Ibrahim Ahmed , Piero Baraldi , Enrico Zio , Horst Lewitschnig
{"title":"A data-driven modelling framework for predicting the quality of semiconductor devices to support burn-in decisions","authors":"Ibrahim Ahmed , Piero Baraldi , Enrico Zio , Horst Lewitschnig","doi":"10.1016/j.cie.2025.111115","DOIUrl":"10.1016/j.cie.2025.111115","url":null,"abstract":"<div><div>Burn-in testing of semiconductor devices is performed to ensure product quality by identifying and removing early-life failures. Given the cost and time required by burn-in testing, this work proposes a framework to predict the quality of a production batch of semiconductor devices before burn-in. Unlike traditional methods for quality prediction that rely solely on statistical data, this framework incorporates production data to improve prediction accuracy. The framework combines statistical methods for feature extraction (Piecewise Aggregate Approximation and Principal Component Analysis) and quality estimation (Clopper-Pearson Estimator) with a modified Probabilistic Support Vector Regression (PSVR) to predict early-life failures. The PSVR hyperparameters are set by a Bayesian Optimization (BO) technique. The framework is validated on a synthetic case study designed to emulate the BI process of semiconductor devices and, then, applied to real data collected during semiconductor production. Results from a synthetic case study and real-world semiconductor production data demonstrate the accuracy of the proposed method in predicting the quality of production batches. The quality predictions can, then, be used to inform efficient burn-in test planning in terms of the number of devices to undergo burn-in and the type of burn-in tests to perform.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111115"},"PeriodicalIF":6.7,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829998","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":"Solving many-objective reentrant hybrid flowshop scheduling problem considering uncertainty factors in thin-film transistor liquid crystal display","authors":"YongWei Wu , XiuFang Lin , GuangYu Zhu","doi":"10.1016/j.cie.2025.111117","DOIUrl":"10.1016/j.cie.2025.111117","url":null,"abstract":"<div><div>The thin-film transistor liquid crystal display (TFT-LCD) front-end array manufacturing process exhibits reentrant characteristics, with uncertainties in the transportation of glass substrates during shop scheduling, further impacting carbon emissions. This study develops a reentrant hybrid flow shop scheduling model considering carbon emissions under uncertain transportation time, where the uncertain transportation time is specifically defined by a triangular fuzzy number (TFN), and a crossing reentrant job handling mechanism is proposed. According to the characteristics of the problem, the shop scheduling process is optimized. In scheduling optimization, the Pythagorean fuzzy set (PFS) is used to solve the problem of uncertain transportation time, and the MYCIN uncertainty factor method, originating from the MYCIN expert system, is employed to evaluate the scheduling scheme and assist metaheuristic algorithm decision-making. A many-objective decision-making method based on PFS and MYCIN uncertainty factors theory is proposed. The golden section factor and the Levy flight are introduced into optimal foraging algorithm (OFA). An improved OFA based on the PFS and MYCIN uncertainty factors (PMYCIN-OFA) is then designed. Finally, three types of experiments are conducted: test cases testing, factory application case testing, and industrial software Flexsim simulations. The results demonstrate that the PMYCIN-OFA surpasses the performance of five classical multi-objective intelligent optimization algorithms and can provide practical solutions in the actual TFT-LCD front-end array manufacturing workshop.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111117"},"PeriodicalIF":6.7,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830110","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}
Chongfeng Li , Xing Pan , Linchao Yang , Jun Wang , Haobing Ma
{"title":"Human control mode enables accurate real-time risk warning in human–machine systems","authors":"Chongfeng Li , Xing Pan , Linchao Yang , Jun Wang , Haobing Ma","doi":"10.1016/j.cie.2025.111110","DOIUrl":"10.1016/j.cie.2025.111110","url":null,"abstract":"<div><div>Data-driven risk analysis serves as an essential approach to risk mitigation in human–machine systems. Presently, risk management rooted in data often depends on labels extracted from risk outcomes, accentuating a causative risk management paradigm. However, these labels frequently fall short in capturing the dynamic evolution of risks in real-time, especially accounting for the impact of human intervention on risk dissemination. In striving for greater precision in real-time risk prediction within human–machine systems, human control is identified as a pivotal factor in shaping risk progression. A precise warning model is devised based on human control patterns, discerned through clustering control data focusing on “timeliness,” “stability,” and “coordination.” This methodology facilitates the development of machine learning-driven warning models. The viability of the proposed approach is substantiated through a case study involving aircraft landing mishaps. This research furnishes a conceptual framework and procedural guidelines to propel risk analysis within human–machine systems, with an emphasis on human-centric risk warnings across diverse industrial contexts.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111110"},"PeriodicalIF":6.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826295","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}
Andres Padillo , Jesús Racero , Jose Carlos Molina , Ignacio Eguía , Javier Padillo
{"title":"Methodological design of a digital twin architecture in advanced surgery applied to the treatment of enteroatmospheric fistula","authors":"Andres Padillo , Jesús Racero , Jose Carlos Molina , Ignacio Eguía , Javier Padillo","doi":"10.1016/j.cie.2025.111105","DOIUrl":"10.1016/j.cie.2025.111105","url":null,"abstract":"<div><div>This research describes the design of an integrated model system to address the monitoring, treatment, and evolution of a pathology throughout its life cycle (LCP, Life Cycle Pathology) based on the Digital Twin (DT) concept, showing the capabilities of the system and the possibilities that it offers in the treatment of the pathology in an integrated way. The concept of DT in the field of medicine is a relatively recent concept. Its application is mainly focused on very reduced areas, such as prosthesis development and simulation of the cardiovascular system mainly. The DT con-cept allows the integration of simulation tools, diagnosis, & treatment, and follow up of pathologies, adapting all of them to the disease and patient. Therefore, so its inclusion in the medical field permits a personalization and creates a source of knowledge in the treatment of diseases. This research, as an application, will address the management of enteroatmospheric fistula (EAF), an uncommon pathology framed within advanced abdominal wall surgery, with a mortality rate close to 40%. To achieve this purpose, the direct and/or indirect variables associated with each patient must be considered in order to control, simulate, and evaluate the pathology Through the combination and collection of the physical information provided by the patient combined with the virtual information offered by the technology (DT); with the aim of being able to anticipate the real changes suffered throughout the LCP; predicting its behaviors and facilitates the surgeons decision-making on the treatment and management of the fistula.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111105"},"PeriodicalIF":6.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143824363","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}
Jichao Zhuang , Xiaotong Ding , Zilin Zhang , Xiaoli Zhao , Weigang Li , Ke Feng
{"title":"Remaining useful life prediction of equipment using a multiobjective optimization reinforced prognostic approach","authors":"Jichao Zhuang , Xiaotong Ding , Zilin Zhang , Xiaoli Zhao , Weigang Li , Ke Feng","doi":"10.1016/j.cie.2025.111116","DOIUrl":"10.1016/j.cie.2025.111116","url":null,"abstract":"<div><div>Data-driven methods have rapidly advanced equipment degradation monitoring and prognosis. However, traditional deep models rely on weak prior degradation knowledge and may not effectively incorporate degradation damage information. To address this limitation, a Deep Multiobjective Optimization Reinforced Prognostic (MORP) framework is proposed in this paper for equipment health prognosis. Specifically, a priori degradation knowledge and multi-source deep features are combined at both the feature and health indicator (HI) levels. They are then quantified into an unsupervised multi-objective optimization decision. Preceding this step, a multi-degradation criterion and HI generalizability are formulated as a multi-objective function, with the aim of enhancing the generalizability, monotonicity, tendency, and robustness of HIs. Comprehensive Health Indicators (CHIs) are then constructed while retaining the advantages of the Pareto frontier, using a reinforcement learning-guided swarm intelligence optimization method. To address anomalies within CHIs, a HI burr correction method featuring an interpolation-extrapolation term is introduced. Additionally, the prediction of remaining useful life is accomplished through a supervised prognostic scheme. Finally, the proposed methodology is applied to equipment datasets to validate its performance.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111116"},"PeriodicalIF":6.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829999","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":"Deep-Q-network-enhanced aquila-equilibrium hyper-heuristic algorithm for preventive maintenance integrated disassembly line balancing involving worker redeployment","authors":"Yufan Huang, Binghai Zhou","doi":"10.1016/j.cie.2025.111113","DOIUrl":"10.1016/j.cie.2025.111113","url":null,"abstract":"<div><div>The increasing production and replacement rates of modern commodities demand efficient recovery of end-of-life (EOL) products. This study promotes green and sustainable remanufacturing by investigating semi-automated disassembly lines. Preventive maintenance (PM), rarely studied in disassembly lines, is integrated with the line balancing problem and worker redeployment scheduling to construct a stable and reliable disassembly process. Additionally, this study considers the diversity of disassembly robots in PM scheduling, including their operating speed, energy consumption, and maintenance requirements, to enhance line efficiency and reduce carbon emissions. A mixed-integer programming model is proposed for the Preventive Maintenance-integrated Semi-Automated Disassembly Line Balancing Problem (PM-SADLBP), and is verified by an exact Epsilon-Constraint method. To solve this NP-hard problem, a Deep-Q-Network-enhanced Aquila-Equilibrium Hyper-Heuristic algorithm (DN-AEHH) is developed. A Hybrid Adaptive-length Triple-layer Real Encoding Approach and Self-repairing Decoding Mechanism are tailored to create an effective mapping between continuous solution space and discrete balancing and scheduling plans. Numerical experiments demonstrate that DN-AEHH outperforms five state-of-the-art algorithms across multiple problem scales, with a dominant rate of 83.01%. Additionally, managerial application shows 7.72% improvement in energy efficiency and 36.04% reduction in weighted cycle time with DN-AEHH to optimize PM. These findings provide practical guidance for line establishment and maintenance, supporting decision-making for managers with diverse preferences and operational contexts.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111113"},"PeriodicalIF":6.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826297","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":"Robust maximum expert consensus model with uncertain cooperative behavior in group decision making","authors":"Bowen Zhang , Yanran Zhu , Min Zhan","doi":"10.1016/j.cie.2025.111098","DOIUrl":"10.1016/j.cie.2025.111098","url":null,"abstract":"<div><div>In group decision making (GDM), the formation of the collective opinion is a cost-consuming discussion and negotiation process due to the nature of inherent opinion divergence. Moreover, the behavior and preference uncertainty of the experts further increases the difficulty of reaching consensus among all the experts. With consideration of the uncertain cooperative behavior in the consensus reaching process (CRP), this study presents the robust maximum expert consensus models to improve the consensus efficiency with a limited cost budget. Firstly, we propose a conflict measurement method based on the opinion divergence and asymmetric trust degree to quantify the cooperative willingness of the experts in the CRP. Then, we characterize the uncertain cooperative behavior of the experts with three classical uncertainty sets, and develop a novel robust maximum expert consensus model with uncertain cooperative behavior to generate the optimal modification suggestions. Finally, the application of the proposed models is illustrated with an example of agricultural insurance premium subsidies, and a detailed sensitive analysis is conducted to verify the effectiveness of the proposed models.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111098"},"PeriodicalIF":6.7,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143826296","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":"Deciphering the pulse of the city: An exploration of the natural features of metro passenger flow using XAI","authors":"Tianli Tang , Jian Zhang , Siyuan Chen , Pengli Mo , Mingyang Pei , Tie-Qiao Tang","doi":"10.1016/j.cie.2025.111097","DOIUrl":"10.1016/j.cie.2025.111097","url":null,"abstract":"<div><div>Urban metro systems are integral to modern public transport, making it essential to understand the factors influencing passenger flow for effective system planning and operations. Current evaluation methods for feature importance often lack precision, creating challenges in accurately profiling influential factors. Recent advancements in explainable artificial intelligence (XAI) present opportunities to enhance feature interpretability and refine natural feature profiling frameworks for metro passenger flow. This study discusses three XAI methods, i.e., LOFO, Fast-LOFO, and SHAP, in systematically evaluating feature importance in metro systems. Utilising the metro smartcard records from Suzhou, we construct a hierarchical tagging system for natural features. Each XAI method is applied to assess feature importance across key factors like time of travel, weekday status, and points of interest, allowing for a comparative analysis of their effects on passenger flow. Our findings show that while dominant features, such as travel hour and weekday status, consistently rank as the most influential across methods, variations arise in the treatment of secondary features. Tree-based models provided stable, high-level rankings, whereas SHAP offered deeper, localised insights, highlighting how specific features influence individual predictions. These differences underscore the need for a multi-method approach to achieve a complete and context-sensitive feature profile.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111097"},"PeriodicalIF":6.7,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143814812","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}
Na Fan , Jia Liu , Liping Ye , Zhoujin Pan , Yifan Dai , Wenjun Fan
{"title":"Dempster–Shafer evidence theory based IFA detection approach towards mixed attacks in VNDN","authors":"Na Fan , Jia Liu , Liping Ye , Zhoujin Pan , Yifan Dai , Wenjun Fan","doi":"10.1016/j.cie.2025.111084","DOIUrl":"10.1016/j.cie.2025.111084","url":null,"abstract":"<div><div>Vehicular Named Data Networking (VNDN) enables communication based on content names rather than vehicle addresses. This approach effectively mitigates the limitations of traditional vehicular networks that rely on TCP/IP-based communication. However, due to various network attacks, VNDN faces significant cybersecurity risks, which severely impact network performance and efficiency. To address these issues, this paper proposes a mixed attacks detection method based on the Dempster–Shafer evidence theory, integrating the Particle Swarm Optimization algorithm (DS-PSO). The method first extracts three key feature indicators: the information entropy offset of the Interest packet names, the cache offset in the content store, and the difference between the number of Interest packets sent and Data packets received by routing nodes per unit time. These indicators are normalized and used as evidence in DS evidence theory. The basic probability assignment of this evidence is then transformed into a parameter selection problem, and PSO is employed to optimize this selection by finding the optimal solution. Building on this, the DS evidence theory is used to fuse the obtained evidence, and the overall network security state is determined based on the fusion results, identifying and detecting existing network attacks. Our experimental results demonstrate that, compared to other methods, the proposed detection method effectively improves detection accuracy and reduces error rate not only in the various single-attack scenarios but also in the mixed-attack scenario.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111084"},"PeriodicalIF":6.7,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143814919","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":"Scheduling optimisation in a multi-deep tier-to-tier four-way shuttle storage and retrieval system","authors":"Chenhao Ren , Qing Yan , Zhi Liu","doi":"10.1016/j.cie.2025.111095","DOIUrl":"10.1016/j.cie.2025.111095","url":null,"abstract":"<div><div>The multi-deep tier-to-tier four-way shuttle storage and retrieval system is a new automated warehouse in which shuttles can reach any position to store and retrieve loads with the assistance of lifts. As a multi-logistics equipment cooperative operation system, request sequencing, logistics equipment selection, and path planning are critical aspects of daily operation and have a significant effect on operation efficiency. Therefore, this paper studies the integrated scheduling optimisation of the three issues. A logistics equipment control policy is proposed to select the shuttle and lift with the earliest handover time for each request. Additionally, the conflict-free working process of logistics equipment is modelled to calculate the operation time for executing all requests. A scheduling optimisation algorithm is designed to optimise the integrated scheduling problem. The analysis of experiments at different scales demonstrates that the proposed algorithm can achieve a balance between exploration and utilisation, and the integrated scheduling method is superior to its competitors. Comparisons between the proposed method and other common control policies show that the operation efficiency is improved by more than 20%. The proposed method can provide valuable decision support for warehouse managers to optimise system operation and improve overall efficiency, even when there are more shuttles.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111095"},"PeriodicalIF":6.7,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143814754","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}