Computers & Industrial Engineering最新文献_第5页

GAT-AD: Graph Attention Networks for contextual anomaly detection in network monitoring

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110830

Hamid Latif-Martínez , José Suárez-Varela , Albert Cabellos-Aparicio , Pere Barlet-Ros

Network anomaly detection is essential to promptly detect and fix issues in the network. Particularly, detecting traffic anomalies enables the early detection of configuration errors, malicious activities, or equipment malfunctions that could lead to severe impact on the network. In this paper, we present GAT-AD, a Deep Learning-based anomaly detection solution for network monitoring systems, which integrates a custom neural network model based on Graph Attention Networks (GAT). Our solution monitors aggregated traffic on origin–destination flows and automatically defines contexts that group flows with similar past activity. The neural network model within GAT-AD can be efficiently trained in a self-supervised manner. We evaluate our solution against two state-of-the-art anomaly detection baselines also based on graph representations and Deep Learning, in two different datasets:

(i)

WaDi, which is a well-known dataset for anomaly detection in a distributed sensor network, and

(i i)

Abilene, where we inject synthetically-generated anomalies into a dataset with real-world traffic from a large-scale backbone network. The results show that GAT-AD outperforms the two anomaly detection baselines: in WaDi by 14.1% in recall and 10.07% in F1-score, and in the Abilene dataset by

\approx

17.5% recall with respect to the best baseline.

{"title":"GAT-AD: Graph Attention Networks for contextual anomaly detection in network monitoring","authors":"Hamid Latif-Martínez , José Suárez-Varela , Albert Cabellos-Aparicio , Pere Barlet-Ros","doi":"10.1016/j.cie.2024.110830","DOIUrl":"10.1016/j.cie.2024.110830","url":null,"abstract":"<div><div>Network anomaly detection is essential to promptly detect and fix issues in the network. Particularly, detecting traffic anomalies enables the early detection of configuration errors, malicious activities, or equipment malfunctions that could lead to severe impact on the network. In this paper, we present <em>GAT-AD</em>, a Deep Learning-based anomaly detection solution for network monitoring systems, which integrates a custom neural network model based on Graph Attention Networks (GAT). Our solution monitors aggregated traffic on origin–destination flows and automatically defines contexts that group flows with similar past activity. The neural network model within <em>GAT-AD</em> can be efficiently trained in a self-supervised manner. We evaluate our solution against two state-of-the-art anomaly detection baselines also based on graph representations and Deep Learning, in two different datasets: <span><math><mrow><mo>(</mo><mi>i</mi><mo>)</mo></mrow></math></span> <em>WaDi</em>, which is a well-known dataset for anomaly detection in a distributed sensor network, and <span><math><mrow><mo>(</mo><mi>i</mi><mi>i</mi><mo>)</mo></mrow></math></span> <em>Abilene</em>, where we inject synthetically-generated anomalies into a dataset with real-world traffic from a large-scale backbone network. The results show that <em>GAT-AD</em> outperforms the two anomaly detection baselines: in <em>WaDi</em> by 14.1% in recall and 10.07% in F1-score, and in the <em>Abilene</em> dataset by <span><math><mo>≈</mo></math></span>17.5% recall with respect to the best baseline.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110830"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143179718","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}

引用次数: 0

Fleet size problem for one-way electric carsharing services considering customers’ waiting tolerance and waiting stress

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110784

Ting Wu , Min Xu , Abdelrahman E.E. Eltoukhy

Service operation problems arising from electric carsharing services have been the research subject of many scholars in the past few years. Previous studies did not consider customers’ psychological waiting stress in the decision-making of electric carsharing services. This study addresses a fleet size problem for one-way electric carsharing services while considering vehicle relocation, vehicle charging, and customers’ waiting tolerance as well as psychological waiting stress. A mixed-integer nonlinear programming (MINLP) model is first developed for the problem. By exploring the model convexity, we put forward an effective outer-approximation algorithm such that the ε-optimal solution can be obtained. Numerical experiments are conducted to demonstrate the efficacy of the proposed model and solution method. We also analyze how the consideration of customers’ waiting tolerance and waiting stress influences the fleet size, system profitability, and service level.

引用次数: 0

A new reliability allocation method for mechanical systems considering parts recycling and performance stability

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110792

Jian Li , Hongwei Wang , Zongyi Mu , Yulong Li , Yanbin Du

A reliability allocation method for mechanical system is proposed in this paper, which considers the parts recycling and the performance stability of system. First, taking the meta-action of the mechanical system as the analysis object, and six influencing factors are comprehensively considered, including the maturity of unit technology, environmental severity, parts recycling and reuse, unit structural complexity, unit maintenance coefficient, and performance impact. The maturity of unit technology, environmental severity and parts recycling and reuse as the qualitative evaluation indexes; The complex of unit structure, coefficient of unit maintenance and performance impact as the quantitative evaluation indexes. Then, the qualitative data and quantitative data are comprehensively analyzed by TOPSIS method to obtain the reliability distribution coefficient of each unit, and the reliability of the mechanical system is allocated reasonably. Compared with the traditional method, the reliability allocation process of mechanical system is analyzed from the perspective of the lifecycle cost and the perspective of mechanical system performance stability. The boundary of influence factors is clear and the rationality results is more reasonable. The reliability allocation of NC rotary table system is analyzed by using the proposed method, and the allocation results is compared with the traditional method to verify the effectiveness of this method.

{"title":"A new reliability allocation method for mechanical systems considering parts recycling and performance stability","authors":"Jian Li , Hongwei Wang , Zongyi Mu , Yulong Li , Yanbin Du","doi":"10.1016/j.cie.2024.110792","DOIUrl":"10.1016/j.cie.2024.110792","url":null,"abstract":"<div><div>A reliability allocation method for mechanical system is proposed in this paper, which considers the parts recycling and the performance stability of system. First, taking the <em>meta</em>-action of the mechanical system as the analysis object, and six influencing factors are comprehensively considered, including the maturity of unit technology, environmental severity, parts recycling and reuse, unit structural complexity, unit maintenance coefficient, and performance impact. The maturity of unit technology, environmental severity and parts recycling and reuse as the qualitative evaluation indexes; The complex of unit structure, coefficient of unit maintenance and performance impact as the quantitative evaluation indexes. Then, the qualitative data and quantitative data are comprehensively analyzed by TOPSIS method to obtain the reliability distribution coefficient of each unit, and the reliability of the mechanical system is allocated reasonably. Compared with the traditional method, the reliability allocation process of mechanical system is analyzed from the perspective of the lifecycle cost and the perspective of mechanical system performance stability. The boundary of influence factors is clear and the rationality results is more reasonable. The reliability allocation of NC rotary table system is analyzed by using the proposed method, and the allocation results is compared with the traditional method to verify the effectiveness of this method.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110792"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180720","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}

引用次数: 0

A data-driven optimization model for the scattered storage assignment with replenishment

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110766

Meng Wang , Xiang Liu , Liping Wang , Yunqi Bian , Kun Fan , Ren-Qian Zhang

Modern warehouses are transitioning from pure storage facilities to order fulfillment centers. To improve order-picking efficiency, picking areas are restricted to small zones to save picker travel distance and thus can only store a limited quantity of SKUs. As a result, replenishment must be frequently carried out which not only causes intensive working efforts but also impacts the order-picking efficiency. Despite of the important role of replenishment, it has been seldom considered in storage assignment planning. This paper proposes a novel optimization model for the storage assignment problem considering both the order-picking and replenishment operations. Instead of the traditional first-extract-then-optimize paradigm, we develop an effective solution method for the problem by integrating the extraction and optimization steps together to avoid the loss of information. Intensive experiments and a case study are presented, the results of which indicate significant advantages of our model against the state-of-the-art counterpart. Several managerial implications are derived: (1) Order data implies substantial useful information for storage assignment planning, including but not limited to the demand correlation of products; (2) The replenishment efforts are intensive and negatively correlated to the order-picking efforts, which therefore should not be neglected in storage assignment planning; (3) To minimize the total working efforts, the optimal replenishment level

r

of the

(r, S)

replenishment policy should be more than

0.4 S

but less than

0.6 S

with respect to each SKU.

{"title":"A data-driven optimization model for the scattered storage assignment with replenishment","authors":"Meng Wang , Xiang Liu , Liping Wang , Yunqi Bian , Kun Fan , Ren-Qian Zhang","doi":"10.1016/j.cie.2024.110766","DOIUrl":"10.1016/j.cie.2024.110766","url":null,"abstract":"<div><div>Modern warehouses are transitioning from pure storage facilities to order fulfillment centers. To improve order-picking efficiency, picking areas are restricted to small zones to save picker travel distance and thus can only store a limited quantity of SKUs. As a result, replenishment must be frequently carried out which not only causes intensive working efforts but also impacts the order-picking efficiency. Despite of the important role of replenishment, it has been seldom considered in storage assignment planning. This paper proposes a novel optimization model for the storage assignment problem considering both the order-picking and replenishment operations. Instead of the traditional first-extract-then-optimize paradigm, we develop an effective solution method for the problem by integrating the extraction and optimization steps together to avoid the loss of information. Intensive experiments and a case study are presented, the results of which indicate significant advantages of our model against the state-of-the-art counterpart. Several managerial implications are derived: (1) Order data implies substantial useful information for storage assignment planning, including but not limited to the demand correlation of products; (2) The replenishment efforts are intensive and negatively correlated to the order-picking efforts, which therefore should not be neglected in storage assignment planning; (3) To minimize the total working efforts, the optimal replenishment level <span><math><mi>r</mi></math></span> of the <span><math><mrow><mo>(</mo><mi>r</mi><mo>,</mo><mi>S</mi><mo>)</mo></mrow></math></span> replenishment policy should be more than <span><math><mrow><mn>0</mn><mo>.</mo><mn>4</mn><mi>S</mi></mrow></math></span> but less than <span><math><mrow><mn>0</mn><mo>.</mo><mn>6</mn><mi>S</mi></mrow></math></span> with respect to each SKU.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110766"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180892","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}

引用次数: 0

Research on location-inventory-routing optimization of emergency logistics based on multiple reliability under uncertainty

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110826

Ling Zhang , Na Yuan , Jing Wang , Jizhao Li

Earthquakes, floods and other types of natural disasters are frequent and bring many devastating effects. The research related to emergency logistics has received much attention in recent years. In order to further improve the rescue efficiency and reduce disaster losses, a multi-objective two-stage stochastic programming model of location-inventory-routing of emergency logistics based on multiple reliability under uncertainty is addressed. The proposed model includes three types of uncertainty as demand, supply and transportation time, and two kinds of reliability as distribution center facilities and road access. It is used for integrated decision making in disaster preparedness and response stages. Factors such as material bulk procurement discount, pre-disaster budget, multiple transportation modes, capacity constraints, and disaster scenarios are considered comprehensively. Then, an algorithm was developed. A non-dominated ranking genetic algorithm (NSGA-II) is used to solve the developed model according to its characteristics. The validity of the model and algorithm is verified by conducting a case study on an earthquake in Sichuan, China, and the Pareto optimal solution set is obtained. Finally, sensitivity analysis of the parameters is performed to investigate the effect of changes in key parameters on the model solutions. Thus, some relevant management insights are provided. The results show that an appropriate increase in the pre-disaster budget can substantially reduce the response cost in the post-disaster period. In addition, increasing the number of resident helicopters within the material inventory by a certain amount can help reduce the total distribution time.

{"title":"Research on location-inventory-routing optimization of emergency logistics based on multiple reliability under uncertainty","authors":"Ling Zhang , Na Yuan , Jing Wang , Jizhao Li","doi":"10.1016/j.cie.2024.110826","DOIUrl":"10.1016/j.cie.2024.110826","url":null,"abstract":"<div><div>Earthquakes, floods and other types of natural disasters are frequent and bring many devastating effects. The research related to emergency logistics has received much attention in recent years. In order to further improve the rescue efficiency and reduce disaster losses, a multi-objective two-stage stochastic programming model of location-inventory-routing of emergency logistics based on multiple reliability under uncertainty is addressed. The proposed model includes three types of uncertainty as demand, supply and transportation time, and two kinds of reliability as distribution center facilities and road access. It is used for integrated decision making in disaster preparedness and response stages. Factors such as material bulk procurement discount, pre-disaster budget, multiple transportation modes, capacity constraints, and disaster scenarios are considered comprehensively. Then, an algorithm was developed. A non-dominated ranking genetic algorithm (NSGA-II) is used to solve the developed model according to its characteristics. The validity of the model and algorithm is verified by conducting a case study on an earthquake in Sichuan, China, and the Pareto optimal solution set is obtained. Finally, sensitivity analysis of the parameters is performed to investigate the effect of changes in key parameters on the model solutions. Thus, some relevant management insights are provided. The results show that an appropriate increase in the pre-disaster budget can substantially reduce the response cost in the post-disaster period. In addition, increasing the number of resident helicopters within the material inventory by a certain amount can help reduce the total distribution time.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110826"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181749","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}

引用次数: 0

An improved beluga whale optimization using ring topology for solving multi-objective task scheduling in cloud

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110836

Behnam Mohammad Hasani Zade, Najme Mansouri, Mohammad Masoud Javidi

To enhance cloud system performance and customer satisfaction levels, task scheduling must be addressed in the system. Beluga Whale Optimization (BWO) is a metaheuristic method that was developed recently. However, this method still suffers from local minima stagnation despite having an operator that enhances the diversity of population. As a result, Opposition-Based Learning (OBL) can be combined with a Levy Fight Distribution (LFD) and a hybrid balance factor to overcome conventional BWO’s main weaknesses, including slow convergence and local optima traps. We present a multi-objective form of improved BWO (IBWO) to solve task scheduling problems considering both makespan and costs. Multi Objective Improved Beluga Whale Optimization with Ring Topology (MO-IBWO-Ring) is proposed as an efficient task scheduling algorithm that uses whales as feasible solutions for cloud computing tasks. Local search capabilities are also enhanced by using the ring topology concept. The proposed MO-IBWO-Ring algorithm as an optimization algorithm is tested on ten new test functions, and its performance is compared with four algorithms (i.e., Decision space-based Niching Non-dominated Sorting Genetic Algorithm II (DN-NSGAII), Multi-Objective Particle Swarm Optimization algorithm with Ring topology and Special Crowding Distance (MO_Ring_PSO_SCD), Omni-optimizer, and Multi-Objective Particle Swarm Optimization (MOPSO)). Two scenarios have been used to evaluate MO-IBWO-Ring’s performance as a task scheduler. 1) Heterogeneous Computing Scheduling Problem (HCSP) is used as the benchmark dataset with a small (512) and a medium (1024) number of tasks, and 2) with random generated tasks and VMs. When measuring provider metrics, the proposed method achieved better results than competing methods.

{"title":"An improved beluga whale optimization using ring topology for solving multi-objective task scheduling in cloud","authors":"Behnam Mohammad Hasani Zade, Najme Mansouri, Mohammad Masoud Javidi","doi":"10.1016/j.cie.2024.110836","DOIUrl":"10.1016/j.cie.2024.110836","url":null,"abstract":"<div><div>To enhance cloud system performance and customer satisfaction levels, task scheduling must be addressed in the system. Beluga Whale Optimization (BWO) is a metaheuristic method that was developed recently. However, this method still suffers from local minima stagnation despite having an operator that enhances the diversity of population. As a result, Opposition-Based Learning (OBL) can be combined with a Levy Fight Distribution (LFD) and a hybrid balance factor to overcome conventional BWO’s main weaknesses, including slow convergence and local optima traps. We present a multi-objective form of improved BWO (IBWO) to solve task scheduling problems considering both makespan and costs. Multi Objective Improved Beluga Whale Optimization with Ring Topology (MO-IBWO-Ring) is proposed as an efficient task scheduling algorithm that uses whales as feasible solutions for cloud computing tasks. Local search capabilities are also enhanced by using the ring topology concept. The proposed MO-IBWO-Ring algorithm as an optimization algorithm is tested on ten new test functions, and its performance is compared with four algorithms (i.e., Decision space-based Niching Non-dominated Sorting Genetic Algorithm II (DN-NSGAII), Multi-Objective Particle Swarm Optimization algorithm with Ring topology and Special Crowding Distance (MO_Ring_PSO_SCD), Omni-optimizer, and Multi-Objective Particle Swarm Optimization (MOPSO)). Two scenarios have been used to evaluate MO-IBWO-Ring’s performance as a task scheduler. 1) Heterogeneous Computing Scheduling Problem (HCSP) is used as the benchmark dataset with a small (512) and a medium (1024) number of tasks, and 2) with random generated tasks and VMs. When measuring provider metrics, the proposed method achieved better results than competing methods.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110836"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180696","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}

引用次数: 0

A machine learning-based hybrid approach for maximizing supply chain reliability in a pharmaceutical supply chain

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110834

Devesh Kumar , Gunjan Soni , Sachin Kumar Mangla , Yigit Kazancoglu , A.P.S. Rathore

In today’s interconnected global economy, supply chain (SC) reliability is crucial particularly in sectors like the pharmaceutical industry, where disruptions can significantly impact public health. SCs have become important to industries due to a customer-driven shift aimed at improving SC reliability, especially in terms of delivery performance. It is crucial to define and find the best strategy for reaching the organizational objectives in SC. While designing a SC, supplier selection (SS) and order allocation are two decisions that have to be made separately. This study addresses the critical challenges of SS and order allocation within pharmaceutical SCs. It proposes a novel, two-phased hybrid approach, the first phase integrates machine learning(ML) and multi-criteria decision-making(MCDM) method for robust SS. The second phase develops a mathematical model to optimize order allocation while considering SC reliability. This work employs support vector machine (SVM) as the particular ML method, in which the training data are historical corporate data that dictate parameters weights. These weights are then used in the measurement of alternatives and ranking according to compromise solution (MARCOS) method to rank the suppliers. A multi- objective mixed integer programming (MOMIP) model is then formulated to identify the right order quantity from the identified suppliers of a pharmaceutical SC in order to minimize SC cost and maximize SC reliability. The results indicate that by optimizing SC reliability and costs, orders are directed to high-priority suppliers. This study provides a comprehensive, data-driven decision-making framework to assure SC’s reliability and cost-efficiency. The implications of the findings are also profound and contribute valuable insights for industry practitioners to improve the performance of SC. To illustrate the proposed methodology, an SC example of a pharmaceutical industry is analyzed using the LINGO solver.

{"title":"A machine learning-based hybrid approach for maximizing supply chain reliability in a pharmaceutical supply chain","authors":"Devesh Kumar , Gunjan Soni , Sachin Kumar Mangla , Yigit Kazancoglu , A.P.S. Rathore","doi":"10.1016/j.cie.2024.110834","DOIUrl":"10.1016/j.cie.2024.110834","url":null,"abstract":"<div><div>In today’s interconnected global economy, supply chain (SC) reliability is crucial particularly in sectors like the pharmaceutical industry, where disruptions can significantly impact public health. SCs have become important to industries due to a customer-driven shift aimed at improving SC reliability, especially in terms of delivery performance. It is crucial to define and find the best strategy for reaching the organizational objectives in SC. While designing a SC, supplier selection (SS) and order allocation are two decisions that have to be made separately. This study addresses the critical challenges of SS and order allocation within pharmaceutical SCs. It proposes a novel, two-phased hybrid approach, the first phase integrates machine learning(ML) and multi-criteria decision-making(MCDM) method for robust SS. The second phase develops a mathematical model to optimize order allocation while considering SC reliability. This work employs support vector machine (SVM) as the particular ML method, in which the training data are historical corporate data that dictate parameters weights. These weights are then used in the measurement of alternatives and ranking according to compromise solution (MARCOS) method to rank the suppliers. A multi- objective mixed integer programming (MOMIP) model is then formulated to identify the right order quantity from the identified suppliers of a pharmaceutical SC in order to minimize SC cost and maximize SC reliability. The results indicate that by optimizing SC reliability and costs, orders are directed to high-priority suppliers. This study provides a comprehensive, data-driven decision-making framework to assure SC’s reliability and cost-efficiency. The implications of the findings are also profound and contribute valuable insights for industry practitioners to improve the performance of SC. To illustrate the proposed methodology, an SC example of a pharmaceutical industry is analyzed using the LINGO solver.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110834"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181810","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}

引用次数: 0

An optimization model and customized solution approaches for in-plant logistic problem within the context of lean management 精益管理背景下工厂内物流问题的优化模型和定制解决方法

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110832

Kadir Büyüközkan , Beren Gürsoy Yılmaz , Gökhan Özçelik , Ömer Faruk Yılmaz

Employing effectiveness, responsiveness, and lean metrics, this study focuses on the impact of product picking/stacking, trailer allocation, and lot splitting implementation strategies on the in-plant logistic problem. While in-plant logistic problems have attracted attention in recent years, the addressed problem involving decisions on production, transportation, and inventory management has received relatively little attention in the literature. Furthermore, to the best of our knowledge, this problem has not yet been explored with operational-level strategies in the context of lean management principles. To fill this gap, we develop a novel generic optimization model with the aim of minimizing overall costs by integrating decisions related to production, transportation, and inventory. Given the NP-hard nature of this problem, we propose customized solution approaches regarding the implemented strategies for handling large-sized problems. To analyze the impact of controlled factors, a Design of Experiment (DoE) framework is established based on a real case study from the wood-based panel industry. On top of that, several metrics, such as WIP levels, utilization rates, and lead time, are considered to provide a comprehensive analysis of the scenarios. The computational results affirm that employing the balanced storage rule for the product picking/stacking strategy, along with the equal sublot division methodology, significantly reduces the overall cost. Additionally, the findings demonstrate that the designed algorithm, namely GA-BSMATE, exhibits robustness to address diverse situations, particularly when the minimum arrival time rule is implemented as a trailer allocation strategy.

{"title":"An optimization model and customized solution approaches for in-plant logistic problem within the context of lean management","authors":"Kadir Büyüközkan , Beren Gürsoy Yılmaz , Gökhan Özçelik , Ömer Faruk Yılmaz","doi":"10.1016/j.cie.2024.110832","DOIUrl":"10.1016/j.cie.2024.110832","url":null,"abstract":"<div><div>Employing effectiveness, responsiveness, and lean metrics, this study focuses on the impact of product picking/stacking, trailer allocation, and lot splitting implementation strategies on the in-plant logistic problem. While in-plant logistic problems have attracted attention in recent years, the addressed problem involving decisions on production, transportation, and inventory management has received relatively little attention in the literature. Furthermore, to the best of our knowledge, this problem has not yet been explored with operational-level strategies in the context of lean management principles. To fill this gap, we develop a novel generic optimization model with the aim of minimizing overall costs by integrating decisions related to production, transportation, and inventory. Given the NP-hard nature of this problem, we propose customized solution approaches regarding the implemented strategies for handling large-sized problems. To analyze the impact of controlled factors, a Design of Experiment (DoE) framework is established based on a real case study from the wood-based panel industry. On top of that, several metrics, such as WIP levels, utilization rates, and lead time, are considered to provide a comprehensive analysis of the scenarios. The computational results affirm that employing the balanced storage rule for the product picking/stacking strategy, along with the equal sublot division methodology, significantly reduces the overall cost. Additionally, the findings demonstrate that the designed algorithm, namely GA-BSMATE, exhibits robustness to address diverse situations, particularly when the minimum arrival time rule is implemented as a trailer allocation strategy.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110832"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181748","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}

引用次数: 0

Unlocking the Synergy: Increasing productivity through Human-AI collaboration in the industry 5.0 Era 释放协同效应：在工业 5.0 时代通过人机协作提高生产力

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110657

Xue Sun , Yu Song

The prevailing trajectory of technological evolution emphasizes the sustainable development of human-AI collaboration. In this study, we employ the coupling coordination degree model to evaluate the dynamics of human-AI collaboration in China and match it with listed companies. Through panel models, the study not only quantifies the contribution of such collaboration to enhancing company input–output efficiency but also explores how it serves as a catalyst for technological catch-up. Our findings indicate that the integration of human capital with AI emerges as a potent driver of company efficiency, with the extent of the impact also tied to organizational characteristics. Furthermore, the scale of investment and organizational size play a crucial role in the effectiveness of HIC, underscoring the adaptability of human-AI collaboration strategies to various organizational contexts and the importance of tailored implementation. Our research highlights the inherent collaborative potential of AI within the Industry 5.0 framework, advocating for the fusion of human creativity with AI precision to foster a development paradigm that is resource-efficient, cost-effective, and human-centric.

{"title":"Unlocking the Synergy: Increasing productivity through Human-AI collaboration in the industry 5.0 Era","authors":"Xue Sun , Yu Song","doi":"10.1016/j.cie.2024.110657","DOIUrl":"10.1016/j.cie.2024.110657","url":null,"abstract":"<div><div>The prevailing trajectory of technological evolution emphasizes the sustainable development of human-AI collaboration. In this study, we employ the coupling coordination degree model to evaluate the dynamics of human-AI collaboration in China and match it with listed companies. Through panel models, the study not only quantifies the contribution of such collaboration to enhancing company input–output efficiency but also explores how it serves as a catalyst for technological catch-up. Our findings indicate that the integration of human capital with AI emerges as a potent driver of company efficiency, with the extent of the impact also tied to organizational characteristics. Furthermore, the scale of investment and organizational size play a crucial role in the effectiveness of HIC, underscoring the adaptability of human-AI collaboration strategies to various organizational contexts and the importance of tailored implementation. Our research highlights the inherent collaborative potential of AI within the Industry 5.0 framework, advocating for the fusion of human creativity with AI precision to foster a development paradigm that is resource-efficient, cost-effective, and human-centric.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110657"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180148","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}

引用次数: 0

Electric vehicle supply chain investment under demand uncertainty: A jointly held real options perspective 需求不确定情况下的电动汽车供应链投资：共同持有实物期权的视角

IF 6.7 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110840

Feng Liu , Carman K.M. Lee , Min Xu

An increasing number of electric vehicle (EV) companies are facing supply chain investment decisions, which are essential for the effective operation and management of their businesses. This study proposes a real options approach to explore the investment timing threshold of the EV supply chain under demand uncertainty. It addresses the limitations of previous studies that primarily focused on the perspective of a single investor under a deterministic demand. To achieve the objective, an analytical real options game model is first presented for investment in the EV supply chain. Then, the investment timing threshold and option value of the EV supply chain are derived under three different scenarios: the integrated case, the revenue-sharing contract case, and the revenue-sharing contract through bargaining. The findings reveal that the investment timing threshold is lower when bargaining occurs between the two parties in the EV supply chain compared to the revenue-sharing contract case. Furthermore, the investment timing threshold exhibits a negative correlation with the drift and learning rates. It also increases with the volatility of the bargaining parameter, risk-free interest rate, and market demand volatility. The option value, on the other hand, shows a positive correlation with the demand-shift and volatility parameters. A bargaining-based revenue-sharing contract is proposed as a means to coordinate the supply chain. These results provide theoretical guidance for investments in the EV supply chain.

{"title":"Electric vehicle supply chain investment under demand uncertainty: A jointly held real options perspective","authors":"Feng Liu , Carman K.M. Lee , Min Xu","doi":"10.1016/j.cie.2024.110840","DOIUrl":"10.1016/j.cie.2024.110840","url":null,"abstract":"<div><div>An increasing number of electric vehicle (EV) companies are facing supply chain investment decisions, which are essential for the effective operation and management of their businesses. This study proposes a real options approach to explore the investment timing threshold of the EV supply chain under demand uncertainty. It addresses the limitations of previous studies that primarily focused on the perspective of a single investor under a deterministic demand. To achieve the objective, an analytical real options game model is first presented for investment in the EV supply chain. Then, the investment timing threshold and option value of the EV supply chain are derived under three different scenarios: the integrated case, the revenue-sharing contract case, and the revenue-sharing contract through bargaining. The findings reveal that the investment timing threshold is lower when bargaining occurs between the two parties in the EV supply chain compared to the revenue-sharing contract case. Furthermore, the investment timing threshold exhibits a negative correlation with the drift and learning rates. It also increases with the volatility of the bargaining parameter, risk-free interest rate, and market demand volatility. The option value, on the other hand, shows a positive correlation with the demand-shift and volatility parameters. A bargaining-based revenue-sharing contract is proposed as a means to coordinate the supply chain. These results provide theoretical guidance for investments in the EV supply chain.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110840"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181829","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}

引用次数: 0