Computers & Industrial Engineering最新文献_第10页

Sustainable environmental design using circular economy in the plastic manufacturing industry for decarbonization 可持续环境设计利用循环经济在塑料制造行业进行脱碳

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-16 DOI: 10.1016/j.cie.2025.111764

Yang Zhou , Qiutong Dong , HafizanMat Som , Jianhua Dai , Tiziana Ciano , Noreen Izza Arshad

Plastic waste is one of the most controversial environmental issues because of the poor recyclability and high carbon emissions of traditional plastic production systems. Traditional processes can be inefficient in sorting materials, consume high amounts of energy, and lack lifecycle integration for plastic products. This research proposes a Sustainable Environmental Design Circular Economy (SEDC) framework that overcomes the limitation and provides an entire end-to-end solution from designing the product to recycling processes. The proposed method applies a Novel Convolutional Neural Network- Naive Gradient Boost- Sandpiper Optimization (CNN-NB-SPO) algorithm to determine high-level features that improve the recyclability and modularity of products. SPO is used in refinement stages to improve the decisions and consequently, energy efficiency with regard to recyclability potential is improved at the design stage. Novel Generative Adversarial Network- Artificial Neural Network (GAN-ANNs), improve reverse logistics so that supply chain operations become efficient, and the recycling waste of cyclicality decreases. The framework is applied to the Kaggle Plastic Waste dataset, in which its effectiveness in improving classification accuracy, material recovery, and reduction of carbon emissions is demonstrated. Basic performance parameters—recyclability rate, energy consumption, CO2 emissions, and accuracy—confirm that the proposed model significantly outperforms traditional approaches to plastic production manufacturing for the advancement of the goals of a circular economy. An integrated, data-driven approach from SEDC provides a scalable solution toward sustainable plastic production and waste management for the support of global decarbonization efforts.

由于传统塑料生产系统的可回收性差和高碳排放，塑料垃圾是最具争议的环境问题之一。传统流程在分类材料方面效率低下，消耗大量能源，并且缺乏塑料产品的生命周期整合。本研究提出了一个可持续环境设计循环经济（SEDC）框架，克服了这一限制，并提供了从产品设计到回收过程的完整端到端解决方案。该方法采用新颖的卷积神经网络-朴素梯度增强-矶鹞优化（CNN-NB-SPO）算法来确定提高产品可回收性和模块化的高级特征。在改进阶段使用SPO来改进决策，因此，在设计阶段提高了关于可回收潜力的能源效率。新型生成对抗网络——人工神经网络（GAN-ANNs），改善逆向物流，使供应链运作变得高效，减少循环废品的回收。将该框架应用于Kaggle塑料废物数据集，证明了其在提高分类精度、材料回收率和减少碳排放方面的有效性。基本性能参数-回收率，能源消耗，二氧化碳排放和准确性-证实了所提出的模型显着优于传统的塑料生产制造方法，以实现循环经济的目标。SEDC的综合数据驱动方法为可持续塑料生产和废物管理提供了可扩展的解决方案，以支持全球脱碳工作。

{"title":"Sustainable environmental design using circular economy in the plastic manufacturing industry for decarbonization","authors":"Yang Zhou , Qiutong Dong , HafizanMat Som , Jianhua Dai , Tiziana Ciano , Noreen Izza Arshad","doi":"10.1016/j.cie.2025.111764","DOIUrl":"10.1016/j.cie.2025.111764","url":null,"abstract":"<div><div>Plastic waste is one of the most controversial environmental issues because of the poor recyclability and high carbon emissions of traditional plastic production systems. Traditional processes can be inefficient in sorting materials, consume high amounts of energy, and lack lifecycle integration for plastic products. This research proposes a Sustainable Environmental Design Circular Economy (SEDC) framework that overcomes the limitation and provides an entire end-to-end solution from designing the product to recycling processes. The proposed method applies a Novel Convolutional Neural Network- Naive Gradient Boost- Sandpiper Optimization (CNN-NB-SPO) algorithm to determine high-level features that improve the recyclability and modularity of products. SPO is used in refinement stages to improve the decisions and consequently, energy efficiency with regard to recyclability potential is improved at the design stage. Novel Generative Adversarial Network- Artificial Neural Network (GAN-ANNs), improve reverse logistics so that supply chain operations become efficient, and the recycling waste of cyclicality decreases. The framework is applied to the Kaggle Plastic Waste dataset, in which its effectiveness in improving classification accuracy, material recovery, and reduction of carbon emissions is demonstrated. Basic performance parameters—recyclability rate, energy consumption, CO2 emissions, and accuracy—confirm that the proposed model significantly outperforms traditional approaches to plastic production manufacturing for the advancement of the goals of a circular economy. An integrated, data-driven approach from SEDC provides a scalable solution toward sustainable plastic production and waste management for the support of global decarbonization efforts.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111764"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841684","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

Accounting for Within-Part Variability in Measurement System Analysis 测量系统分析中部分内变异性的核算

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-23 DOI: 10.1016/j.cie.2025.111766

Mahmut Onur Karaman , Murat Caner Testik , Murat Kulahci , Stefan Steiner , Yusuf Emre Arslan

Measurement system analysis is often performed in industry to check the quality of a measurement system. When assessing the capability of measurement systems, two key components of measurement error are commonly considered: repeatability and reproducibility. Experimental designs are generally used to quantify these error components, and the resulting investigation is referred to as a Gauge Repeatability and Reproducibility (Gauge R&R) study. Yet another possible source of error that is often overlooked is within-part variability, which can be a significant source of variability in the measurements of parts. Investigation of this error source requires modifications to both the experimental setup and the effects model for quantifying the components of variability. In this study, we analyze the effects of various measurement assessment plans on the Gauge R&R metric when within-part variation is present. Alternative measurement assessment plans and their ANOVA models are proposed. As common geometric forms in manufacturing processes, cylindrical and rectangular prism shaped parts are considered. Using computer simulations of parts having within-part variability, it is shown that neglecting within-part variation can cause misleading conclusions from an MSA study, and as a consequence, practitioners may not recognize the actual performance of their measurement system. Our conclusions are justified by a real world case study for a cylindrical part.

测量系统分析在工业中经常用于检查测量系统的质量。在评估测量系统的能力时，通常要考虑测量误差的两个关键组成部分：可重复性和再现性。实验设计通常用于量化这些误差成分，由此产生的调查被称为量规重复性和再现性（Gauge R&；R）研究。然而，另一个经常被忽视的可能的误差来源是部件内部的可变性，这可能是部件测量中可变性的一个重要来源。对这种误差源的研究需要修改实验设置和用于量化变异成分的影响模型。在本研究中，我们分析了当存在部分内变化时，各种测量评估计划对量规R&；R度量的影响。提出了备选测量评估方案及其方差分析模型。圆柱形和矩形棱柱形零件是制造过程中常见的几何形状。使用具有部分内变异性的部件的计算机模拟，表明忽略部分内变异性可能导致从MSA研究中得出误导性结论，因此，从业者可能无法识别其测量系统的实际性能。我们的结论是由一个圆柱形零件的实际案例研究证明。

{"title":"Accounting for Within-Part Variability in Measurement System Analysis","authors":"Mahmut Onur Karaman , Murat Caner Testik , Murat Kulahci , Stefan Steiner , Yusuf Emre Arslan","doi":"10.1016/j.cie.2025.111766","DOIUrl":"10.1016/j.cie.2025.111766","url":null,"abstract":"<div><div>Measurement system analysis is often performed in industry to check the quality of a measurement system. When assessing the capability of measurement systems, two key components of measurement error are commonly considered: repeatability and reproducibility. Experimental designs are generally used to quantify these error components, and the resulting investigation is referred to as a Gauge Repeatability and Reproducibility (Gauge R&R) study. Yet another possible source of error that is often overlooked is within-part variability, which can be a significant source of variability in the measurements of parts. Investigation of this error source requires modifications to both the experimental setup and the effects model for quantifying the components of variability. In this study, we analyze the effects of various measurement assessment plans on the Gauge R&R metric when within-part variation is present. Alternative measurement assessment plans and their ANOVA models are proposed. As common geometric forms in manufacturing processes, cylindrical and rectangular prism shaped parts are considered. Using computer simulations of parts having within-part variability, it is shown that neglecting within-part variation can cause misleading conclusions from an MSA study, and as a consequence, practitioners may not recognize the actual performance of their measurement system. Our conclusions are justified by a real world case study for a cylindrical part.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111766"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841686","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

Online process monitoring under quality data scarcity: Self-starting truncated EWMA schemes for time between events 高质量数据稀缺下的在线过程监控：事件间隔时间的自启动截断EWMA方案

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-22 DOI: 10.1016/j.cie.2025.111777

FuPeng Xie , JingWei Liu , JiaCai Huang , YuXing Dai , Quan Sun , XueLong Hu , Philippe Castagliola

This study proposes one-sided self-starting truncated EWMA (SST-EWMA) control charts for effective high-quality process monitoring in situations where extensive in-control time-between-events (TBE) observations are unavailable. By constructing a pivot quantity and establishing variable mappings, a self-starting framework specifically tailored for Gamma distributed TBE observations is developed. The integration of a variable truncation mechanism into this framework further enhances sensitivity to small to moderate process shifts. To investigate the detection properties of the proposed schemes, simulation were conducted to examine the effects of the shape parameter

α

, the number of reference TBE observations

M

, and the smoothing parameter

λ

on the average time to signal (

ATS

). Based on the simulation results, guidelines are provided for achieving

ATS

performance comparable to that of the corresponding known-parameter schemes. Comparative analysis demonstrates that, although slightly inferior to the one-sided TEWMA TBE charts under known parameters, the proposed charts exhibit superior adaptability in scenarios with scarce TBE data, and also outperform the existing self-starting EWMA TBE chart, validating the effectiveness of the variable truncation mechanism. Finally, two case studies are presented to illustrate the practical implementation of the proposed control charts in industrial engineering applications.

本研究提出了单侧自启动截断EWMA （SST-EWMA）控制图，用于在无法获得大量控制时间间隔（TBE）观测的情况下进行有效的高质量过程监控。通过构造一个枢轴量和建立变量映射，开发了一个专门为Gamma分布TBE观测量身定制的自启动框架。将可变截断机制集成到该框架中，进一步提高了对小到中等过程移位的敏感性。为了研究所提方案的检测特性，通过仿真研究了形状参数α、参考TBE观测数M和平滑参数λ对平均到信号时间（ATS）的影响。根据仿真结果，给出了实现ATS性能与相应的已知参数方案相当的准则。对比分析表明，虽然在已知参数下，本文提出的图略逊于单侧的EWMA TBE图，但在TBE数据稀缺的场景下，该图表现出更强的适应性，也优于现有的自启动EWMA TBE图，验证了变量截断机制的有效性。最后，提出了两个案例来说明所提出的控制图在工业工程应用中的实际实现。

{"title":"Online process monitoring under quality data scarcity: Self-starting truncated EWMA schemes for time between events","authors":"FuPeng Xie , JingWei Liu , JiaCai Huang , YuXing Dai , Quan Sun , XueLong Hu , Philippe Castagliola","doi":"10.1016/j.cie.2025.111777","DOIUrl":"10.1016/j.cie.2025.111777","url":null,"abstract":"<div><div>This study proposes one-sided self-starting truncated EWMA (SST-EWMA) control charts for effective high-quality process monitoring in situations where extensive in-control time-between-events (TBE) observations are unavailable. By constructing a pivot quantity and establishing variable mappings, a self-starting framework specifically tailored for Gamma distributed TBE observations is developed. The integration of a variable truncation mechanism into this framework further enhances sensitivity to small to moderate process shifts. To investigate the detection properties of the proposed schemes, simulation were conducted to examine the effects of the shape parameter <span><math><mi>α</mi></math></span>, the number of reference TBE observations <span><math><mi>M</mi></math></span>, and the smoothing parameter <span><math><mi>λ</mi></math></span> on the average time to signal (<span><math><mi>ATS</mi></math></span>). Based on the simulation results, guidelines are provided for achieving <span><math><mi>ATS</mi></math></span> performance comparable to that of the corresponding known-parameter schemes. Comparative analysis demonstrates that, although slightly inferior to the one-sided TEWMA TBE charts under known parameters, the proposed charts exhibit superior adaptability in scenarios with scarce TBE data, and also outperform the existing self-starting EWMA TBE chart, validating the effectiveness of the variable truncation mechanism. Finally, two case studies are presented to illustrate the practical implementation of the proposed control charts in industrial engineering applications.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111777"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841685","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 collaborative operation-energy planning method for liquefied natural gas bunkering ports considering integrated electricity-gas microgrid 考虑电-气集成微电网的液化天然气加注港协同运行-能量规划方法

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-13 DOI: 10.1016/j.cie.2025.111742

Liping Zhang , Qingcheng Zeng , Chenrui Qu , Moacir Godinho Filho

The rapid growth of LNG-fueled and dual-fuel vessels is driving many green container ports to expand their services to include LNG bunkering. Meanwhile, these ports are establishing Integrated Electricity–LNG Microgrids (IELMs) that utilize LNG as a conversion energy source to mitigate renewable intermittency and enhance energy resilience. This evolution underscores the increasing importance of coordinated operation and energy planning in LNG bunkering ports. To address this challenge, this study develops a mixed-integer nonlinear programming (MINLP) model that captures the coupling between port operation and microgrid energy plan. The model jointly optimizes berth allocation, equipment assignment for both HFO- and LNG-powered vessels, and energy conversion and supply decisions within the IELM. Based on this formulation, a two-stage operation–energy planning framework (TWOEPF) is proposed, integrating a branch-and-price (BP) algorithm with the Gurobi solver to balance solution quality and computational efficiency. A heuristic greedy initialization, adaptive termination criteria, and tailing-off mitigation strategies are incorporated to enhance convergence performance. Numerical experiments demonstrate that the proposed framework outperforms traditional two-stage methods by delivering higher solution quality, while also exhibiting superior computational efficiency compared with the integrated framework. Moreover, the proposed BP-based approach consistently outperforms the ALNS-based approach within the TWOEPF. This advantage is particularly evident in practical-scale instances, where the average optimality gap remains at 10%–14%, confirming its robustness and computational superiority. Sensitivity analyses further show that IELMs significantly enhance both cost efficiency and emission reduction, offering valuable managerial insights for LNG bunkering port planning.

LNG燃料船和双燃料船的快速增长正在推动许多绿色集装箱港口扩大其服务，包括LNG加油。与此同时，这些港口正在建立综合电力-液化天然气微电网（ielm），利用液化天然气作为转换能源，以减轻可再生能源的间歇性，提高能源弹性。这一演变凸显了在液化天然气加注港协调运营和能源规划的重要性。为了解决这一挑战，本研究开发了一个混合整数非线性规划（MINLP）模型，该模型捕捉了港口运营与微电网能源计划之间的耦合。该模型共同优化了泊位分配、HFO和lng动力船舶的设备分配，以及IELM内的能量转换和供应决策。在此基础上，提出了一种两阶段运行-能源规划框架（TWOEPF），将分支-价格（BP）算法与Gurobi求解器相结合，以平衡求解质量和计算效率。采用启发式贪婪初始化、自适应终止准则和尾迹缓解策略来提高收敛性能。数值实验表明，该框架比传统的两阶段方法具有更高的解质量，同时与集成框架相比也具有更高的计算效率。此外，所提出的基于bp的方法在TWOEPF中始终优于基于als的方法。这种优势在实际规模的实例中尤为明显，其中平均最优性差距保持在10%-14%，证实了其鲁棒性和计算优势。敏感性分析进一步表明，ielm显著提高了成本效率和减排，为LNG加注港规划提供了有价值的管理见解。

{"title":"A collaborative operation-energy planning method for liquefied natural gas bunkering ports considering integrated electricity-gas microgrid","authors":"Liping Zhang , Qingcheng Zeng , Chenrui Qu , Moacir Godinho Filho","doi":"10.1016/j.cie.2025.111742","DOIUrl":"10.1016/j.cie.2025.111742","url":null,"abstract":"<div><div>The rapid growth of LNG-fueled and dual-fuel vessels is driving many green container ports to expand their services to include LNG bunkering. Meanwhile, these ports are establishing Integrated Electricity–LNG Microgrids (IELMs) that utilize LNG as a conversion energy source to mitigate renewable intermittency and enhance energy resilience. This evolution underscores the increasing importance of coordinated operation and energy planning in LNG bunkering ports. To address this challenge, this study develops a mixed-integer nonlinear programming (MINLP) model that captures the coupling between port operation and microgrid energy plan. The model jointly optimizes berth allocation, equipment assignment for both HFO- and LNG-powered vessels, and energy conversion and supply decisions within the IELM. Based on this formulation, a two-stage operation–energy planning framework (TWOEPF) is proposed, integrating a branch-and-price (BP) algorithm with the Gurobi solver to balance solution quality and computational efficiency. A heuristic greedy initialization, adaptive termination criteria, and tailing-off mitigation strategies are incorporated to enhance convergence performance. Numerical experiments demonstrate that the proposed framework outperforms traditional two-stage methods by delivering higher solution quality, while also exhibiting superior computational efficiency compared with the integrated framework. Moreover, the proposed BP-based approach consistently outperforms the ALNS-based approach within the TWOEPF. This advantage is particularly evident in practical-scale instances, where the average optimality gap remains at 10%–14%, confirming its robustness and computational superiority. Sensitivity analyses further show that IELMs significantly enhance both cost efficiency and emission reduction, offering valuable managerial insights for LNG bunkering port planning.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111742"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841613","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

Consensus reaching framework for maximum expert consensus with uncertain asymmetric Costs: A data-driven robust approach 具有不确定非对称成本的最大专家共识达成框架：数据驱动的稳健方法

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-26 DOI: 10.1016/j.cie.2025.111781

Qiuyu Yu , Liang Chang , Shaojian Qu , Ying Ji

The maximum expert consensus model (MECM) has emerged as a pivotal framework for group decision-making (GDM) under uncertainty. However, traditional MECM often neglects asymmetric adjustment costs, dynamic opinion evolution, and hybrid uncertainty structures. To overcome these deficiencies, this paper develops the MECM framework that integrates asymmetric costs, linear uncertainty distribution consensus thresholds, and hybrid uncertainty sets. A dynamic weight-driven adjustment mechanism is introduced to refine non-consensus opinions and improve convergence efficiency. Building upon this, a data-driven robust MECM is proposed, which employs historical data for quantifiable decision support. The proposed framework is empirically validated through a carbon quota negotiation case involving eight Chinese regions. Results confirm that the model effectively balances economic efficiency, consensus quality, and collective acceptability while maintaining robustness under uncertain conditions. Sensitivity and comparative analyses further demonstrate the flexibility and practical feasibility of the proposed framework relative to conventional consensus optimization models.

专家最大共识模型（MECM）已成为不确定条件下群体决策的关键框架。然而，传统的MECM往往忽略了不对称调整成本、动态意见演变和混合不确定性结构。为了克服这些不足，本文开发了集成不对称成本、线性不确定性分布共识阈值和混合不确定性集的MECM框架。引入动态权重驱动的调整机制，对非一致意见进行细化，提高收敛效率。在此基础上，提出了一种数据驱动的鲁棒MECM，该MECM利用历史数据提供可量化的决策支持。通过一个涉及中国8个地区的碳配额谈判案例，对所提出的框架进行了实证验证。结果证实，该模型有效地平衡了经济效率、共识质量和集体可接受性，同时在不确定条件下保持鲁棒性。灵敏度分析和对比分析进一步证明了该框架相对于传统共识优化模型的灵活性和实际可行性。

{"title":"Consensus reaching framework for maximum expert consensus with uncertain asymmetric Costs: A data-driven robust approach","authors":"Qiuyu Yu , Liang Chang , Shaojian Qu , Ying Ji","doi":"10.1016/j.cie.2025.111781","DOIUrl":"10.1016/j.cie.2025.111781","url":null,"abstract":"<div><div>The maximum expert consensus model (MECM) has emerged as a pivotal framework for group decision-making (GDM) under uncertainty. However, traditional MECM often neglects asymmetric adjustment costs, dynamic opinion evolution, and hybrid uncertainty structures. To overcome these deficiencies, this paper develops the MECM framework that integrates asymmetric costs, linear uncertainty distribution consensus thresholds, and hybrid uncertainty sets. A dynamic weight-driven adjustment mechanism is introduced to refine non-consensus opinions and improve convergence efficiency. Building upon this, a data-driven robust MECM is proposed, which employs historical data for quantifiable decision support. The proposed framework is empirically validated through a carbon quota negotiation case involving eight Chinese regions. Results confirm that the model effectively balances economic efficiency, consensus quality, and collective acceptability while maintaining robustness under uncertain conditions. Sensitivity and comparative analyses further demonstrate the flexibility and practical feasibility of the proposed framework relative to conventional consensus optimization models.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111781"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977756","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 metamodeling based simulation approach to investigate ambulance multi-period redeployment in emergency medical services 一种基于元模型的急救医疗服务中救护车多周期调配的仿真方法

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2026-01-04 DOI: 10.1016/j.cie.2026.111802

Lina Aboueljinane , Youness Frichi

Metamodeling based simulation (MBS) is an approach that is increasingly used in the simulation-based optimization literature. Its aim is to use a metamodel to find the relationship between the inputs and outputs of a simulation model, enabling the outputs to be predicted and optimized more rapidly than with the simulation model alone. MBS is an approach that, despite its interest, has not yet been widely used to study emergency medical services. The objective of this research is to propose an MBS approach for the multi-period redeployment problem of civil protection ambulances in the Fes-Meknes region (Morocco). For this purpose, a discrete event simulation model of this system associated with two designs of experiments (DOE) (i.e., Latin hypercube design (LHD) and random sampling) were used to generate two datasets with the number of ambulances of each type in each base for each period as inputs, and total coverage of the territory as output. The datasets were used to train and test four ensemble learning metamodels from the gradient boosting library (Gradient Boosting, XGBoost, CatBoost, and LightGBM) and to compare them with three other metamodels: feedforward neural network (FFNN), Random Forest (RF), and Support Vector Machine (SVR). Finally, the Elitist Genetic Algorithm (EGA) was used to optimize the predictions of the best-performing metamodels. The results showed a clear superiority of gradient boosting algorithms, with CatBoost achieving the highest accuracy (R² = 0.96, MAPE = 0.012, RMSE = 0.013 on Random sampling), significantly outperforming Random Forest (R² ≤ 0.67), FFNN (R² ≤ 0.64), and SVR (R² ≤ 0.52). In the optimization phase, although Random sampling provided better metamodeling metrics, LHD proved superior for optimization quality. The EGA associated with the CatBoost metamodel and LHD DOE achieved the highest performance, yielding a total coverage 10.1 % higher than the commercial OptQuest solver, while reducing computational time by a factor of 20.

基于元建模的仿真（MBS）是一种在基于仿真的优化文献中越来越多使用的方法。它的目的是使用元模型来找到仿真模型的输入和输出之间的关系，使输出能够比单独使用仿真模型更快地被预测和优化。MBS是一种方法，尽管它很有趣，但尚未广泛用于研究紧急医疗服务。本研究的目的是为菲斯-梅克内斯地区（摩洛哥）民防救护车的多期重新部署问题提出一种MBS方法。为此，使用该系统的离散事件模拟模型，结合两种实验设计（即拉丁超立方体设计（LHD）和随机抽样），生成两个数据集，其中每个基地在每个时期的每种类型的救护车数量作为输入，区域的总覆盖作为输出。这些数据集用于训练和测试来自梯度增强库的四个集成学习元模型（gradient boosting、XGBoost、CatBoost和LightGBM），并将它们与其他三个元模型（前馈神经网络（FFNN）、随机森林（RF）和支持向量机（SVR））进行比较。最后，利用精英遗传算法（EGA）对表现最佳的元模型进行预测优化。结果表明，梯度增强算法具有明显的优势，CatBoost在随机抽样上的准确率最高（R2 = 0.96, MAPE = 0.012, RMSE = 0.013），显著优于Random Forest （R2≤0.67）、FFNN （R2≤0.64）和SVR （R2≤0.52）。在优化阶段，尽管随机抽样提供了更好的元建模指标，但LHD被证明在优化质量方面更胜一筹。与CatBoost元模型和LHD DOE相关联的EGA实现了最高的性能，产生的总覆盖率比商用OptQuest求解器高10.1%，同时将计算时间减少了20倍。

{"title":"A metamodeling based simulation approach to investigate ambulance multi-period redeployment in emergency medical services","authors":"Lina Aboueljinane , Youness Frichi","doi":"10.1016/j.cie.2026.111802","DOIUrl":"10.1016/j.cie.2026.111802","url":null,"abstract":"<div><div>Metamodeling based simulation (MBS) is an approach that is increasingly used in the simulation-based optimization literature. Its aim is to use a metamodel to find the relationship between the inputs and outputs of a simulation model, enabling the outputs to be predicted and optimized more rapidly than with the simulation model alone. MBS is an approach that, despite its interest, has not yet been widely used to study emergency medical services. The objective of this research is to propose an MBS approach for the multi-period redeployment problem of civil protection ambulances in the Fes-Meknes region (Morocco). For this purpose, a discrete event simulation model of this system associated with two designs of experiments (DOE) (i.e., Latin hypercube design (LHD) and random sampling) were used to generate two datasets with the number of ambulances of each type in each base for each period as inputs, and total coverage of the territory as output. The datasets were used to train and test four ensemble learning metamodels from the gradient boosting library (Gradient Boosting, XGBoost, CatBoost, and LightGBM) and to compare them with three other metamodels: feedforward neural network (FFNN), Random Forest (RF), and Support Vector Machine (SVR). Finally, the Elitist Genetic Algorithm (EGA) was used to optimize the predictions of the best-performing metamodels. The results showed a clear superiority of gradient boosting algorithms, with CatBoost achieving the highest accuracy (R<sup>2</sup> = 0.96, MAPE = 0.012, RMSE = 0.013 on Random sampling), significantly outperforming Random Forest (R<sup>2</sup> ≤ 0.67), FFNN (R<sup>2</sup> ≤ 0.64), and SVR (R<sup>2</sup> ≤ 0.52). In the optimization phase, although Random sampling provided better metamodeling metrics, LHD proved superior for optimization quality. The EGA associated with the CatBoost metamodel and LHD DOE achieved the highest performance, yielding a total coverage 10.1 % higher than the commercial OptQuest solver, while reducing computational time by a factor of 20.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111802"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927269","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

Synthetical-consistency control and preference consensus handling in group best-worst method under incomplete intuitionistic multiplicative context 不完全直觉乘法环境下群体最佳-最差法的综合一致性控制与偏好共识处理

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2025-11-27 DOI: 10.1016/j.cie.2025.111707

Xiaoyun Lu , Yejun Xu , Zhong-lin Ye , Tong-Feng Li , Ze-Hui Chen

The Best-Worst Method (BWM), as a core analytical tool for tackling multi-criteria decision making (MCDM) challenges in artificial intelligence (AI), demonstrates remarkable practical efficacy at the analytical dimension of industrial engineering. However, existing BWMs are generally based on the assumption of complete preference information, and their consistency analysis framework focuses mainly on cardinal consistency of preference relations. In addition, particularly in the context of BWM, there is a lack of systematic research on consensus-reaching mechanisms for group decision making (GDM). The above problems seriously restrict the application and expansion of BWM. Intuitionistic multiplicative preference relations (IMPRs) demonstrate unique theoretical advantages in addressing imbalanced information representation within the field of artificial intelligence (AI). Given the above facts, this study develops an extended model of BWM under incomplete intuitionistic multiplicative context, exploring consensus reaching and synthetical consistency management. Firstly, this study constructs an optimization model by integrating intuitionistic multiplicative operations with enhanced consistency control to address the challenge of incomplete preference information. Secondly, dual consistency measures (ordinal consistency and cardinal consistency) are introduced, supplemented by corresponding optimization models, to ensure the transmission logic of alternatives ranking and the numerical stability of preference strength. Moreover, a dynamic consensus-reaching mechanism featuring synthetical consistency management and dynamic expert weight allocation is developed to enhance the acceptability of GDM outcomes within the expert group. Finally, the validity of the proposed BWM is demonstrated by solving the engineering application problem of evaluating the new energy storage technology, and its advantages compared with existing BWMs are demonstrated through comparison and sensitivity analyses.

Best-Worst Method （BWM）作为解决人工智能（AI）中多标准决策（MCDM）挑战的核心分析工具，在工业工程的分析维度上显示出显著的实际效果。然而，现有的决策机制一般是基于完全偏好信息的假设，其一致性分析框架主要侧重于偏好关系的基数一致性。此外，特别是在群体决策管理的背景下，缺乏对群体决策（GDM）达成共识机制的系统研究。上述问题严重制约了水运的应用和推广。直觉乘法偏好关系（impr）在解决人工智能（AI）领域的信息表示不平衡方面显示出独特的理论优势。鉴于上述事实，本研究建立了不完全直觉乘法环境下的BWM扩展模型，探讨共识达成和综合一致性管理。首先，针对偏好信息不完全的挑战，构建了直觉乘法运算与增强一致性控制相结合的优化模型。其次，引入双一致性度量（有序一致性和基数一致性），并辅以相应的优化模型，保证了方案排序的传递逻辑和偏好强度的数值稳定性；在此基础上，建立了以综合一致性管理和专家权重动态分配为特征的动态共识达成机制，以提高专家组对GDM结果的接受度。最后，通过解决评价新型储能技术的工程应用问题，论证了所提BWM的有效性，并通过对比分析和敏感性分析，论证了所提BWM与现有BWM相比的优势。

{"title":"Synthetical-consistency control and preference consensus handling in group best-worst method under incomplete intuitionistic multiplicative context","authors":"Xiaoyun Lu , Yejun Xu , Zhong-lin Ye , Tong-Feng Li , Ze-Hui Chen","doi":"10.1016/j.cie.2025.111707","DOIUrl":"10.1016/j.cie.2025.111707","url":null,"abstract":"<div><div>The Best-Worst Method (BWM), as a core analytical tool for tackling multi-criteria decision making (MCDM) challenges in artificial intelligence (AI), demonstrates remarkable practical efficacy at the analytical dimension of industrial engineering. However, existing BWMs are generally based on the assumption of complete preference information, and their consistency analysis framework focuses mainly on cardinal consistency of preference relations. In addition, particularly in the context of BWM, there is a lack of systematic research on consensus-reaching mechanisms for group decision making (GDM). The above problems seriously restrict the application and expansion of BWM. Intuitionistic multiplicative preference relations (IMPRs) demonstrate unique theoretical advantages in addressing imbalanced information representation within the field of artificial intelligence (AI). Given the above facts, this study develops an extended model of BWM under incomplete intuitionistic multiplicative context, exploring consensus reaching and synthetical consistency management. Firstly, this study constructs an optimization model by integrating intuitionistic multiplicative operations with enhanced consistency control to address the challenge of incomplete preference information. Secondly, dual consistency measures (ordinal consistency and cardinal consistency) are introduced, supplemented by corresponding optimization models, to ensure the transmission logic of alternatives ranking and the numerical stability of preference strength. Moreover, a dynamic consensus-reaching mechanism featuring synthetical consistency management and dynamic expert weight allocation is developed to enhance the acceptability of GDM outcomes within the expert group. Finally, the validity of the proposed BWM is demonstrated by solving the engineering application problem of evaluating the new energy storage technology, and its advantages compared with existing BWMs are demonstrated through comparison and sensitivity analyses.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111707"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145792183","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 novel process monitoring method for multivariate autocorrelated mixed-type data based on transformer model integrated with the feature-enhancement learning method 一种基于变压器模型与特征增强学习方法相结合的多变量自相关混合型数据过程监测方法

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-22 DOI: 10.1016/j.cie.2025.111776

Li Xue , Sen Feng , Tianci Zhao , Zhen He , Yuanzhong Jia , Tianye He

In the context of big data-driven intelligent manufacturing, process data often exhibit high dimensionality, multiple variables, and complex correlations. When these data comprise multiple variable types with unknown distributions, traditional parametric control charts struggle to address these challenges effectively. This study leverages the transformer model to monitor mixed continuous, count, and categorical data types in multivariate autocorrelated processes, proposing a feature-enhancement learning monitoring method. The experimental results demonstrate that the transformer model integrated with the proposed feature-enhancement learning method outperforms traditional monitoring approaches, such as residual control charts and

T^{2}

control charts, as well as other models, such as back propagation (BP), convolutional neural network (CNN), recurrent neural network (RNN), gated recurrent unit (GRU) and long short-term memory (LSTM), and also two traditional control charts constructed based on statistical methods for monitoring mixed-type data. The method’s effectiveness is further validated through a case study in semiconductor manufacturing. This study provides a theoretical foundation for applying deep learning technology to monitor multivariate autocorrelated processes.

在大数据驱动的智能制造背景下，过程数据往往呈现高维、多变量、复杂关联的特征。当这些数据包含具有未知分布的多种变量类型时，传统的参数控制图难以有效地解决这些挑战。本研究利用变压器模型监测多元自相关过程中的混合连续、计数和分类数据类型，提出了一种特征增强学习监测方法。实验结果表明，结合特征增强学习方法的变压器模型优于残差控制图和T2控制图等传统监测方法，也优于反向传播（BP）、卷积神经网络（CNN）、递归神经网络（RNN）、门控递归单元（GRU）和长短期记忆（LSTM）等其他模型。基于统计方法构造了两种传统的控制图，用于监测混合类型数据。通过半导体制造的实例研究，进一步验证了该方法的有效性。本研究为应用深度学习技术监测多变量自相关过程提供了理论基础。

{"title":"A novel process monitoring method for multivariate autocorrelated mixed-type data based on transformer model integrated with the feature-enhancement learning method","authors":"Li Xue , Sen Feng , Tianci Zhao , Zhen He , Yuanzhong Jia , Tianye He","doi":"10.1016/j.cie.2025.111776","DOIUrl":"10.1016/j.cie.2025.111776","url":null,"abstract":"<div><div>In the context of big data-driven intelligent manufacturing, process data often exhibit high dimensionality, multiple variables, and complex correlations. When these data comprise multiple variable types with unknown distributions, traditional parametric control charts struggle to address these challenges effectively. This study leverages the transformer model to monitor mixed continuous, count, and categorical data types in multivariate autocorrelated processes, proposing a feature-enhancement learning monitoring method. The experimental results demonstrate that the transformer model integrated with the proposed feature-enhancement learning method outperforms traditional monitoring approaches, such as residual control charts and <span><math><msup><mrow><mi>T</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> control charts, as well as other models, such as back propagation (BP), convolutional neural network (CNN), recurrent neural network (RNN), gated recurrent unit (GRU) and long short-term memory (LSTM), and also two traditional control charts constructed based on statistical methods for monitoring mixed-type data. The method’s effectiveness is further validated through a case study in semiconductor manufacturing. This study provides a theoretical foundation for applying deep learning technology to monitor multivariate autocorrelated processes.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111776"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885431","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

From railway disruptions to recovery: An improved Benders decomposition for the dynamic train timetable rescheduling and rolling stock reassignment 从铁路中断到恢复：动态列车时刻表重新调度和机车车辆重新分配的改进Benders分解

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-27 DOI: 10.1016/j.cie.2025.111794

Nsabimana Buhigiro , Liujiang Kang , Qingying Lai , Huijun Sun , Qianwen Xu

This paper proposes a novel rolling-horizon-based optimization framework for managing railway operations, which integrates dynamic train timetable rescheduling and rolling stock reassignment under uncertain disruption durations. Unlike existing approaches that assume fixed-duration disruptions, our method explicitly incorporates real-time uncertainty by enabling adaptive recovery strategies. These include resource schedule adjustments, service cancellations, short-turning, stop-skipping, and the strategic insertion of additional train services. The problem is formulated as a mixed-integer linear programming model that aims to minimize total delay, operational costs, penalties for cancellations, and costs related to slot planning for additional train services. The formulation respects a variety of operational constraints, including fleet feasibility and service continuity, enabling dynamic and feasible rescheduling. To overcome the computational challenges of real-time decision-making with gradually revealed disruption information, we develop an improved Benders decomposition (IBD) algorithm. The method decomposes the model into a master problem (rolling stock reassignment) and a subproblem (timetable rescheduling), and incorporates custom multi-optimality cuts within a rolling horizon framework to enhance convergence. For benchmarking, we also implement a two-stage sequential algorithm (TSA). Numerical experiments on the Beijing Batong metro line demonstrate that IBD significantly outperforms both TSA and commercial solvers in computational efficiency. Our approach provides practically viable solutions for railway operators facing uncertain disruptions, bridging the gap between theoretical models and real-world applicability.

本文提出了一种新的基于滚动水平的铁路运营管理优化框架，该框架将不确定中断持续时间下的列车时刻表动态调度和车辆重新分配相结合。与现有的假设固定时间中断的方法不同，我们的方法通过启用自适应恢复策略明确地结合了实时不确定性。这些措施包括资源调度调整、服务取消、短转、跳站和战略性地插入额外的列车服务。该问题被表述为一个混合整数线性规划模型，其目标是最小化总延误、运营成本、取消处罚以及与额外列车服务的时段规划相关的成本。该方案考虑了各种操作约束，包括机队可行性和服务连续性，实现了动态和可行的重新调度。为了克服实时决策的计算挑战，我们开发了一种改进的Benders分解（IBD）算法。该方法将模型分解为一个主问题（车辆重新分配）和一个子问题（时间表重新调度），并在滚动地平线框架内引入自定义多最优切割以增强收敛性。对于基准测试，我们还实现了两阶段顺序算法（TSA）。在北京八通地铁上的数值实验表明，IBD在计算效率上明显优于TSA和商用求解器。我们的方法为面临不确定中断的铁路运营商提供了切实可行的解决方案，弥合了理论模型与现实应用之间的差距。

{"title":"From railway disruptions to recovery: An improved Benders decomposition for the dynamic train timetable rescheduling and rolling stock reassignment","authors":"Nsabimana Buhigiro , Liujiang Kang , Qingying Lai , Huijun Sun , Qianwen Xu","doi":"10.1016/j.cie.2025.111794","DOIUrl":"10.1016/j.cie.2025.111794","url":null,"abstract":"<div><div>This paper proposes a novel rolling-horizon-based optimization framework for managing railway operations, which integrates dynamic train timetable rescheduling and rolling stock reassignment under uncertain disruption durations. Unlike existing approaches that assume fixed-duration disruptions, our method explicitly incorporates real-time uncertainty by enabling adaptive recovery strategies. These include resource schedule adjustments, service cancellations, short-turning, stop-skipping, and the strategic insertion of additional train services. The problem is formulated as a mixed-integer linear programming model that aims to minimize total delay, operational costs, penalties for cancellations, and costs related to slot planning for additional train services. The formulation respects a variety of operational constraints, including fleet feasibility and service continuity, enabling dynamic and feasible rescheduling. To overcome the computational challenges of real-time decision-making with gradually revealed disruption information, we develop an improved Benders decomposition (IBD) algorithm. The method decomposes the model into a master problem (rolling stock reassignment) and a subproblem (timetable rescheduling), and incorporates custom multi-optimality cuts within a rolling horizon framework to enhance convergence. For benchmarking, we also implement a two-stage sequential algorithm (TSA). Numerical experiments on the Beijing Batong metro line demonstrate that IBD significantly outperforms both TSA and commercial solvers in computational efficiency. Our approach provides practically viable solutions for railway operators facing uncertain disruptions, bridging the gap between theoretical models and real-world applicability.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111794"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885437","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

Data-driven order batching policy: Focusing on the fulfillment center of Kurly 数据驱动的订单批处理策略：关注Kurly的履行中心

IF 6.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Industrial Engineering

Pub Date : 2026-03-01 Epub Date: 2025-12-24 DOI: 10.1016/j.cie.2025.111767

Juyoung Wang, Soohyung Park, Byungju Goo, Dongyun Kang, Soojee Kim, Jaehyeong Choi, Choonoh Lee

Order batching is a key operation in e-commerce fulfillment centers, exerting major influence on labor costs, throughput, and overall facility performance. In high-volume grocery warehouses, such as those operated by Kurly Inc., efficient batching is particularly crucial to meet narrow delivery windows and keep a high-level customer satisfaction. Traditional approaches often aim to minimize travel distance for item picking tasks or makespan, but Kurly’s primary bottleneck arises from the accumulation of totes (plastic bins) on conveyors, delaying downstream packing and limiting daily processing capacity. To address this challenge, we propose a data-driven order batching framework that directly targets tote number reduction by embedding a linear regression model into an integer program. The regression predicts how many totes a candidate batch will require, allowing us to optimize order-to-batch assignments with minimal tote usage. Tests with real operational data show that our hybrid strategy combining a genetic algorithm-based order batching policy and Gurobi’s no relaxation heuristic reduces tote congestion by up to 92% compared to Kurly’s legacy randomized batching algorithm. These advances expedite packing, increase order throughput, and improve resource utilization. Overall, our findings illustrate how data-driven objectives and off-the-shelf solvers can be successfully leveraged in large-scale industrial contexts to address pervasive bottlenecks in modern e-commerce warehousing.

订单批处理是电子商务履行中心的一项关键操作，对劳动力成本、吞吐量和整体设施性能产生重大影响。在库利公司（Kurly Inc.）运营的大容量杂货仓库中，高效的批处理对于满足狭窄的交货窗口和保持高水平的客户满意度尤为重要。传统方法的目标通常是尽量减少拣货任务的运输距离或最大完工时间，但Kurly的主要瓶颈来自输送带上的手提袋（塑料箱）的堆积，延迟了下游包装，限制了日常处理能力。为了应对这一挑战，我们提出了一个数据驱动的订单批处理框架，该框架通过将线性回归模型嵌入到整数程序中，直接针对减少订单数量。回归预测候选批将需要多少个手提袋，允许我们以最小的手提袋使用量优化订单到批的分配。使用实际操作数据进行的测试表明，与Kurly的传统随机批处理算法相比，我们的混合策略结合了基于遗传算法的顺序批处理策略和Gurobi的无松弛启发式算法，可减少高达92%的包拥塞。这些进步加快了包装，增加了订单吞吐量，提高了资源利用率。总的来说，我们的研究结果说明了数据驱动的目标和现成的解决方案如何在大规模工业环境中成功地利用，以解决现代电子商务仓储中普遍存在的瓶颈。

{"title":"Data-driven order batching policy: Focusing on the fulfillment center of Kurly","authors":"Juyoung Wang, Soohyung Park, Byungju Goo, Dongyun Kang, Soojee Kim, Jaehyeong Choi, Choonoh Lee","doi":"10.1016/j.cie.2025.111767","DOIUrl":"10.1016/j.cie.2025.111767","url":null,"abstract":"<div><div>Order batching is a key operation in e-commerce fulfillment centers, exerting major influence on labor costs, throughput, and overall facility performance. In high-volume grocery warehouses, such as those operated by Kurly Inc., efficient batching is particularly crucial to meet narrow delivery windows and keep a high-level customer satisfaction. Traditional approaches often aim to minimize travel distance for item picking tasks or makespan, but Kurly’s primary bottleneck arises from the accumulation of totes (plastic bins) on conveyors, delaying downstream packing and limiting daily processing capacity. To address this challenge, we propose a data-driven order batching framework that directly targets tote number reduction by embedding a linear regression model into an integer program. The regression predicts how many totes a candidate batch will require, allowing us to optimize order-to-batch assignments with minimal tote usage. Tests with real operational data show that our hybrid strategy combining a genetic algorithm-based order batching policy and Gurobi’s no relaxation heuristic reduces tote congestion by up to 92% compared to Kurly’s legacy randomized batching algorithm. These advances expedite packing, increase order throughput, and improve resource utilization. Overall, our findings illustrate how data-driven objectives and off-the-shelf solvers can be successfully leveraged in large-scale industrial contexts to address pervasive bottlenecks in modern e-commerce warehousing.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"213 ","pages":"Article 111767"},"PeriodicalIF":6.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841687","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