems for industrial applications, enabling more intelligent and adaptive assembly processes during the design phase.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"202 ","pages":"Article 110959"},"PeriodicalIF":6.7,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143445942","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":"Personalized product design and user review and experience analysis: A data-driven hybrid novel approach","authors":"Shulin Lan ,&nbsp;Yinfei Jiang ,&nbsp;Tao Guo ,&nbsp;Shaochun Li ,&nbsp;Chen Yang ,&nbsp;T.C. Edwin Cheng ,&nbsp;Kanchana Sethanan ,&nbsp;Ming-Lang Tseng","doi":"10.1016/j.cie.2025.110939","DOIUrl":"10.1016/j.cie.2025.110939","url":null,"abstract":"<div><div>This study contributes to mass customization by addressing the lack of effective methods for extracting and analyzing personalized demand indicators from user feedback. Prior studies often neglect the mapping relationship between user feedback and production characteristics, the practical integration of user experience data with product design constraints, limiting their ability to meet diverse consumer needs. To overcome these challenges, this study proposes a data-driven approach that combines k-means clustering, sentiment analysis, and deep learning to identify key comment factors impacting the user experience of customized products. This study offers substantial scientific value by proposing a systematic and scalable method for understanding consumer preferences in mass customization. It provides manufacturers with actionable insights for improving product competitiveness and customer satisfaction. The results demonstrate that product thinness and performance are the most critical factors for personalized information technology product design, significantly influencing user satisfaction. Regression analysis confirms that while these factors, along with price, heavily affect user ratings, battery life and heat dissipation are of secondary importance.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"202 ","pages":"Article 110939"},"PeriodicalIF":6.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395653","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 novel utilités additives—based social network group decision-making method considering preference consistency","authors":"Zhiwei Xu ,&nbsp;Peng Li ,&nbsp;Cuiping Wei ,&nbsp;Jian Liu","doi":"10.1016/j.cie.2025.110947","DOIUrl":"10.1016/j.cie.2025.110947","url":null,"abstract":"<div><div>Nowadays, social networks and mobile internet have become prominent features of daily life, leading to increasingly interconnected relationships among decision-makers (DMs). The social network group decision-making (SNGDM) method uses social network analysis technology to consider the impact of social trust relationships among DMs on decision results during the decision-making process. The Utilités Additives (UTA) method can infer the DMs’ preference structure based on the partial preference information. This method effectively resolves the consensus problem in SNGDM by utilizing the DMs’ preference structure. This paper proposes a novel SNGDM method based on the UTA method that considers the consistency of preference information provided by DMs in the form of pairwise comparisons. Firstly, since the trust relationship between DMs is asymmetric and DM’s opinions are usually different, a new preference conflict degree between DMs in SNGDM is defined. Then, to consider the opinion differences and social trust relationship between DMs in the clustering process, a clustering method based on the preference conflict degree is proposed. Furthermore, to obtain the maximal subsets of consistent pairwise comparisons for each DM, we designed a simulation algorithm involving an optimization model to examine the pairwise comparisons provided by the DMs and to obtain the maximal subsets of consistent pairwise comparisons. Moreover, since using only preference information in the form of pairwise comparisons in the consensus reaching process (CRP) leads to a limited space for changes in DMs’ opinions, a method for converting the opinions of DMs based on maximal subsets of consistent pairwise comparisons is proposed. This method transforms pairwise comparisons provided by DMs into fuzzy preference relations (FPRs). In addition, in the CRP, a method for adjusting the FPRs of DMs is proposed. Finally, a case study is conducted using real data on new energy vehicles from Autohome to illustrate the effectiveness of the proposed method.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"202 ","pages":"Article 110947"},"PeriodicalIF":6.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438158","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}