Computers & Industrial Engineering最新文献_第9页

Solving multi-objective energy-saving flexible job shop scheduling problem by hybrid search genetic algorithm

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110829

Linyuan Hao, Zhiyuan Zou, Xu Liang

{"title":"Solving multi-objective energy-saving flexible job shop scheduling problem by hybrid search genetic algorithm","authors":"Linyuan Hao, Zhiyuan Zou, Xu Liang","doi":"10.1016/j.cie.2024.110829","DOIUrl":"10.1016/j.cie.2024.110829","url":null,"abstract":"<div><div>For the issue of energy consumption in the multi-objective flexible job shop scheduling problem (MOFJSP), balancing machine load is significant for enhancing environmental sustainability and cost efficiency in intelligent manufacturing. Most studies overlook the critical role of machine load in energy consumption. Therefore, this paper establishes a multi-objective energy-saving flexible job shop scheduling model with the objectives of minimizing the maximum and total machine load, makespan, then proposes a hybrid search genetic algorithm (HSGA) to solve this problem. Firstly, for enhancing population diversity, this paper proposes a cluster-based initial solution selection strategy, preventing the issue of limited search range caused by high similarity among initial solutions. Secondly, to broaden the search scope for multi-objective optimal solutions, this paper proposes a population selection strategy that considers individual neighborhood density and designed multiple neighborhood operators for variable neighborhood search (VNS). Finally, this paper proposes an adaptive strategy to dynamically adjust crossover and mutation probabilities for genetic operators, achieving a balance between global and local search. Experimental results show that the HSGA exhibits superior performance.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110829"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143179710","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

Run orders in factorial designs using the assignment–expansion method

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110844

Romario A. Conto López , Alexander A. Correa Espinal , Olga C. Úsuga Manco , Pablo A. Maya Duque

引用次数: 0

Optimisation of port investment strategies considering uncertain cargo demand and environmental pollutions

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110788

Bo Lu , Rifeng Luo , Xin Wu , Huipo Wang

{"title":"Optimisation of port investment strategies considering uncertain cargo demand and environmental pollutions","authors":"Bo Lu , Rifeng Luo , Xin Wu , Huipo Wang","doi":"10.1016/j.cie.2024.110788","DOIUrl":"10.1016/j.cie.2024.110788","url":null,"abstract":"<div><div>Port investment is assuming a critical role in contemporary maritime economics, attributable to the escalating demands for enhancing port efficiency and the growing awareness of environmental issues. Currently, numerous ports are operating at full capacity to manage incoming cargoes. Investing in port infrastructure holds the potential to enhance overall port productivity; nevertheless, such investments necessitate substantial financial resources and sufficient time, may encounter limitations due to environmental regulations, and are subject to risks stemming from uncertain demand. Existing investment analysis methods have been utilized to evaluate the impact of uncertainty on port investments, yet they tend to be overly theoretical or lack flexibility in decision-making. In light of these limitations, our study aims to explore a novel approach to optimize port investment strategies considering uncertain cargo demand and environmental concerns, through the development of a multi-stage stochastic dynamic programming model. This model places emphasis on investment choices related to expanding berth capacity, integrating environmental pollution constraints and financial limitations, all while accounting for demand uncertainties. Ultimately, our proposed methodology demonstrates improved analytical capabilities in addressing uncertainty and environmental pollution, as exemplified in a case study.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110788"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180891","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 deep reinforcement learning method based on a multiexpert graph neural network for flexible job shop scheduling 基于多专家图神经网络的深度强化学习方法，用于灵活的作业车间调度

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110768

Dailin Huang, Hong Zhao, Weiquan Tian, Kangping Chen

{"title":"A deep reinforcement learning method based on a multiexpert graph neural network for flexible job shop scheduling","authors":"Dailin Huang, Hong Zhao, Weiquan Tian, Kangping Chen","doi":"10.1016/j.cie.2024.110768","DOIUrl":"10.1016/j.cie.2024.110768","url":null,"abstract":"<div><div>When addressing flexible job shop scheduling problems (JSPs) via deep reinforcement learning (DRL), disjunctive graphs are commonly selected as the state observations of the agents. The previously developed methods primarily utilize graph neural networks (GNNs) to extract information from disjunctive graphs. However, as the instance scale increases, agents struggle to handle states with varying distributions, leading to reward confusion. To overcome this issue, inspired by the large-scale ’mixture-of-experts (MoE)’ model, we propose a novel module, i.e., a multiexpert GNN (ME-GNN), which integrates several approaches through a gating mechanism. Furthermore, the expert systems within the module facilitate lossless information propagation, providing robust support for solving complex cases. The experimental results demonstrate the effectiveness of our method. On synthetic datasets, our approach reduces the required makespan by 1.19%, and on classic datasets, it achieves a reduction of 1.34%. The multiple experts contained in the ME-GNN module enhance the overall flexibility of the system, effectively shortening the makespan.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110768"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181805","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 framework to define, design and construct digital twins in the mining industry 采矿业数字双胞胎的定义、设计和构建框架

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110805

Luke van Eyk, P. Stephan Heyns

{"title":"A framework to define, design and construct digital twins in the mining industry","authors":"Luke van Eyk, P. Stephan Heyns","doi":"10.1016/j.cie.2024.110805","DOIUrl":"10.1016/j.cie.2024.110805","url":null,"abstract":"<div><div>The mining industry is set to increasingly use technological innovations surrounding digitalisation, particularly in the context of the fourth industrial revolution, to address current productivity challenges and safety concerns. Digital twins serve as an enabling technology for many digitalisation-based technological innovations. However, there is currently a lack of a comprehensive understanding of the digital twin concept within the mining industry. This paper presents a framework customised to mining which delineates various dimensions, model types and properties associated with a digital twin. The framework establishes a shared understanding of the concept, serving as a blueprint for the development of future digital twin works in the mining industry. The framework is enriched by accompanying model selection tools which could aid new users in developing digital twins within the proposed framework. Two case studies depicting existing mining digital twins are presented and deconstructed within the proposed framework. These case studies illustrate the framework’s ability to effectively identify various digital twin types, instilling confidence in the framework’s ability to thoroughly deconstruct existing works whilst simultaneously serving as an effective tool to construct future digital twins.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110805"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181742","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

A novel multi-stage precision reliability assessment method for mechanical system by Bayesian fusion 贝叶斯融合的新型机械系统多阶段精密可靠性评估方法

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110744

Xiaogang Zhang , Wei Chen , Hongwei Wang , Yulong Li , Zhongyuan Zhao , Weixi Wang , Jin Zhang

{"title":"A novel multi-stage precision reliability assessment method for mechanical system by Bayesian fusion","authors":"Xiaogang Zhang , Wei Chen , Hongwei Wang , Yulong Li , Zhongyuan Zhao , Weixi Wang , Jin Zhang","doi":"10.1016/j.cie.2024.110744","DOIUrl":"10.1016/j.cie.2024.110744","url":null,"abstract":"<div><div>Precision reliability is crucial for evaluating mechanical system performance. However, limited data makes reliability assessment challenging due to difficult data collection and small sample sizes. Currently, little research has focused on using initial theoretical models as prior information for reliability assessment. This paper proposes a multi-stage precision reliability assessment method for a mechanical system by Bayesian fusion, which can effectively integrate design phase models with usage phase data under limited data conditions to carry out reliability assessment. First, the mechanical system is divided into <em>meta</em>-action units for precision modeling during the design phase. Then, an initial theoretical precision model is developed by incorporating operational error sources. Next, initial theoretical precision model is used to fit the Wiener process-driven model as Bayesian prior information, and reliability assessment is evaluated under different distribution assumptions for both the prior information and experimental data. This approach combines the prior advantages of the theoretical model with the data processing ability of the data-driven model under no prior data and small sample sizes, improving assessment precision and interpretability. Finally, a case study on a machine tool rotary table system validates the effectiveness of this method.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110744"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181801","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 optimization of work package scheme problem to minimize project carbon emissions and cost 多目标优化工作包方案问题，最大限度减少项目碳排放和成本

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110831

Yaning Zhang , Xiao Li , Yue Teng , Geoffrey Q.P. Shen , Sijun Bai

{"title":"Multi-objective optimization of work package scheme problem to minimize project carbon emissions and cost","authors":"Yaning Zhang , Xiao Li , Yue Teng , Geoffrey Q.P. Shen , Sijun Bai","doi":"10.1016/j.cie.2024.110831","DOIUrl":"10.1016/j.cie.2024.110831","url":null,"abstract":"<div><div>The construction industry accounts for around 30% of global energy consumption and 33% of CO<sub>2</sub> emissions. For the carbon neutrality initiative, reducing carbon emissions from construction projects become a critical objective for project success. However, a dilemma arises in balancing carbon emissions and project cost, particularly during the work package-based project planning phase. To address this issue, this article presents a novel multi-objective optimization model for the work package scheme problem, aimed at minimizing both project carbon emissions and cost. Multi-objective Evolutionary Algorithms (EAs) are developed to solve the model. Firstly, a multi-objective Mixed-Integer Programming (MIP) model is developed to establish the functional relation between work package attributes (duration and work content) and optimization objectives (carbon emissions and cost). Secondly, two multi-objective optimization EAs, NSGA-II and SPEA2, are developed to obtain the Pareto frontier. The experimental results indicate that NSGA-II and SPEA2 exhibit superior trade-off capabilities compared to the Gurobi and the state-of-the-art heuristic algorithm. Compared to Gurobi, the proposed EAs achieve an approximately 68% reduction in carbon emissions, accompanied by about an 11% cost increase. Compared to the heuristic algorithm, the EAs achieve around 10% reductions in carbon emissions with an approximately 5% cost increase. Additionally, sensitivity analysis conducted on a project instance dataset demonstrates the robustness of the proposed model and algorithms. This article paves the way for achieving low-carbon and sustainable construction project management in the context of carbon neutrality.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110831"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181828","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

The backroom assignment problem for in-store order fulfillment

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2025.110912

Sebastian Koehler, Felicia Theilacker

{"title":"The backroom assignment problem for in-store order fulfillment","authors":"Sebastian Koehler, Felicia Theilacker","doi":"10.1016/j.cie.2025.110912","DOIUrl":"10.1016/j.cie.2025.110912","url":null,"abstract":"<div><div>Efficient in-store fulfillment is essential for today’s omnichannel services, as retailers are taking on tasks previously performed by customers themselves while shopping. This paper introduces a novel backroom assignment problem for omnichannel stores, aiming to optimize the allocation of articles to a forward pick area exclusively dedicated to online demand. We present both random and dedicated storage policy formulations for the backroom assignment problem (<em>BAP</em>), determining the allocation of articles, their quantities to the forward pick area, and the selection of storage units. To achieve a balance between computational efficiency and solution quality, we introduce two decomposition methods. We evaluate the impact of our proposed BAP formulations using real data from a drug store chain and quantify the effects of an increasing online demand ratio and different forward pick area sizes on the in-store logistical effort. Results from a three-store use case demonstrate that backroom assignments can substantially reduce in-store logistical effort compared to a scenario without backroom usage, especially as demand shifts increasingly towards the online channel. The results also show that our decomposition methods are effective in handling problem instances in most cases, equipping retailers to evaluate the influence of backroom assignments. We conclude with managerial implications and explore future research opportunities.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"202 ","pages":"Article 110912"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446044","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

OptiPower AI: A deep reinforcement learning framework for intelligent cluster energy management and V2X optimization in industrial applications OptiPower AI：用于工业应用中智能集群能源管理和 V2X 优化的深度强化学习框架

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110762

Sami Ben Slama

{"title":"OptiPower AI: A deep reinforcement learning framework for intelligent cluster energy management and V2X optimization in industrial applications","authors":"Sami Ben Slama","doi":"10.1016/j.cie.2024.110762","DOIUrl":"10.1016/j.cie.2024.110762","url":null,"abstract":"<div><div>Peer-to-peer (P2P) energy trading has emerged as a practical solution for efficient energy management, particularly with the rising affordability of renewable energy and electric vehicles (EVs). This paper introduces the Optimal Power Artificial Intelligence (OptiPower AI) algorithm, a significant advancement in Intelligent Cluster Energy Management (ICEM). OptiPower AI combines Double Deep Q-Network (DDQN)-based Deep Reinforcement Learning (DRL), Vehicle-to-Everything (V2X) technology, and P2P energy trading to optimize energy distribution among clusters of prosumers and consumers. The system efficiently manages Renewable Energy Sources (RES) and EVs, achieving a 19.18% reduction in energy costs and a 50.02% decrease in average energy prices across V2X and P2P scenarios.</div><div>OptiPower AI uses DRL to dynamically allocate energy and implement real-time pricing, enhancing energy efficiency and user satisfaction. Simulations based on meteorological data from Tunisia validate the system’s ability to improve thermal comfort, increase energy savings, and lower costs. The model’s parameters enable accurate forecasting and allocation, showcasing OptiPower AI’s reliability in variable demand conditions. This work advances the application of DRL in decentralized, sustainable P2P energy management systems for industrial clusters, addressing critical challenges in energy distribution, efficiency, and cost reduction.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110762"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181740","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

Decision-making framework for sustainability-related supply chain risk management 与可持续性相关的供应链风险管理的决策框架

IF 6.7 1区工程技术

Computers & Industrial Engineering Pub Date : 2025-02-01 DOI: 10.1016/j.cie.2024.110825

Ming-Fu Hsu

{"title":"Decision-making framework for sustainability-related supply chain risk management","authors":"Ming-Fu Hsu","doi":"10.1016/j.cie.2024.110825","DOIUrl":"10.1016/j.cie.2024.110825","url":null,"abstract":"<div><div>This research introduces practical insight into sustainable supply chain management (SCM), by viewing it as a risk management procedure. Most sustainability-related messages are transmitted via accounting narratives, but digesting enormous narratives in a timely manner is not a non-trivial task. To combat this, this study sets up an advanced decision-making framework with objectivity to point out those messages related to sustainability issues and then adopts a statistical-based sentimental dictionary to quantify the messages. In so doing, a manager’s/corporate’s inclination toward each sustainability-related issue can be inferred/conjectured. It is widely acknowledged that a firm with good performance normally has efficient supply chains (SCs) and appropriate risk response strategies. In contrast to well-examined studies on the relationship between financial performance and efficient SCs, works on how and to what extent efficient SCs contribute to firm value from a financial market perspective are quite scarce. To fill the gap in the literature, the study takes two firm value drivers, “earn” (i.e., profitability) and “turn” (i.e., asset utilization), and evaluates on how they contribute to firm value. The results indicate that the semiconductor industry tends to be much more efficient in translating “earn” as opposed to “turn” into firm value. This study equips a framework with forecasting capability and introduces “what-if” scenario analysis to assist managers in formulating stepwise improvement strategies based on what success level they want to reach. The roles of managers are thus switched from preventively monitoring the past/present to proactively planning the future.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"200 ","pages":"Article 110825"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181751","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