论文速递 | IISE Transactions 2-3月文章精选

编者按

在本系列文章中，我们对顶刊《IISE Transactions》上2-3月份在线发布的文章进行了精选（共 8 篇），并总结其基本信息，旨在帮助读者快速洞察领域最新动态。

推荐文章1

● 题目：Store Fulfillment with Autonomous Mobile Robots and In-Store Customers

基于自主移动机器人和店内顾客的店铺订单履行

● 原文链接：https://doi.org/10.1080/24725854.2025.2485171

● 作者：Joyjit Bhowmick, Jennifer Pazour*, Iman Dayarian

● 发布时间：2025-03-28

● 摘要：

Omnichannel services, such as buy-online-pickup-in-store, curbside pickup, and ship-from-store, have shifted the order-picking tasks previously completed by in-store customers doing their own shopping to the retailer’s responsibility. To fulfill these orders, many retailers have deployed a store fulfillment strategy, where online orders are picked from brick-and-mortar retail store shelves. We focus on the design of operations inside a store where in-store customers collaborate with autonomous mobile robots (AMRs) to pick online orders. Due to the uncertainty in in-store customers’ availability and their willingness to participate, the problem of synchronizing in-store customers with AMRs is highly stochastic. Thus, we model the stochastic order-picking problem with uncertain synchronization times of in-store customers and AMRs as a Markov Decision Process to determine how a retailer should dynamically assign tasks to a set of AMRs and dedicated pickers. We develop a heuristic solution framework that generates a set of initial assignments and routes for heterogenous picking resources and dynamically updates them as the actual synchronization times between AMRs and in-store customers unfold. We analyze multiple strategies to generate the initial set of task assignments and routes as well as update such decisions based on the system state. To provide guidance on whether the proposed approach is economically and operationally viable, we conduct extensive computational experiments using actual online grocery orders and empirical shopping behavior data. We illustrate the feasibility of such a policy to achieve similar picking performance as the status quo and through an economic analysis show that deploying dedicated pickers and AMRs aided by in-store customers in a store environment is economically viable.

全渠道服务，如在线购买-店内自取、路边自取和店内发货，已将以前由店内顾客在购物时完成的订单拣选任务转移到零售商的责任上。为了履行这些订单，许多零售商已部署了店铺履行策略，即从实体零售店货架上拣选在线订单。本文聚焦于店内运营设计，探讨店内顾客与自主移动机器人（AMRs）合作完成在线订单拣选的场景。由于店内顾客的可用性和参与意愿存在不确定性，店内顾客与AMRs的同步问题具有高度的随机性。因此，我们将这一具有不确定同步时间的随机订单拣选问题建模为马尔可夫决策过程，以确定零售商应如何动态分配任务给AMRs和专职拣货员。我们开发了一个启发式解决框架，生成异质化拣货资源的初步任务分配和路线，并随着AMRs和店内顾客实际同步时间的变化动态更新这些任务和路线。我们分析了多种策略来生成初步任务分配和路线，并根据系统状态更新这些决策。为了评估该方法在经济和操作上的可行性，我们利用实际的在线生鲜订单和经验性购物行为数据进行了大量的计算实验。我们展示了该策略在实现与现有方法相似的拣货性能方面的可行性，并通过经济分析表明，在店铺环境中，部署专职拣货员和AMRs，并借助店内顾客的协作，是经济上可行的。

推荐文章2

● 题目：Stochastic Modeling of Human Lumbar Functional Spinal Units System Degeneration

人类腰椎功能性脊柱单元系统退化的随机建模

● 原文链接：https://doi.org/10.1080/24725854.2025.2485171

● 作者：Tong Wu, Litai Ma, Yao Cheng, Kerui Zhang, Kang Li, Yi Yang, Hao Liu, Changxi Wang*

● 发布时间：2025-03-28

● 摘要：

The degeneration of the human lumbar functional spinal units (FSUs) system is a global health concern. The FSUs system consists of four interdependent subsystems, each with an intervertebral disc and a facet joint that are subject to degeneration over time. The FSUs system fails when the overall disc height reduction or any facet joint contact force reaches the corresponding threshold. Existing research mainly uses regression-based models to describe the relationship between age and intervertebral disc height in the general population. A specific patient’s time-related progression of the FSUs system’s degeneration indicators are yet to be quantitatively characterized by the prediction models. We develop a stochastic model for the FSUs system degeneration process. The model captures the uncertainties of subsystems’ and components’ degeneration initiation time, order and interdependencies. Two failure mechanisms are proposed based on biomechanics and the components’ spatial and mechanical interdependencies. To facilitate the model’s clinical applications, individual-specific characteristics are incorporated into the extended models. Reliability metrics such as the overall reliability functions, mean time to failure and mean residual life are proposed for practical application purposes. Actual time-series data are collected for model validation. The results show that the proposed model outperforms existing stochastic and biostatistical models.

人类腰椎功能性脊柱单元（FSUs）系统的退化是全球健康关注的问题。FSUs系统由四个相互依赖的子系统组成，每个子系统包含一个椎间盘和一个小关节，这些结构随着时间的推移容易发生退化。当椎间盘高度整体减少或任何小关节接触力达到相应阈值时，FSUs系统会发生故障。现有研究主要使用基于回归的模型来描述年龄与一般人群中椎间盘高度之间的关系。然而，针对特定患者的FSUs系统退化指标随时间的进展尚未通过预测模型进行定量刻画。我们开发了一个用于FSUs系统退化过程的随机模型。该模型捕捉了子系统和组件退化启动时间、顺序及相互依赖关系的不确定性。基于生物力学以及组件的空间和机械相互依赖性，提出了两种故障机制。为了促进该模型的临床应用，个体特征被纳入扩展模型中。提出了整体可靠性函数、平均故障时间和平均剩余寿命等可靠性指标，供实际应用参考。通过收集实际时间序列数据来验证模型的有效性。结果表明，所提模型优于现有的随机模型和生物统计学模型。

推荐文章3

● 题目：Capacity Representation in Sales and Operations Planning: Aggregation through Projection

销售与运营计划中的产能表示：通过投影进行聚合

● 原文链接：https://doi.org/10.1080/24725854.2025.2477690

● 作者：Soroush Fatemi-Anaraki*, Martin Grunow, Stefan Weltge

● 发布时间：2025-03-13

● 摘要：

Software systems supporting sales and operations planning operate on the basis of total production volumes of products. They ensure that production volumes are feasible with respect to the capacity at different production sites without allocating them to individual resources. We consider the problem of finding a representation of the set of production volumes that respects the capacity by means of linear inequalities and that only uses variables corresponding to the total production volumes. For single-stage production systems, we derive a complete description of this type analytically. Since this description has exponential size, we present an algorithmic framework for approximating this set. Adopting a polyhedral perspective, our algorithmic framework can be applied to obtain projections of arbitrary polytopes, including those that represent multi-stage production systems. In a case study from a German semiconductor manufacturer, we demonstrate the superiority of our approach over existing methods with respect to the computation time and quality of approximation. Through extensive numerical experiments, we show that our approach can be applied efficiently to instances with a wide range of values for the production system’s parameters, i.e., the number of production stages, resources at each stage, and alternative process plans.

支持销售与运营计划的软件系统是基于产品的总生产量进行操作的。它们确保生产量在不同生产站点的产能范围内是可行的，而无需将其分配到各个单独的资源上。我们考虑的问题是，如何通过线性不等式找到一种表示生产量集合的方法，该方法能够尊重产能限制，并且只使用与总生产量相关的变量。对于单阶段生产系统，我们从解析角度推导了此类表示的完整描述。由于该描述的规模是指数级的，我们提出了一种算法框架来近似表示该集合。采用多面体的视角，我们的算法框架可以应用于获得任意多面体的投影，包括表示多阶段生产系统的多面体。在一项来自德国半导体制造商的案例研究中，我们展示了我们的方法在计算时间和近似质量方面相较于现有方法的优越性。通过广泛的数值实验，我们表明，所提出的方法能够高效应用于具有广泛参数值范围的生产系统实例，例如生产阶段数量、每个阶段的资源以及替代工艺计划。

推荐文章4

● 题目：Bayesian Optimization with Active Constraint Learning for Advanced Manufacturing Process Design

基于贝叶斯优化与主动约束学习的先进制造过程设计

● 原文链接：https://doi.org/10.1080/24725854.2025.2475505

● 作者：Guoyan Li, Yujia Wang, Swastik Kar, Xiaoning Jin*

● 发布时间：2025-03-07

● 摘要：

This study addresses the complex challenge of identifying process parameters for optimal manufacturing outcomes in advanced manufacturing, where nonlinear and costly process-to-quality relationships prevail. We introduce a novel experimental design framework that energizes the optimization of process parameters and feasibility constraint learning with a significantly reduced number of trials as compared to traditional Design of Experiments methods. Our approach is grounded in two primary methodologies: (1) active multi-criteria sample for constraint estimation and (2) Bayesian optimization-based sample for optimal parameter identification. This integration facilitates the efficient discovery of globally optimal parameter settings and outperforms multiple benchmark models in constraint estimation accuracy. The framework’s efficacy is demonstrated through application on both synthetic datasets and a real-world case study involving the synthesis of 2D materials, demonstrating its potential to enhance manufacturing efficiency and quality in complex manufacturing processes significantly.

本研究解决了在先进制造中识别过程参数以实现最佳制造结果的复杂挑战，其中非线性和高成本的过程-质量关系占主导地位。我们提出了一种新型实验设计框架，与传统的实验设计方法相比，能够显著减少试验次数，同时推动过程参数优化与可行性约束学习的进展。我们的方法基于两种主要方法论：（1）用于约束估计的主动多标准采样，和（2）基于贝叶斯优化的样本用于最优参数识别。这种集成方法促进了全局最优参数设置的高效发现，并在约束估计精度方面优于多个基准模型。通过在合成数据集和涉及二维材料合成的实际案例研究中的应用，展示了该框架的有效性，证明其在复杂制造过程中的潜力，能够显著提升制造效率和质量。

推荐文章5

● 题目：Multi-objective simulation-optimization for a distribution centre resource planning

面向配送中心资源规划的多目标仿真优化

● 原文链接：https://doi.org/10.1080/24725854.2025.2475307

● 作者：Yan Li*, Yeo Keng Swee, Haobin Li, Ek Peng Chew

● 发布时间：2025-03-07

● 摘要：

This study tackles resource planning in distribution centers, aiming to enhance efficiency while minimizing the number of deployed workers and forklifts. We achieve this by optimizing resource schedules across different areas and time periods. Initially, we developed a detailed warehouse simulation model to reflect resource limitations and their impact on operations. Specifically, we define staging areas, including the receiving dock, inbound buffer area, and outbound buffer area, which serve as the start and end points of all activities and the nexus of resource allocation. Utilizing modular modeling and an event-driven discrete-event mechanism, our proposed model can accelerate the simulation process while ensuring high fidelity. We then design multi-objective simulation-optimization models, aiming for Pareto optimality, minimizing average queuing time, workforce size, and forklift fleetsize under different skill set scenarios. Using a customized multiple gradient descent-simultaneous perturbation stochastic approximation algorithm, our approach effectively handles many-objective problems and significantly reduces CPU time compared to evolutionary algorithms. A case study highlights the inbound buffer area as a key bottleneck and reveals the impact of incomplete skills on workforce deployment. Drawing insights from the results, we discuss several strategies for enhancing efficiency—including deploying part-time workers—offering new solutions to warehouse resource planning challenges.

本研究解决了配送中心的资源规划问题，旨在提高效率，同时最小化部署的工人和叉车数量。我们通过优化不同区域和时间段的资源调度来实现这一目标。首先，我们开发了一个详细的仓库仿真模型，以反映资源限制及其对操作的影响。具体而言，我们定义了多个暂存区，包括接收码头、入库缓冲区和出库缓冲区，这些区域作为所有活动的起点和终点，并且是资源分配的枢纽。通过采用模块化建模和事件驱动的离散事件机制，我们提出的模型能够加速仿真过程，同时确保高度的精确性。接着，我们设计了多目标仿真优化模型，旨在实现帕累托最优性，最小化不同技能场景下的平均排队时间、劳动力规模和叉车车队规模。通过使用定制的多重梯度下降-同步扰动随机逼近算法，我们的方法能够有效处理多目标问题，并且相比于进化算法显著减少了CPU时间。一项案例研究突出了入库缓冲区作为关键瓶颈，并揭示了不完整技能对劳动力部署的影响。根据研究结果，我们讨论了几种提高效率的策略，包括部署兼职工人，并为仓库资源规划问题提供了新的解决方案。

推荐文章6

● 题目：Planning Reliability Assurance Tests for Autonomous Vehicles Based on Disengagement Events Data

基于脱离事件数据的自动驾驶汽车可靠性保证测试规划

● 原文链接：https://doi.org/10.1080/24725854.2025.2475324

● 作者：Simin Zheng, Lu Lu, Yili Hong*, Jian Liu

● 发布时间：2025-03-04

● 摘要：

Artificial intelligence (AI) technology has become increasingly prevalent and transforms our everyday lives. One important application of AI technology is the development of autonomous vehicles (AVs). However, the reliability of an AV needs to be carefully demonstrated via an assurance test so that the product can be used with confidence in the field. To plan for an assurance test, one needs to determine how many AVs need to be tested for how many miles and the standard for passing the test. Existing research has made great efforts in developing reliability demonstration tests in the other fields of applications for product development and assessment. However, statistical methods have not been utilized in AV test planning. This paper aims to fill in this gap by developing statistical methods for planning AV reliability assurance tests based on recurrent events data. We explore the relationship between multiple criteria of interest in the context of planning AV reliability assurance tests. Specifically, we develop two test planning strategies based on homogeneous and non-homogeneous Poisson processes while balancing multiple objectives with the Pareto front approach. We also offer recommendations for practical use. The disengagement events data from the California Department of Motor Vehicles AV testing program is used to illustrate the proposed assurance test planning methods.

人工智能（AI）技术已经日益普及，并深刻改变了我们的日常生活。AI技术的一个重要应用是自动驾驶汽车（AV）的开发。然而，自动驾驶汽车的可靠性需要通过保证测试来谨慎验证，以确保该产品可以在实际环境中安全使用。为了规划保证测试，需要确定测试多少辆自动驾驶汽车、测试多少英里以及通过测试的标准。现有研究在其他产品开发与评估领域中已做出了大量努力，旨在开发可靠性验证测试。然而，统计方法尚未在自动驾驶汽车测试规划中得到应用。本文旨在通过基于重复事件数据开发统计方法，填补这一空白，推动自动驾驶汽车可靠性保证测试的规划。我们探讨了在规划自动驾驶汽车可靠性保证测试过程中，多个感兴趣标准之间的关系。具体来说，我们基于均匀和非均匀泊松过程，发展了两种测试规划策略，并通过帕累托前沿方法平衡多目标之间的关系。我们还提供了实际应用的建议。通过使用加利福尼亚州机动车管理局（DMV）自动驾驶汽车测试项目的脱离事件数据，来说明所提出的保证测试规划方法。

推荐文章7

● 题目：Scheduling AGVs in ports with battery charging and swapping

具有电池充电和更换的港口自动引导车调度

● 原文链接：https://doi.org/10.1080/24725854.2025.2468722

● 作者：Lu Zhen, Qian Zhang, Zheyi Tan, Shuaian Wang*

● 发布时间：2025-02-20

● 摘要：

Efficient scheduling of automated guided vehicles (AGVs) in automated container terminals (ACTs) is crucial to their operations management under the initiative of green port and smart port development. Facing numerous containers, a port operator needs to assign container loading/unloading tasks to AGVs, sequence the tasks for each AGV, and arranges the battery charging or swapping activities for the AGVs in a high-efficient manner, which affects the operational performance of the port and further impacts its annual throughput. This study proposes a mathematical model for scheduling AGVs under the battery charging-swapping mixed mode. The model should be solved in a short time, otherwise the proposed methodology cannot apply in realistic port environment. Therefore, an efficient column generation based solution method is designed for solving the models; a novel label setting algorithm is also proposed and embedded in the above method for solving the pricing problems in a fast way. Based on two representative ACTs, i.e., the first ACT in China and the largest ACT in the world, numerical experiments are conducted to derive some managerial insights for ACTs’ operations management on AGVs under different battery management modes.

在绿色港口和智能港口发展的倡议下，自动化集装箱码头（ACTs）中自动引导车（AGVs）的高效调度对其运营管理至关重要。在面对大量集装箱的情况下，港口运营商需要将集装箱装卸任务分配给AGV，确定每个AGV的任务顺序，并以高效的方式安排AGV的电池充电或更换活动，这直接影响港口的运营绩效，并进一步影响其年度吞吐量。本研究提出了一种基于电池充电-更换混合模式的AGV调度数学模型。该模型需要在短时间内解决，否则所提出的方法将无法在实际港口环境中应用。因此，本文设计了一种高效的列生成求解方法来解决该模型；同时提出并嵌入了一种新的标签设置算法，以快速解决定价问题。基于两个具有代表性的ACT，分别是中国的首个ACT和世界上最大的ACT，进行了数值实验，以从不同电池管理模式下对AGV的运营管理中提取一些管理见解。

推荐文章8

● 题目：IISE PG&E Energy Analytics Challenge 2024: Forecasting day-ahead electricity prices

IISE PG&E能源分析挑战赛2024：预测次日电力价格

● 原文链接：https://doi.org/10.1080/24725854.2024.2447049

● 作者：Ahmed Aziz Ezzat*, Mahan Mansouri, Murat Yildirim, Xiaolei Fang

● 发布时间：2025-02-11

● 摘要：

Electricity price forecasting is one of the cornerstones of modern-day power system operation. Over the last two decades, the field has seen many methodological advancements. On one end, traditional statistical methods remain widely prevalent in today’s energy industry, as they have proven consistently to “stand the test of time.” On the other end, emerging predictive techniques (e.g., machine and deep learning) have demonstrated immense potential. Yet, due to limited benchmarking studies, the magnitude of improvement realized by such emerging methods relative to their statistical counterparts is not entirely clear. In response, two technical divisions of the Institute of Industrial & Systems Engineers (IISE) partnered with the Pacific Gas and Electric Company (PG&E)—one of the largest utility companies in the United States—in order to organize an electricity price forecasting challenge in 2024. Using three years of pricing signals and exogenous information from California’s electricity market, the competition challenged teams of researchers and practitioners to design their own models and submit forecasts for day-ahead electricity prices, which were independently evaluated against a test set that has been withheld from all teams. This article introduces the challenge, as well as an overview of the methods used by the top-performing contestants. A distilled summary of the key insights and lessons learned by the challenge organizers is then presented, together with their relevance to the topic of electricity price forecasting. This is then followed by recommendations for future similarly focused competitions. To accelerate the research and development on this important topic, all data used in the challenge have been made publicly available by the challenge organizers.

电力价格预测是现代电力系统运行的基石之一。在过去的二十年里，电力价格预测领域经历了许多方法论的进展。在一方面，传统的统计方法仍在当今能源行业中广泛应用，因为它们已经证明能经受住“时间的考验”。另一方面， 新兴的预测技术，例如机器学习和深度学习，展示出了巨大的潜力。然而，由于基准研究的限制，尚不完全清楚这些新兴方法相较于传统统计方法的改进幅度。为此，工业与系统工程师学会（IISE）的两个技术部门与美国最大的公用事业公司之一——太平洋煤气与电力公司（PG&E）合作，组织了2024年的电力价格预测挑战赛。比赛使用了来自加利福尼亚电力市场的三年价格信号及外生信息，挑战参赛的研究人员和从业者团队设计各自的模型，并提交次日电力价格的预测结果，这些预测结果将在一个独立的测试集上进行评估，该测试集对所有参赛队伍保持保密。本文介绍了该挑战赛，并概述了表现最佳的参赛者所采用的方法。随后，总结了挑战赛组织者获得的关键见解和经验教训，并讨论了这些见解与电力价格预测主题的相关性。最后，本文提出了对未来类似聚焦比赛的建议。为了加速这一重要课题的研究与发展，所有用于挑战赛的数据已由组织者公开发布。