Computers & Industrial Engineering最新文献

{"title":"Temporal transaction network anomaly detection for Industrial Internet of Things with federated graph neural networks","authors":"Qingyong Wang ,&nbsp;Beibei Han","doi":"10.1016/j.cie.2025.111122","DOIUrl":"10.1016/j.cie.2025.111122","url":null,"abstract":"<div><div>The Industrial Internet of Things (IIoT) has experienced significant advancements in recent years, resulting in a considerable increase in the volume of data generated by interconnected devices. This surge in data has created new opportunities to enhance the quality of service in machine learning applications within the IIoT through data sharing. Among these applications, anomaly detection in transaction networks utilizing graph neural networks (GNNs) has emerged as a prominent research topic. However, most current anomaly detection methods either focus exclusively on single-faceted transaction information or assume that multiple types of transaction network data are centrally stored or shared. In the field of IIoT scenario, privacy concerns and legal restrictions frequently hinder data centralization, resulting in data islands, which refer to decentralized multisource transaction information. Therefore, we propose a novel <u>fed</u>erated <u>G</u>NNs framework for the <u>t</u>emporal <u>t</u>ransaction network <u>a</u>nomaly <u>d</u>etection, designated as FedGT<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>AD. Specifically, the training process is bifurcated: client-side privacy temporal transaction network feature extraction is conducted locally at its corresponding client, while privacy-protected feature aggregation from all clients occurs on a trusted server. To facilitate more effective anomaly detection, each client initially models edge features and temporal transaction information as node attributes, along with network snapshots for subsequent graph feature computation with GNNs. During the integration process, the server integrates the node-level embedding and computes multisource transaction network features from all clients following a differential privacy mechanism to ensure client-side data security. The experimental results on three decentralized multisource transaction networks demonstrated that FedGT<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>AD outperforms baseline methods by 0.9% to 2.7% in accuracy. Overall, FedGT<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>AD offers a promising approach for mining decentralized multisource transaction networks while preserving privacy in anomaly detection tasks.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111122"},"PeriodicalIF":6.7,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887071","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":"Line balancing for energy efficiency in production: A qualitative and quantitative literature analysis","authors":"Julian Petersen ,&nbsp;Amir Nourmohammadi ,&nbsp;Masood Fathi ,&nbsp;Morteza Ghobakhloo ,&nbsp;Madjid Tavana","doi":"10.1016/j.cie.2025.111144","DOIUrl":"10.1016/j.cie.2025.111144","url":null,"abstract":"<div><div>In the rapidly evolving landscape of hyperconnected digital manufacturing, known as Industry 4.0, achieving energy efficiency has become a critical priority. As manufacturers worldwide strive to meet sustainable development goals, enhancing energy efficiency is essential for reducing operational costs and minimizing environmental impact. In this context, line balancing is a pivotal strategy for optimizing energy consumption within manufacturing processes. This study presents a comprehensive literature review on the Line Balancing Problems (LBPs) focused on enhancing energy efficiency. The review aims to provide a holistic understanding of this domain by examining past, present, and future trends. A systematic literature review is conducted using the PRISMA method, incorporating both qualitative and quantitative analyses. The quantitative analysis identifies prevalent patterns and emerging trends in energy efficiency optimization within the LBP domain. Concurrently, the qualitative analysis explores various aspects of existing studies, including configurations of lines, managerial considerations, objectives, solution methodologies, and real-world applications. This review synthesizes current knowledge and highlights potential avenues for future research, underlining the importance of energy efficiency in driving sustainable practices in Industry 4.0 and the emerging Industry 5.0 paradigm.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"205 ","pages":"Article 111144"},"PeriodicalIF":6.7,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143904090","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":"System-Wide Optimization of Free-Floating Bike-Sharing for Urban Rail Stations: A demand prediction and scheduling approach","authors":"Jinjun Tang ,&nbsp;Maoxin Ren ,&nbsp;Ziyue Yuan ,&nbsp;Jianming Cai ,&nbsp;Yunyi Liang","doi":"10.1016/j.cie.2025.111121","DOIUrl":"10.1016/j.cie.2025.111121","url":null,"abstract":"<div><div>Free-floating bike-sharing (FFBS) addresses the first/last mile challenges in urban rail transit (URT), while facing supply–demand imbalance problems owing to unrestricted bike parking. Previous research primarily equated actual bike usage with demand and focused on cost-efficiency, which overlooks unmet demand and system-wide optimization. This study proposes a comprehensive framework to optimize FFBS availability at URT stations, particularly during peak hours, through 1) demand prediction, 2) time-based scheduling, 3) priority scheduling strategy, and 4) system-wide optimization. The proposed method incorporates URT ridership as a pivotal feature to enhance the accuracy of bike-sharing demand prediction in URT transfer scenarios. To achieve bike-scheduling benefits, this study introduces a grid-based approach to convert ride data into predictive orders for bike scheduling, measuring time savings across transit modes. Additionally, a prioritization strategy for bike redistribution is designed based on the classification of bus routes around URT stations, ensuring a balanced integration of FFBS and other public transport modes. A multi-objective optimization model is designed to minimize operating costs and maximize passenger time savings, which is addressed with the NSGA-III algorithm. A numerical study using Shenzhen’s public transportation data reveals that prioritizing selected stations leads to a 19.4% greater average time savings per order compared to non-priority stations, along with a 7.60% reduction in total passenger travel time. This study more accurately reflects the actual demand, thereby achieving the supply–demand balance in URT-BBS transfers.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111121"},"PeriodicalIF":6.7,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864664","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":"Reliability and optimal age-based replacement policy for consecutive 2-out-of-n:G system equipped with protection blocks","authors":"Serkan Eryilmaz","doi":"10.1016/j.cie.2025.111120","DOIUrl":"10.1016/j.cie.2025.111120","url":null,"abstract":"<div><div>This paper concerns the reliability evaluation and optimal age-based replacement policy for the linear consecutive 2-out-of-<span><math><mi>n</mi></math></span>:G system whose two consecutive components are protected by a block that has its own failure rate. Two alternative methods are proposed to compute the reliability of the system. The first method is based on direct probabilistic approach and uses the reliability of the ordinary consecutive 2-out-of-<span><math><mi>n</mi></math></span>:G system. The second method is based on the concept of survival signature. Closed form equations for the system reliability and the mean number of failed components within the system are obtained. The optimal age-based replacement policy is also defined and studied. Extensive numerical results are presented to illustrate the findings.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111120"},"PeriodicalIF":6.7,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143869591","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 inter-subgroup compensation mechanism by Nash bargaining game for managing non-cooperative behavior in group decision making","authors":"Jie Yang ,&nbsp;Jian Wu ,&nbsp;Francisco Chiclana ,&nbsp;Mingshuo Cao ,&nbsp;Ronald R. Yager","doi":"10.1016/j.cie.2025.111114","DOIUrl":"10.1016/j.cie.2025.111114","url":null,"abstract":"<div><div>Non-cooperative behavior exhibited by DMs when they must make excessive interest compromises hinders the achievement of group consensus. This study develops an inter-subgroup compensation mechanism using the Nash bargaining game under the minimum cost consensus model (MCCM) framework to managing non-cooperative behavior. First, a cooperative acceptability index (CAI) based on compromise limit costs is proposed to objectively identify non-cooperative behavior. By quantifying the acceptable compromise limit costs, the CAI ensures that consensus adjustments remain within acceptable bounds. Then, an inter-subgroup compensation mechanism is designed using the Nash bargaining game from the perspective of Kaldor–Hicks improvement. This mechanism enables cooperative DMs to incentivize non-cooperative peers via resource transfers, achieving dual optimization by minimizing collective costs and ensuring individual acceptability. Finally, a community renewal application example and comparison analysis are provided to illustrate the efficacy of the proposed approach.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111114"},"PeriodicalIF":6.7,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864663","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":"Coordinating oncologist appointments with chemotherapy treatments under uncertainty","authors":"Ege Ozyuksel ,&nbsp;Serhat Gul ,&nbsp;Tonguç Ünlüyurt ,&nbsp;Batuhan Çelik","doi":"10.1016/j.cie.2025.111123","DOIUrl":"10.1016/j.cie.2025.111123","url":null,"abstract":"<div><div>Scheduling chemotherapy treatments in outpatient chemotherapy clinics (OCCs) presents significant challenges due to limited resources, uncertainty in infusion durations, and the need for coordinating with oncologist consultations. This study addresses these challenges through integrating oncologist consultation and chemotherapy scheduling by determining appointment times for a daily list of patients. A two-stage stochastic mixed-integer programming model is developed, considering stochastic factors such as infusion durations and the statuses of chemotherapy treatment approvals after consultations. In the first stage of the model, patients of each oncologist are organized in a sequence, and appointment times are set. In the second stage, patients are assigned to chairs and nurses using an optimal myopic policy. The objective function penalizes the expected weighted sum of the total working time of the OCC and the waiting times of patients. To represent the original scenario set by a reduced scenario set, a scenario reduction algorithm is employed. The algorithm, a Wasserstein Distance-Based Local Search Algorithm (WD-LSA), is tested using real data from a major academic oncology hospital in Turkey. The performance of the WD-LSA algorithm is demonstrated by comparing with CPLEX for smaller number of scenarios and with heuristic algorithms for larger number of scenarios. We find that the gap is quite small when compared with CPLEX solutions and the solutions are much better than the solutions found by the practical scheduling heuristics from the literature. The trade-off between patient waiting time and total working time is assessed. The dependency of the performance measures to the number of oncologists and nurses is investigated. Lastly, the value of stochastic solution is estimated.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111123"},"PeriodicalIF":6.7,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143869589","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 optimization approach for crowdshipping leveraging smart lockers as decentralized urban transshipment hubs","authors":"Xin-Yu Zhuang ,&nbsp;I-Lin Wang ,&nbsp;Chia-Yen Lee","doi":"10.1016/j.cie.2025.111137","DOIUrl":"10.1016/j.cie.2025.111137","url":null,"abstract":"<div><div>Urban last-mile delivery systems face increasing challenges from rising e-commerce demand, frequent delivery failures, and sustainability concerns. This paper presents a novel integration of decentralized smart lockers into crowdshipping operations, uniquely leveraging their excess capacity as ad hoc transshipment points to improve delivery networks. Specifically, parcels are transferred via smart lockers by one or more crowdshippers, reducing trip detours and expanding geographical coverage. Unlike prior studies, our approach eliminates the need for time-synchronized parcel handovers, significantly enhancing operational flexibility. A mixed-integer programming (MIP) model is developed to optimize driver-parcel assignments and routing for the entire system without imposing a single-transshipment assumption. However, to address scalability challenges in large instances, we introduce a rolling-horizon framework and two tailored column-generation algorithms—complete (CCG) and greedy (GCG)—which assume at most one transshipment per parcel. In experiments with 900 drivers and 300 parcels, the CCG achieves exact solutions in 20 min under this assumption, while the GCG demonstrates a 12.1% cost reduction with a 1–2% optimality gap, requiring significantly less computation time. Although the MIP and rolling-horizon models can only solve smaller instances, they validate the effectiveness of the algorithms. This study provides practical and scalable solutions for overcoming last-mile delivery challenges.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111137"},"PeriodicalIF":6.7,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850659","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":"Dynamic task allocations with Q-learning based particle swarm optimization for human-robot collaboration disassembly of electric vehicle battery recycling","authors":"Jinhua Xiao ,&nbsp;Zhiwen Zhang ,&nbsp;Sergio Terzi ,&nbsp;Nabil Anwer ,&nbsp;Benoît Eynard","doi":"10.1016/j.cie.2025.111133","DOIUrl":"10.1016/j.cie.2025.111133","url":null,"abstract":"<div><div>With the wide application of Electric Vehicles (EV) and intelligent technology, the recycling of EV batteries presents significant challenges to cope with the dynamic disassembly tasks and operations. Similarly, human-robot collaborative (HRC) disassembly has emerged as an effective solution to accomplish the disassembly task allocation and improve efficiency. This paper proposed an improved HRC disassembly method integrating Q-learning-based Particle Swarm Optimization (PSO) to optimize the disassembly task sequence for multi-agent disassembly strategies. Furthermore, the Q-learning model is integrated to guide the variable neighborhood search (VNS) algorithm enabling efficient neighborhood structure selection to enhance local search capabilities and optimize multi-agent disassembly sorting tasks. By considering the disassembly experiment of Mercedes-Benz EQS NCM 811 battery as a case study, the proposed method is deeply analyzed and compared with traditional methods under the same objective function. The results demonstrate the proposed algorithm reduces the fitness value and improves the optimization of disassembly tasks. The experimental results show that the proposed algorithm effectively improves the efficiency of HRC disassembly compared to other algorithms, offering a more efficient solution for the recycling of retired EV batteries.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111133"},"PeriodicalIF":6.7,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143858938","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":"Considering regret psychology and non-cooperative competition among alternatives for heterogeneous multi-attribute group decision making","authors":"Yang Huang ,&nbsp;Meiqiang Wang","doi":"10.1016/j.cie.2025.111132","DOIUrl":"10.1016/j.cie.2025.111132","url":null,"abstract":"<div><div>In reality, to select the best one from a set of alternatives, there are widespread situations that require several experts to assess the attribute values of each alternative with heterogeneous information. The purpose of this paper is to solve the heterogeneous multi-attribute group decision making (HMAGDM) problems with attribute values involving real numbers, intervals, intuitionistic fuzzy sets, interval type-2 fuzzy sets, and interval-valued hesitant fuzzy sets from the perspective that alternatives have regret psychology with respect to the assessment information and that there is a non-cooperative competitive relationship among alternatives. Therefore, a method based on regret theory and interval data envelopment analysis (DEA) game cross-efficiency model is proposed for HMAGDM. The method adopts a process of aggregation followed by exploration. In the aggregation phase, a regret theory-based expert weight determination model is constructed to derive the weights of experts, and the individual decision matrices provided by individual experts are further aggregated into a collective decision matrix. Then, the heterogeneous information in the collective decision matrix is uniformly converted into intervals, which are represented as variables with unknown parameters. According to these variables, a regret theory-based interval DEA game cross-efficiency model is proposed to calculate the comprehensive values of alternatives and thus rank alternatives. The feasibility and effectiveness of the proposed method are illustrated by a supplier selection example.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111132"},"PeriodicalIF":6.7,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854916","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":"Integrating machine learning based EWMA control charts for multivariate process monitoring","authors":"Muhammad Waqas Kazmi,&nbsp;Muhammad Noor-ul-Amin","doi":"10.1016/j.cie.2025.111131","DOIUrl":"10.1016/j.cie.2025.111131","url":null,"abstract":"<div><div>Memory-type control charts, such as the multivariate EWMA (MEWMA), are recognized for their effectiveness in detecting small to moderate changes in the process mean vector. In comparison, Adaptive Multivariate EWMA (AMEWMA) control charts offer superior capabilities over traditional methods. This study proposes an adaptive multivariate EWMA (SAMEWMA) control chart based on Machine Learning (ML) techniques such as Random Forest (RF), K-NN, and Support Vector Regression (SVR) to monitor specifically small shifts in the process mean vector. The results show that the proposed chart demonstrates exceptional performance in detecting small shifts in the mean vector compared to various existing charts, such as AMEWMA-I and AMEWMA-II. Investigations also prove the superiority of the SVR method among other ML approaches. The Average Run Length (ARL) matric is employed to determine the performance of the control charts using the Monte Carlo (MC) simulation technique. Two real-world examples are presented to demonstrate the effectiveness and superiority of the proposed control chart in detecting variations in the process mean vector.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111131"},"PeriodicalIF":6.7,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143869555","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}