Computers & Industrial Engineering最新文献_第2页

Hierarchical decision and control method for the human–exoskeleton collaborative packaging system based on deep reinforcement learning

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-25 DOI: 10.1016/j.cie.2025.111063

Bin Wang, Hao Tang, Shurun Wang, Zhaowu Ping, Qi Tan

{"title":"Hierarchical decision and control method for the human–exoskeleton collaborative packaging system based on deep reinforcement learning","authors":"Bin Wang, Hao Tang, Shurun Wang, Zhaowu Ping, Qi Tan","doi":"10.1016/j.cie.2025.111063","DOIUrl":"10.1016/j.cie.2025.111063","url":null,"abstract":"<div><div>The packaging process is an important part of the production and transportation process, and many companies have introduced exoskeleton robots to mitigate worker fatigue in the packaging process. Therefore, a human–exoskeleton collaborative packaging system with random product arrivals is studied, focusing on the operation decision and assistive force control of the system. A hierarchical decision and control policy is proposed to prevent the worker’s fatigue level from crossing a threshold while improving the energy efficiency of the exoskeleton and the system’s productivity. First, a hierarchical decision and control architecture is designed, in which the upper layer makes decisions on operations and the lower layer controls the assistive forces. Second, the optimal hierarchical decision and control policy is solved by combining the double DQN (DDQN) for discrete actions and the deep deterministic policy gradient (DDPG) for continuous actions. Finally, the proposed policy is validated in the constructed visualization virtual platform. The simulation results show that the proposed policy can effectively control worker fatigue and improve the energy efficiency of the equipment and the productivity of the system.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111063"},"PeriodicalIF":6.7,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748596","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

UNSW HomeNet: A network traffic flow dataset for AI-based smart home device classification

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-25 DOI: 10.1016/j.cie.2025.111041

Md Mizanur Rahman , Faycal Bouhafs , Sayed Amir Hoseini , Frank den Hartog

{"title":"UNSW HomeNet: A network traffic flow dataset for AI-based smart home device classification","authors":"Md Mizanur Rahman , Faycal Bouhafs , Sayed Amir Hoseini , Frank den Hartog","doi":"10.1016/j.cie.2025.111041","DOIUrl":"10.1016/j.cie.2025.111041","url":null,"abstract":"<div><div>The emergence of the Internet of Things (IoT) has introduced a variety of devices into smart homes, making smart home networks increasingly complex and insecure. However, many IoT device manufacturers prioritize functionality, time-to-market, and performance over security, leaving IoT devices and networks vulnerable. Automatic device classification techniques are crucial for applying various network management approaches to ensure both performance and security. Despite the considerable research effort devoted to device classification, very few datasets are publicly available for in-depth investigation. This paper identifies the currently available public datasets for smart home device classification and highlights their limitations. These limitations encouraged us to develop a new, large-scale network traffic flow dataset for AI-Based smart home device classification dataset comprising more than 200 million data points stemming from 105 different IoT and non-IoT devices. This dataset is now publicly available to the research community, and in this paper we present and describe its properties. Furthermore, we evaluated the effectiveness of different Machine Learning algorithms in classifying these devices. Our results indicate that the Random Forest algorithm achieves the highest accuracy at 0.906 with recall, precision, and F1 scores of 0.877, 0.901, and 0.887, respectively. Finally, we investigated the importance of the features and found that only 12 features are largely responsible for the observed levels of accuracy.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111041"},"PeriodicalIF":6.7,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738624","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

Public–private collaborations in humanitarian relief supplies: Incentive reserve contracts

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-24 DOI: 10.1016/j.cie.2025.111031

Yijing Cao , Jun Tian , Kai Huang

{"title":"Public–private collaborations in humanitarian relief supplies: Incentive reserve contracts","authors":"Yijing Cao , Jun Tian , Kai Huang","doi":"10.1016/j.cie.2025.111031","DOIUrl":"10.1016/j.cie.2025.111031","url":null,"abstract":"<div><div>Collaboration between nonprofit organizations (NPOs) and enterprises plays a crucial role in disaster preparedness. However, the pressures of high risk, high cost, and uncertainty can deter enterprises from maintaining strategic reserves before a disaster, potentially leading to inefficiencies in private enterprise participation in disaster relief. This study develops incentive reserve contracts enhance partnerships between NPOs and enterprise and secure humanitarian supplies. We evaluate two levers widely used by NPOs, physical procurement reserves and incentive coefficient, which jointly influence enterprises’ autonomous production capacity reserves. Importantly, simultaneous reserve and priority reserve are different. Furthermore, disasters often trigger price fluctuations in spot markets, complicating temporary procurement for unmet pre-disaster demands. We focus on the actual demand and market variations for different supplies to design differentiated reserves and incentives. Our findings indicate that incentive contracts are more flexible and cost-effective than advance payments for the same reserves, particularly when NPOs prioritize reserves. We further extend the model to consider corporate social responsibility, probability of emergencies, and different distribution functions of demand to examine the generality and applicability of the proposed approach, which is also verified by numerical experiments. In summary, this study provides better guidance for relief supply chain players dealing with various supplies and disaster environments, increases corporate engagement, and improves the overall efficiency of relief supply reservation.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111031"},"PeriodicalIF":6.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697371","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

Harnessing heterogeneous graph neural networks for Dynamic Job-Shop Scheduling Problem solutions

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-24 DOI: 10.1016/j.cie.2025.111060

Chien-Liang Liu , Po-Hao Weng , Chun-Jan Tseng

{"title":"Harnessing heterogeneous graph neural networks for Dynamic Job-Shop Scheduling Problem solutions","authors":"Chien-Liang Liu , Po-Hao Weng , Chun-Jan Tseng","doi":"10.1016/j.cie.2025.111060","DOIUrl":"10.1016/j.cie.2025.111060","url":null,"abstract":"<div><div>Manufacturing firms increasingly face the challenge of managing production complexity in the face of global competition and evolving customer demands. A critical component for maintaining efficiency and profitability in such an environment is the ability to solve the Job-Shop Scheduling Problem (JSSP) effectively. Traditional methods often fail in dynamic manufacturing settings, where unpredictability and the need for real-time adaptability can render static approaches obsolete. This study introduces a novel framework that uses Deep Reinforcement Learning (DRL) to address these limitations and navigate the intricacies of dynamic JSSP. By integrating heterogeneous graph neural networks (HGNNs) with DRL, we develop a model that not only captures the complex interconnections inherent in JSSP, but also dynamically adapts to the evolving nature of real-world manufacturing systems. Our proposed model is size-agnostic, meaning that it can deal with JSSPs with variable problem sizes. In addition, we introduce a new training method called Bootstrap Curriculum Learning (BCL) that enhances the model’s resilience and adaptability by training it in stages, progressively introducing the model to more challenging scheduling problem cases. The performance of the proposed model, evaluated against public benchmarks and synthetic datasets, shows superior performance and generalizability, offering a robust solution to dynamic scheduling challenges in smart manufacturing.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111060"},"PeriodicalIF":6.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715648","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

Coordination of the supply chain with quality improvement and customer returns

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-22 DOI: 10.1016/j.cie.2025.111057

Xinghao Yan

{"title":"Coordination of the supply chain with quality improvement and customer returns","authors":"Xinghao Yan","doi":"10.1016/j.cie.2025.111057","DOIUrl":"10.1016/j.cie.2025.111057","url":null,"abstract":"<div><div>Customer returns are a common issue that significantly impacts firms’ profits, regardless of product quality. To address this, firms can implement strategies like the supplier’s quality improvement and the retailer’s return policy. Additionally, contracts such as buy-back agreements can help distribute the costs of returns between the supplier and retailer. This study employs game theory to analyze how these strategies are formed at equilibrium and how they affect supply chain performance. We also explore whether buy-back contracts and other popular contracts, such as revenue-sharing and sales-target contracts, can coordinate these strategies effectively. Our findings reveal that a decentralized structure discourages the supplier’s quality improvement efforts but does not discourage the retailer’s return policy initiative. Coordination requires differentiating buy-back items based on their reasons, such as quality issues, customer preferences, or leftover stock. While returns due to customer preference should be excluded from buy-back contracts, items returned due to quality or leftovers should be included. Furthermore, the sales rebate contract proves effective in achieving coordination, while the revenue-sharing contract does not. Numerical examples indicate that both the revenue-sharing parameter and the buy-back price for returns due to customer preferences negatively impact supply chain profits. However, buy-back prices for quality returns, leftover units, and sales rebates can potentially enhance overall supply chain profitability.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111057"},"PeriodicalIF":6.7,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715649","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

Integrated optimization of timetabling and berthing for dual-source trolleybus routes along corridors

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-22 DOI: 10.1016/j.cie.2025.111066

Baoyu Hu , Cheng Gao , Wei Gao

{"title":"Integrated optimization of timetabling and berthing for dual-source trolleybus routes along corridors","authors":"Baoyu Hu , Cheng Gao , Wei Gao","doi":"10.1016/j.cie.2025.111066","DOIUrl":"10.1016/j.cie.2025.111066","url":null,"abstract":"<div><div>An integrated optimization approach for timetable and berth allocation has been proposed to address congestion issues at transportation nodes in common-route corridors for dual-source trolleybus systems. The study integrates travel times and the uncertainty of passenger demand to establish a bi-objective mixed-integer optimization model for minimizing the fleet sizes and required number of berths at common stations. By utilizing a Monte Carlo simulation to obtain the expected values of the fleet size and number of berths during actual route operations, the model can generate robust timetables and determine the number of berths at the common stations. The solving algorithm comprises a multi-objective particle swarm optimization with random weight variations. The results from a case study on four dual-source trolleybus routes in Beijing demonstrate that the model reduces the fleet size by 7.78% and number of berths at common stations by 11.11%. Consequently, this model can effectively reduce the long-term operational costs of bus companies and minimize the impacts of route operations on the road network.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111066"},"PeriodicalIF":6.7,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715651","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

Drone-assisted delivery optimization: Balancing time and cost with multiple truck routes for efficient service

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-22 DOI: 10.1016/j.cie.2025.111061

Shalabh Singh

引用次数: 0

Accelerated acceptance sampling plan for degraded products based on inverse Gaussian process considering the acceleration factor uncertainty

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-22 DOI: 10.1016/j.cie.2025.111052

Huiling Zheng , Jun Yang , Yu Zhao

{"title":"Accelerated acceptance sampling plan for degraded products based on inverse Gaussian process considering the acceleration factor uncertainty","authors":"Huiling Zheng , Jun Yang , Yu Zhao","doi":"10.1016/j.cie.2025.111052","DOIUrl":"10.1016/j.cie.2025.111052","url":null,"abstract":"<div><div>Acceptance sampling plan based on accelerated degradation tests, denoted as ADASP, is widely employed to verify the reliability of degraded products, including risk analysis, sampling plan design, and decision-making criterion determination. Most existing research focuses on identifying the optimal accelerated degradation test to improve the efficiency of ADASP, but often overlooks the differing objectives of producers and consumers regarding the acceptance index, which may result in the test plan failing to effectively meet their needs. To address this, based on the inverse Gaussian process, we propose a comprehensive accelerated degradation sampling plan by optimizing the parameter estimation accuracy while protecting their interests. Beyond the product quality risk, the acceleration factor (AF) uncertainty introduces additional risk to ADASP. Current studies primarily tackle AF uncertainty using probability distribution or interval. However, obtaining AF’s distribution is challenging, especially with limited prior knowledge and complex models. Therefore, apply the generalized pivotal quantity to derive a confidence interval of AF, and effectively manage this uncertainty-driven risk using significance level. Subsequently, a detailed decision-making criterion is derived by solving the risk constraint equations for both parties. Finally, simulation studies and case applications on springs are conducted to demonstrate the effectiveness of the proposed method.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111052"},"PeriodicalIF":6.7,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697372","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

How does dual-credit policy regulate competitive fuel vehicle and new energy vehicle manufacturers? based on operational decision analysis under multiple scenarios

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-22 DOI: 10.1016/j.cie.2025.111076

Junchong Pu , Weide Chun

{"title":"How does dual-credit policy regulate competitive fuel vehicle and new energy vehicle manufacturers? based on operational decision analysis under multiple scenarios","authors":"Junchong Pu , Weide Chun","doi":"10.1016/j.cie.2025.111076","DOIUrl":"10.1016/j.cie.2025.111076","url":null,"abstract":"<div><div>This article investigates the remarkable impacts of the dual-credit policy (DCP) on fuel vehicle (FV) and new energy vehicle (NEV) automakers, and considers the competition for emission reduction between FVs and NEVs. We apply the game-theoretic approach to design four scenarios, i.e., no DCP, DCP to regulate NEV automakers, DCP to regulate FV automakers, and DCP to regulate dual automakers. The study reveals that increasing the credit trading price reduces the emission reduction level for FVs but not for NEVs. When the DCP regulates NEV automakers, the credit trading price positively correlates with the automaker’s profit. An increase in each NEV credit boosts the emission reduction level of NEVs and automakers’ profits. Conversely, an increase in the NEV credit ratio lowers the emission reduction level of FVs. The higher the credit trading price, each NEV credit and NEV credit ratio contribute to reducing the total carbon emission level. Meanwhile, the total carbon emission level is the lowest in the scenario of DCP regulating dual automakers, but the automakers’ profits will suffer some losses. Also, the scenario of DCP regulating NEV automakers to achieve the highest profits will result in a higher carbon emission level. Moreover, the main contribution of this study is to identify the business performance of DCP regulating single or dual automakers, while simultaneously pointing out the effective choices for DCP to promote the green operations of competing automakers. Our results suggest some novel management recommendations for automakers and governments that can contribute to enhancing the sustainability of the automotive industry.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111076"},"PeriodicalIF":6.7,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143734746","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

Multi-objective dynamic feedback algorithm for solving the multi-drop three-dimensional multiple bin-size bin packing problem

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-03-21 DOI: 10.1016/j.cie.2025.111059

Yi Liu, Xiaoyun Jiang

{"title":"Multi-objective dynamic feedback algorithm for solving the multi-drop three-dimensional multiple bin-size bin packing problem","authors":"Yi Liu, Xiaoyun Jiang","doi":"10.1016/j.cie.2025.111059","DOIUrl":"10.1016/j.cie.2025.111059","url":null,"abstract":"<div><div>Three-dimensional multiple bin-size bin packing problem (3D-MBSBPP) is a crucial component of logistics and transportation systems. Prior studies focus on 3D-MBSBPP in cases where unloading is not considered. However, as the variety of vehicle types and the number of customers’ cargo increase, it not only reduces the efficiency of cargo loading and unloading but also increases the diversified needs of companies. To address these difficulties, more efficient methods are imperatively required. In this study, we construct a novel model for the multi-drop 3D-MBSBPP, which incorporates three objectives: maximizing vehicle space utilization rate, minimizing vehicle usage costs and spatial blockage index, while considering some practical constraints. Given the high complexity of this model, we propose a novel multi-objective dynamic feedback algorithm to solve it, which consists of three stages. Among them, Stage 1 focuses on optimizing the placement relationship between cargoes with different unloading sequences; Stage 2 dynamically adjusts and optimizes the vehicle types; and Stage 3 further optimizes the quality of the solution. More importantly, the proposed algorithm helps decision makers with the trade-off between multiple objectives. We demonstrate the effectiveness of the proposed algorithm through comparative experiments on benchmark instances and apply it to solve muti-drop 3D-MBSBPP. The results indicate that based on generating smaller spatial blockage index, the proposed algorithm can improve the average vehicle space utilization rate and reduce the average vehicle usage costs. This demonstrates the superiority of the proposed algorithm in solving the multi-drop 3D-MBSBPP.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111059"},"PeriodicalIF":6.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715650","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