Supply Chain Analytics最新文献_第5页

A multi-objective analytics approach for supply chain optimization in flexible manufacturing systems 柔性制造系统供应链优化的多目标分析方法

Supply Chain Analytics

Pub Date : 2025-10-13 DOI: 10.1016/j.sca.2025.100170

Shahed Mahmud , Ripon K. Chakrabortty , Alireza Abbasi , Michael J. Ryan

This study contributes to the advancement of supply chain scheduling (SCS) through the development of a comprehensive mathematical framework that unifies multi-objective supplier selection, demand allocation, production scheduling, and inventory management within flexible manufacturing systems (FMS). Amidst the rapid progress of FMS and Industry 4.0 technologies, integrating these supply-chain decisions has become indispensable for ensuring timely and cost-efficient delivery of customized products. Yet research remains limited when supply, inventory, flexible routing and sequencing decisions must be handled simultaneously, often yielding conflicting objectives. We therefore propose a bi-objective SCS model that jointly optimizes supply, inventory and production portfolios to meet heterogeneous customer orders under due-date constraints. The shop floor is modeled as a flexible job shop with sequence-dependent setup times and inventory constraints, and the framework embeds supplier selection and demand allocation decisions for critical parts. Since the resulting problem is NP-hard, a multi-objective JAYA algorithm (MOJAYA) is devised, featuring a Pareto-cluster update rule and a problem-specific co-evaluated local search. Extensive experiments on 15 benchmark instances show MOJAYA, against four established algorithms, consistently yields wider, more uniform Pareto fronts, lowering mean inverted generational distance by up to 48% and increasing hyper-volume by up to 23% within the same computational budget; Friedman and Wilcoxon tests confirm these gains are statistically significant (

p < 0.05

). In a representative instance, the decision schedule costs 357448 with 44 cumulative tardiness, and supplies managers with detailed production, supply, and inventory portfolios. The proposed approach therefore enhances decision-making flexibility across supply-chain stages, offering a data-driven tool for SCS problems.

本研究通过开发一个综合的数学框架，将柔性制造系统（FMS）中的多目标供应商选择、需求分配、生产调度和库存管理统一起来，为供应链调度（SCS）的进步做出了贡献。在FMS和工业4.0技术的快速发展中，整合这些供应链决策对于确保及时和经济高效地交付定制产品至关重要。然而，当供应、库存、灵活的路线和排序决策必须同时处理时，研究仍然有限，往往产生相互冲突的目标。因此，我们提出了一个双目标SCS模型，该模型联合优化供应、库存和生产组合，以满足到期日期约束下的异构客户订单。车间被建模为具有顺序依赖的设置时间和库存约束的灵活作业车间，并且该框架嵌入了关键部件的供应商选择和需求分配决策。由于所得到的问题是np困难的，因此设计了一种多目标JAYA算法（MOJAYA），该算法具有帕累托聚类更新规则和特定于问题的协同评估局部搜索。在15个基准实例上进行的大量实验表明，与四种已建立的算法相比，MOJAYA始终产生更宽、更均匀的Pareto前沿，在相同的计算预算下，将平均倒代距离降低了48%，将超容量提高了23%。Friedman和Wilcoxon检验证实了这些增益在统计学上是显著的（p<0.05）。在一个有代表性的实例中，决策计划的成本为357448，累计延迟时间为44，并为管理人员提供详细的生产、供应和库存组合。因此，提出的方法提高了供应链各个阶段的决策灵活性，为SCS问题提供了数据驱动的工具。

{"title":"A multi-objective analytics approach for supply chain optimization in flexible manufacturing systems","authors":"Shahed Mahmud , Ripon K. Chakrabortty , Alireza Abbasi , Michael J. Ryan","doi":"10.1016/j.sca.2025.100170","DOIUrl":"10.1016/j.sca.2025.100170","url":null,"abstract":"<div><div>This study contributes to the advancement of supply chain scheduling (SCS) through the development of a comprehensive mathematical framework that unifies multi-objective supplier selection, demand allocation, production scheduling, and inventory management within flexible manufacturing systems (FMS). Amidst the rapid progress of FMS and Industry 4.0 technologies, integrating these supply-chain decisions has become indispensable for ensuring timely and cost-efficient delivery of customized products. Yet research remains limited when supply, inventory, flexible routing and sequencing decisions must be handled simultaneously, often yielding conflicting objectives. We therefore propose a bi-objective SCS model that jointly optimizes supply, inventory and production portfolios to meet heterogeneous customer orders under due-date constraints. The shop floor is modeled as a flexible job shop with sequence-dependent setup times and inventory constraints, and the framework embeds supplier selection and demand allocation decisions for critical parts. Since the resulting problem is NP-hard, a multi-objective JAYA algorithm (MOJAYA) is devised, featuring a Pareto-cluster update rule and a problem-specific co-evaluated local search. Extensive experiments on 15 benchmark instances show MOJAYA, against four established algorithms, consistently yields wider, more uniform Pareto fronts, lowering mean inverted generational distance by up to 48% and increasing hyper-volume by up to 23% within the same computational budget; Friedman and Wilcoxon tests confirm these gains are statistically significant (<span><math><mrow><mi>p</mi><mo><</mo><mn>0</mn><mo>.</mo><mn>05</mn></mrow></math></span>). In a representative instance, the decision schedule costs 357448 with 44 cumulative tardiness, and supplies managers with detailed production, supply, and inventory portfolios. The proposed approach therefore enhances decision-making flexibility across supply-chain stages, offering a data-driven tool for SCS problems.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100170"},"PeriodicalIF":0.0,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145320088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

From black box to analytical insight: A data-driven evaluation of technological sustainability in manufacturing supply chains 从黑箱到分析洞察：制造业供应链中技术可持续性的数据驱动评估

Supply Chain Analytics

Pub Date : 2025-10-10 DOI: 10.1016/j.sca.2025.100171

Marco Vacchi , Davide Settembre-Blundo , Luca Iattici , Anna Maria Ferrari , Roberto Rosa , Nicholas Berselli

Technological infrastructures critically drive resilience and sustainability in manufacturing supply chains yet remain severely underrepresented in conventional sustainability assessment frameworks. This paper introduces the Organizational Technological Sustainability Assessment (O-TSA), an innovative data-driven model that transforms operational technology data into strategic insight. Anchored in Life Cycle Thinking, O-TSA evaluates technological sustainability through three quantifiable dimensions: Input/Output Availability, Operational Performance, and Technical Quality, each measured via weighted indicators and standardized scoring functions. The framework delivers two actionable metrics: the Technological Sustainability Index (TSI), providing a precise measurement of current technological maturity, and the Technology Improvement Index (TII), quantifying performance evolution to enable evidence-based decision-making. When applied to a ceramic tile manufacturer, the model revealed specific operational inefficiencies while documenting a significant improvement in technological sustainability over a one-year period, primarily through enhanced documentation systems and digital integration. Empirical validation confirms the model's effectiveness in converting fragmented data streams into prioritized action points. By rendering previously invisible technological dependencies explicit and measurable, the O-TSA framework enables supply chain managers to align technological investments with sustainability objectives, facilitating the development of analytically-managed, resilient industrial ecosystems in resource-intensive environments.

技术基础设施对制造业供应链的弹性和可持续性至关重要，但在传统的可持续性评估框架中，技术基础设施的代表性仍然严重不足。本文介绍了组织技术可持续性评估（O-TSA），这是一种将运营技术数据转化为战略洞察力的创新数据驱动模型。O-TSA以生命周期思维为基础，通过三个可量化的维度来评估技术可持续性：投入/产出可用性、运营绩效和技术质量，每个维度都通过加权指标和标准化评分函数来衡量。该框架提供了两个可操作的指标：技术可持续性指数（TSI），提供当前技术成熟度的精确测量，以及技术改进指数（TII），量化绩效演变以实现基于证据的决策。当应用于瓷砖制造商时，该模型揭示了具体的操作效率低下，同时记录了一年来技术可持续性的显着改善，主要是通过增强文档系统和数字集成。经验验证证实了该模型在将碎片数据流转换为优先行动点方面的有效性。O-TSA框架将以前不可见的技术依赖关系呈现为明确和可测量的，使供应链管理者能够将技术投资与可持续性目标结合起来，促进资源密集型环境中分析管理、弹性工业生态系统的发展。

{"title":"From black box to analytical insight: A data-driven evaluation of technological sustainability in manufacturing supply chains","authors":"Marco Vacchi , Davide Settembre-Blundo , Luca Iattici , Anna Maria Ferrari , Roberto Rosa , Nicholas Berselli","doi":"10.1016/j.sca.2025.100171","DOIUrl":"10.1016/j.sca.2025.100171","url":null,"abstract":"<div><div>Technological infrastructures critically drive resilience and sustainability in manufacturing supply chains yet remain severely underrepresented in conventional sustainability assessment frameworks. This paper introduces the Organizational Technological Sustainability Assessment (O-TSA), an innovative data-driven model that transforms operational technology data into strategic insight. Anchored in Life Cycle Thinking, O-TSA evaluates technological sustainability through three quantifiable dimensions: Input/Output Availability, Operational Performance, and Technical Quality, each measured via weighted indicators and standardized scoring functions. The framework delivers two actionable metrics: the Technological Sustainability Index (TSI), providing a precise measurement of current technological maturity, and the Technology Improvement Index (TII), quantifying performance evolution to enable evidence-based decision-making. When applied to a ceramic tile manufacturer, the model revealed specific operational inefficiencies while documenting a significant improvement in technological sustainability over a one-year period, primarily through enhanced documentation systems and digital integration. Empirical validation confirms the model's effectiveness in converting fragmented data streams into prioritized action points. By rendering previously invisible technological dependencies explicit and measurable, the O-TSA framework enables supply chain managers to align technological investments with sustainability objectives, facilitating the development of analytically-managed, resilient industrial ecosystems in resource-intensive environments.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100171"},"PeriodicalIF":0.0,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145320087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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 learning and policy optimization approach for supply chain order classification 供应链订单分类的深度学习和策略优化方法

Supply Chain Analytics

Pub Date : 2025-09-29 DOI: 10.1016/j.sca.2025.100166

Ramakrishna Garine , Ripon K. Chakrabortty

Timely delivery is a critical performance metric in supply chain management, yet achieving consistent on-time delivery has become increasingly challenging in the face of global uncertainties and complex logistics networks. Recent disruptions, such as pandemics, extreme weather events, and geopolitical conflicts, have exposed vulnerabilities in supply chains, resulting in frequent delivery delays. While traditional heuristics and simple statistical methods have proven inadequate to capture the myriad factors that contribute to delays in modern supply chains, Machine learning (ML) and Deep Learning (DL) approaches have emerged as powerful tools to improve the accuracy and reliability of delivery delay prediction. Consequently, this study presents a hybrid predictive framework that integrates DL models with Reinforcement Learning (RL) to improve binary classification of order status (on-time vs. late). We first benchmark several DL architectures, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bi-LSTM, and Stacked LSTM, enhanced with regularization and extended training epochs, alongside a fine-tuned eXtreme Gradient Boost (XGBoost) model. These models are evaluated using accuracy, precision, recall, and the F1-score, with Bi-LSTM and Stacked LSTM achieving strong generalization performance. Building on this, we deploy a Proximal Policy Optimization (PPO) agent that incorporates deep learning outputs as part of its observation space. The RL agent uses a reward-based feedback loop to improve adaptability under dynamic conditions. Experimental results show that the hybrid DL-RL model achieves superior classification accuracy and an F1-score greater than 0.99, outperforming standalone methods. Although the PPO agent alone struggled with detecting minorities due to imbalance, integrating DL features mitigated this limitation. The findings support the use of hybrid architectures for real-time order status prediction and provide a scalable pathway for intelligent supply chain decision making. Future work will address class imbalance and enhance policy robustness through cost-sensitive and explainable RL strategies.

及时交货是供应链管理的关键绩效指标，但面对全球不确定性和复杂的物流网络，实现一致的准时交货变得越来越具有挑战性。最近的中断，如流行病、极端天气事件和地缘政治冲突，暴露了供应链的脆弱性，导致频繁的交货延迟。虽然传统的启发式方法和简单的统计方法已被证明不足以捕捉导致现代供应链延迟的无数因素，但机器学习（ML）和深度学习（DL）方法已成为提高交付延迟预测准确性和可靠性的强大工具。因此，本研究提出了一个混合预测框架，该框架将深度学习模型与强化学习（RL）集成在一起，以改进订单状态（准时与延迟）的二元分类。我们首先测试了几种深度学习架构，卷积神经网络（CNN），长短期记忆（LSTM）， Bi-LSTM和堆叠LSTM，通过正则化和扩展的训练时代增强，以及微调的极限梯度增强（XGBoost）模型。这些模型使用准确率、精密度、召回率和f1分数进行评估，其中Bi-LSTM和堆叠LSTM具有较强的泛化性能。在此基础上，我们部署了一个近端策略优化（PPO）代理，该代理将深度学习输出作为其观察空间的一部分。RL代理使用基于奖励的反馈回路来提高动态条件下的适应性。实验结果表明，混合DL-RL模型具有较好的分类精度，f1得分大于0.99，优于独立模型。虽然PPO代理由于不平衡而难以检测少数群体，但集成DL功能减轻了这一限制。研究结果支持使用混合架构进行实时订单状态预测，并为智能供应链决策提供可扩展的途径。未来的工作将通过成本敏感和可解释的RL策略来解决阶级不平衡问题并增强政策稳健性。

{"title":"A deep learning and policy optimization approach for supply chain order classification","authors":"Ramakrishna Garine , Ripon K. Chakrabortty","doi":"10.1016/j.sca.2025.100166","DOIUrl":"10.1016/j.sca.2025.100166","url":null,"abstract":"<div><div>Timely delivery is a critical performance metric in supply chain management, yet achieving consistent on-time delivery has become increasingly challenging in the face of global uncertainties and complex logistics networks. Recent disruptions, such as pandemics, extreme weather events, and geopolitical conflicts, have exposed vulnerabilities in supply chains, resulting in frequent delivery delays. While traditional heuristics and simple statistical methods have proven inadequate to capture the myriad factors that contribute to delays in modern supply chains, Machine learning (ML) and Deep Learning (DL) approaches have emerged as powerful tools to improve the accuracy and reliability of delivery delay prediction. Consequently, this study presents a hybrid predictive framework that integrates DL models with Reinforcement Learning (RL) to improve binary classification of order status (on-time vs. late). We first benchmark several DL architectures, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bi-LSTM, and Stacked LSTM, enhanced with regularization and extended training epochs, alongside a fine-tuned eXtreme Gradient Boost (XGBoost) model. These models are evaluated using accuracy, precision, recall, and the F1-score, with Bi-LSTM and Stacked LSTM achieving strong generalization performance. Building on this, we deploy a Proximal Policy Optimization (PPO) agent that incorporates deep learning outputs as part of its observation space. The RL agent uses a reward-based feedback loop to improve adaptability under dynamic conditions. Experimental results show that the hybrid DL-RL model achieves superior classification accuracy and an F1-score greater than 0.99, outperforming standalone methods. Although the PPO agent alone struggled with detecting minorities due to imbalance, integrating DL features mitigated this limitation. The findings support the use of hybrid architectures for real-time order status prediction and provide a scalable pathway for intelligent supply chain decision making. Future work will address class imbalance and enhance policy robustness through cost-sensitive and explainable RL strategies.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100166"},"PeriodicalIF":0.0,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An analytical framework for decision criteria validation in complex supply chains 复杂供应链中决策标准验证的分析框架

Supply Chain Analytics

Pub Date : 2025-09-29 DOI: 10.1016/j.sca.2025.100169

Frank Michael Theunissen, Shafiq Alam, Aymen Sajjad

Multi-Criteria Decision Making (MCDM) in supply chain management often applies rigorous methods for weighting and aggregation yet devotes little attention to the structural validity of the decision criteria that precede them. Even when organisations do not proceed to full MCDM model application, criteria are still elicited during problem structuring and used to justify initiative selection. This paper introduces a topological validation framework that addresses this asymmetry by representing criteria as a high-dimensional Decision Criteria Configuration (DCC). Using tools from Topological Data Analysis (TDA), we translate foundational MCDM axioms into measurable invariants: completeness through connectivity, non-redundancy through structural impact analysis, and logical consistency through cycle detection. Two industrial experiments demonstrate the framework’s utility. In a supply chain strategy-setting workshop, TDA diagnosed the criteria set underpinning initiative selection as a “conceptual monolith,” revealing significant redundancies and systemic feedback loops overlooked by conventional facilitation. In a subsequent inventory classification exercise, the audit resolved expert deadlock by reducing 32 proposed criteria to a minimal, non-redundant core of six operationally essential levers, providing an objective and defensible basis for moving forward. By transforming criteria sets into auditable decision architectures, this approach ensures that MCDM models and the initiatives they justify rest on a validated foundation before weighting or ranking alternatives. For managers, it functions as a pre-hoc “structural audit,” reducing redundancy, exposing hidden interdependencies, and directing resources toward criteria that genuinely drive strategic and operational outcomes.

供应链管理中的多准则决策（MCDM）通常采用严格的加权和汇总方法，但很少关注其前面决策准则的结构有效性。即使组织没有进行完整的MCDM模型应用，在问题构建过程中仍然会得出标准，并用于证明主动性选择的合理性。本文介绍了一个拓扑验证框架，通过将标准表示为高维决策标准配置（DCC）来解决这种不对称。使用拓扑数据分析（TDA）的工具，我们将基本的MCDM公理转化为可测量的不变量：通过连接实现完整性，通过结构影响分析实现非冗余，通过循环检测实现逻辑一致性。两个工业实验证明了该框架的实用性。在供应链战略制定研讨会上，TDA将支持主动性选择的标准集诊断为“概念性的大件”，揭示了传统促进所忽视的重大冗余和系统性反馈循环。在随后的盘存分类工作中，审计通过将32项拟议标准减少到最小的、非冗余的六个业务基本杠杆核心，解决了专家僵局，为下一步工作提供了客观和可靠的基础。通过将标准集转换为可审计的决策体系结构，该方法确保MCDM模型和它们所证明的计划在对备选方案进行加权或排序之前建立在经过验证的基础上。对于管理人员来说，它的功能是预先的“结构审计”，减少冗余，暴露隐藏的相互依赖性，并将资源导向真正驱动战略和操作结果的标准。

{"title":"An analytical framework for decision criteria validation in complex supply chains","authors":"Frank Michael Theunissen, Shafiq Alam, Aymen Sajjad","doi":"10.1016/j.sca.2025.100169","DOIUrl":"10.1016/j.sca.2025.100169","url":null,"abstract":"<div><div>Multi-Criteria Decision Making (MCDM) in supply chain management often applies rigorous methods for weighting and aggregation yet devotes little attention to the structural validity of the decision criteria that precede them. Even when organisations do not proceed to full MCDM model application, criteria are still elicited during problem structuring and used to justify initiative selection. This paper introduces a topological validation framework that addresses this asymmetry by representing criteria as a high-dimensional Decision Criteria Configuration (DCC). Using tools from Topological Data Analysis (TDA), we translate foundational MCDM axioms into measurable invariants: completeness through connectivity, non-redundancy through structural impact analysis, and logical consistency through cycle detection. Two industrial experiments demonstrate the framework’s utility. In a supply chain strategy-setting workshop, TDA diagnosed the criteria set underpinning initiative selection as a “conceptual monolith,” revealing significant redundancies and systemic feedback loops overlooked by conventional facilitation. In a subsequent inventory classification exercise, the audit resolved expert deadlock by reducing 32 proposed criteria to a minimal, non-redundant core of six operationally essential levers, providing an objective and defensible basis for moving forward. By transforming criteria sets into auditable decision architectures, this approach ensures that MCDM models and the initiatives they justify rest on a validated foundation before weighting or ranking alternatives. For managers, it functions as a pre-hoc “structural audit,” reducing redundancy, exposing hidden interdependencies, and directing resources toward criteria that genuinely drive strategic and operational outcomes.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100169"},"PeriodicalIF":0.0,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An analytical investigation of inflation’s effects on supply chain strategies 通货膨胀对供应链战略影响的分析研究

Supply Chain Analytics

Pub Date : 2025-09-26 DOI: 10.1016/j.sca.2025.100168

Kosar Akhavan Chayjan , Jafar Razmi , Saman Hassanzadeh Amin

Inflation poses significant challenges to supply chain operations by raising procurement and operational costs, dampening customer demand, and complicating decision-making for suppliers and retailers. This study investigates the optimization of supply chain strategies under inflationary pressures, addressing the inadequacy of traditional ordering and pricing approaches. We model a supply chain comprising one supplier and two retailers exposed to inflation-driven price volatility. Using an analytical optimization framework, eight scenarios are evaluated based in retailers’ adoption of hedging strategies through option contracts versus optimal order quantity strategies, while considering lead time dynamics and retailer competition. The results indicate that inflation profoundly influences optimal order quantities, supplier capacity, and the profitability of all supply chain participants. Full collaboration yields profit growth exceeding 1900 % compared to non-cooperative settings, whereas partial collaboration still results in gains of more than 25 %. Conversely, the least efficient scenarios incur profit losses of up to 95 %, highlighting the substantial penalty of insufficient coordination. Notably, the joint adoption of hedging strategies by both retailers yields the highest supply chain profit, particularly in environments characterized by longer lead times or elevated inflation rates. Hedging enables retailers to stabilize prices, sustain customer demand, and shield customers from inflation’s adverse effects. Furthermore, collaboration among retailers enhances overall supply chain resilience. This research offers actionable insights for practitioners aiming to aiming mitigate inflationary risks, emphasizing the essential roles of analytical planning, hedging, and coordination in supply chain management under inflationary conditions.

通货膨胀提高了采购和运营成本，抑制了客户需求，使供应商和零售商的决策复杂化，给供应链运营带来了重大挑战。本研究探讨通货膨胀压力下的供应链策略优化，以解决传统订货和定价方法的不足。我们建立了一个供应链模型，其中包括一个供应商和两个零售商，受到通货膨胀驱动的价格波动的影响。使用分析优化框架，在考虑交货时间动态和零售商竞争的情况下，基于零售商通过期权合约采用对冲策略与最优订单数量策略的八种情况进行了评估。研究结果表明，通货膨胀对供应链参与者的最优订货量、供应商能力和盈利能力产生了深远的影响。与非合作环境相比，完全合作产生的利润增长超过1900 %，而部分合作仍然产生超过25 %的收益。相反，效率最低的情况会导致高达95% %的利润损失，这突出了协调不足带来的巨大损失。值得注意的是，两家零售商联合采用对冲策略可以产生最高的供应链利润，特别是在交货时间较长或通货膨胀率较高的环境下。对冲使零售商能够稳定价格，维持顾客需求，并保护顾客免受通货膨胀的不利影响。此外，零售商之间的合作提高了整个供应链的弹性。本研究为旨在降低通胀风险的从业者提供了可操作的见解，强调了分析计划、对冲和协调在通胀条件下供应链管理中的重要作用。

{"title":"An analytical investigation of inflation’s effects on supply chain strategies","authors":"Kosar Akhavan Chayjan , Jafar Razmi , Saman Hassanzadeh Amin","doi":"10.1016/j.sca.2025.100168","DOIUrl":"10.1016/j.sca.2025.100168","url":null,"abstract":"<div><div>Inflation poses significant challenges to supply chain operations by raising procurement and operational costs, dampening customer demand, and complicating decision-making for suppliers and retailers. This study investigates the optimization of supply chain strategies under inflationary pressures, addressing the inadequacy of traditional ordering and pricing approaches. We model a supply chain comprising one supplier and two retailers exposed to inflation-driven price volatility. Using an analytical optimization framework, eight scenarios are evaluated based in retailers’ adoption of hedging strategies through option contracts versus optimal order quantity strategies, while considering lead time dynamics and retailer competition. The results indicate that inflation profoundly influences optimal order quantities, supplier capacity, and the profitability of all supply chain participants. Full collaboration yields profit growth exceeding 1900 % compared to non-cooperative settings, whereas partial collaboration still results in gains of more than 25 %. Conversely, the least efficient scenarios incur profit losses of up to 95 %, highlighting the substantial penalty of insufficient coordination. Notably, the joint adoption of hedging strategies by both retailers yields the highest supply chain profit, particularly in environments characterized by longer lead times or elevated inflation rates. Hedging enables retailers to stabilize prices, sustain customer demand, and shield customers from inflation’s adverse effects. Furthermore, collaboration among retailers enhances overall supply chain resilience. This research offers actionable insights for practitioners aiming to aiming mitigate inflationary risks, emphasizing the essential roles of analytical planning, hedging, and coordination in supply chain management under inflationary conditions.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100168"},"PeriodicalIF":0.0,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145266091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A systematic review of text mining analytics for supply chain risk management using online data 基于在线数据的供应链风险管理文本挖掘分析系统综述

Supply Chain Analytics

Pub Date : 2025-09-25 DOI: 10.1016/j.sca.2025.100167

Georgios Gelastopoulos, Christos Keramydas

Global supply chains are increasingly complex and vulnerable, requiring new approaches for detecting and managing risks. Text mining, a branch of natural language processing, can extract insights from unstructured online data such as news, reports, and social media. This paper presents a systematic review of 33 peer-reviewed studies on text mining in supply chain risk management (SCRM). The review addresses four research questions: (i) which types of online data are used and how their characteristics affect reliability and timeliness, (ii) which techniques are applied and with what trade-offs, (iii) how text mining contributes to risk identification, prediction, and mitigation, and (iv) what gaps and opportunities remain for future research. A bibliometric analysis is also conducted to highlight publication trends, contributors, and thematic clusters. The findings reveal that Twitter and news sources dominate, while methods range from sentiment analysis and topic modeling to advanced neural models such as BERT. Applications emphasize risk identification and visibility, with emerging work in predictive analytics and decision support. A conceptual framework is proposed linking unstructured data to risk management decisions. This review contributes to the literature by underscoring the value of real-time textual for improving visibility, agility, and resilience in complex supply chains.

全球供应链日益复杂和脆弱，需要新的方法来发现和管理风险。文本挖掘是自然语言处理的一个分支，可以从新闻、报道和社交媒体等非结构化在线数据中提取见解。本文系统回顾了33篇关于供应链风险管理（SCRM）中文本挖掘的同行评议研究。该审查解决了四个研究问题：(i)使用了哪些类型的在线数据以及它们的特征如何影响可靠性和及时性，（ii）应用了哪些技术以及进行了哪些权衡，（iii）文本挖掘如何有助于风险识别、预测和缓解，以及（iv）未来研究的差距和机会。还进行了文献计量分析，以突出出版趋势，贡献者和专题集群。研究结果显示，Twitter和新闻来源占主导地位，而方法范围从情感分析和主题建模到高级神经模型（如BERT）。应用程序强调风险识别和可见性，以及预测分析和决策支持方面的新兴工作。提出了一个将非结构化数据与风险管理决策联系起来的概念框架。这篇综述通过强调实时文本对提高复杂供应链中的可见性、敏捷性和弹性的价值，对文献做出了贡献。

{"title":"A systematic review of text mining analytics for supply chain risk management using online data","authors":"Georgios Gelastopoulos, Christos Keramydas","doi":"10.1016/j.sca.2025.100167","DOIUrl":"10.1016/j.sca.2025.100167","url":null,"abstract":"<div><div>Global supply chains are increasingly complex and vulnerable, requiring new approaches for detecting and managing risks. Text mining, a branch of natural language processing, can extract insights from unstructured online data such as news, reports, and social media. This paper presents a systematic review of 33 peer-reviewed studies on text mining in supply chain risk management (SCRM). The review addresses four research questions: (i) which types of online data are used and how their characteristics affect reliability and timeliness, (ii) which techniques are applied and with what trade-offs, (iii) how text mining contributes to risk identification, prediction, and mitigation, and (iv) what gaps and opportunities remain for future research. A bibliometric analysis is also conducted to highlight publication trends, contributors, and thematic clusters. The findings reveal that Twitter and news sources dominate, while methods range from sentiment analysis and topic modeling to advanced neural models such as BERT. Applications emphasize risk identification and visibility, with emerging work in predictive analytics and decision support. A conceptual framework is proposed linking unstructured data to risk management decisions. This review contributes to the literature by underscoring the value of real-time textual for improving visibility, agility, and resilience in complex supply chains.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100167"},"PeriodicalIF":0.0,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An analytical approach to blockchain-driven identity management in sustainable forest supply chains 可持续森林供应链中区块链驱动身份管理的分析方法

Supply Chain Analytics

Pub Date : 2025-09-19 DOI: 10.1016/j.sca.2025.100161

Robertas Damaševičius , Rytis Maskeliūnas

This study explores the application of Self-Sovereign Digital Identity (SSDI) and blockchain technology in forest supply chain management to improve traceability, sustainability and regulatory compliance. It addresses how these technologies can overcome the limitations of traditional identity management and improve forestry operations’ transparency, efficiency, and environmental accountability. An Ethereum-based blockchain framework was used for this study, focusing on metrics such as transaction throughput and latency. Experimental tests were conducted to analyze the performance of SSDI in forest supply chains, focusing on real-time data management and secure identity control. A framework aligned with the Forest 4.0 initiative was proposed to evaluate the efficacy of SSDI. The results show that the integration of SSDI with blockchain significantly improves traceability and sustainability within forest supply chains, with high transaction rates and reduced latency. The decentralized system improves transparency and trust, promotes efficient identity management among stakeholders, and improves compliance with environmental regulations. Our study is among the first to apply SSDI in forestry, advancing digital transformation in this sector. Demonstrating SSDI’s capacity to streamline data handling and boost traceability, it offers practical recommendations for stakeholders seeking sustainable and digitally secure supply chain management practices.

本研究探讨了自主数字身份（SSDI）和区块链技术在森林供应链管理中的应用，以提高可追溯性、可持续性和法规遵从性。它讨论了这些技术如何克服传统身份管理的局限性，提高林业经营的透明度、效率和环境问责制。本研究使用了基于以太坊的区块链框架，重点关注交易吞吐量和延迟等指标。通过实验测试，分析了SSDI在森林供应链中的性能，重点是实时数据管理和安全身份控制。提出了一个与森林4.0倡议相一致的框架来评估SSDI的有效性。结果表明，SSDI与区块链的集成显著提高了森林供应链的可追溯性和可持续性，提高了交易率，减少了延迟。分散式系统提高了透明度和信任，促进了利益相关者之间的有效身份管理，并改善了对环境法规的遵守。我们的研究是首批将SSDI应用于林业的研究之一，推动了该行业的数字化转型。它展示了SSDI简化数据处理和提高可追溯性的能力，为寻求可持续和数字安全供应链管理实践的利益相关者提供了实用建议。

{"title":"An analytical approach to blockchain-driven identity management in sustainable forest supply chains","authors":"Robertas Damaševičius , Rytis Maskeliūnas","doi":"10.1016/j.sca.2025.100161","DOIUrl":"10.1016/j.sca.2025.100161","url":null,"abstract":"<div><div>This study explores the application of Self-Sovereign Digital Identity (SSDI) and blockchain technology in forest supply chain management to improve traceability, sustainability and regulatory compliance. It addresses how these technologies can overcome the limitations of traditional identity management and improve forestry operations’ transparency, efficiency, and environmental accountability. An Ethereum-based blockchain framework was used for this study, focusing on metrics such as transaction throughput and latency. Experimental tests were conducted to analyze the performance of SSDI in forest supply chains, focusing on real-time data management and secure identity control. A framework aligned with the Forest 4.0 initiative was proposed to evaluate the efficacy of SSDI. The results show that the integration of SSDI with blockchain significantly improves traceability and sustainability within forest supply chains, with high transaction rates and reduced latency. The decentralized system improves transparency and trust, promotes efficient identity management among stakeholders, and improves compliance with environmental regulations. Our study is among the first to apply SSDI in forestry, advancing digital transformation in this sector. Demonstrating SSDI’s capacity to streamline data handling and boost traceability, it offers practical recommendations for stakeholders seeking sustainable and digitally secure supply chain management practices.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100161"},"PeriodicalIF":0.0,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145121269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A comprehensive bibliometric review of digitalization impacts on supply chain risk management 数字化对供应链风险管理影响的综合文献计量学综述

Supply Chain Analytics

Pub Date : 2025-09-18 DOI: 10.1016/j.sca.2025.100165

Hossein Ghanbari , Mostafa Shabani , Emran Mohammadi , Hamidreza Seiti

In the age of Industry 4.0, traditional supply chains are transforming into digital supply chains through the integration of advanced technologies such as the Internet of Things (IoT), Cloud Computing, Digital Twin, Artificial Intelligence (AI), and Blockchain Technologies. These technologies enable real-time data sharing, enhanced visibility, increased agility, robust data integrity and security, and more effective decision-making. As global supply chains face increasing uncertainties and complexities, the impact of digitalization on supply chain risk management has gained significant attention from both researchers and practitioners. However, despite this rising interest, the current research status in this field remains somewhat unclear. The existing body of work lacks a comprehensive overview of how digital technologies can influence risk management practices across different supply chain contexts. To address this gap, this paper aims to investigate the key research areas by applying bibliometric analysis to identify and visualize the underlying structure of the field of digitalization’s impact on supply chain risk management. We conducted a bibliometric review to analyze the structure and global trends related to the impact of digitalization on supply chain risk management, covering the period from 2000 to February 2024. A total of 1012 bibliographic records were initially retrieved from the Web of Science databases, with 1001 English-language records retained for analysis to ensure consistency and accessibility. Using bibliometric analyses, we examined key trends, topics, and interrelationships within the literature, providing insights into how research in this area has evolved and potential future directions it may take. The findings of this study contribute to a deeper understanding of current patterns and knowledge gaps, offering a foundation for further research efforts in this field.

在工业4.0时代，通过物联网（IoT）、云计算、数字孪生（digital Twin）、人工智能（AI）、区块链技术等先进技术的融合，传统供应链正在向数字供应链转型。这些技术能够实现实时数据共享、增强可见性、提高敏捷性、强大的数据完整性和安全性，以及更有效的决策。随着全球供应链面临越来越多的不确定性和复杂性，数字化对供应链风险管理的影响受到了研究者和实践者的极大关注。然而，尽管人们对该领域的兴趣日益浓厚，但目前该领域的研究现状仍不明朗。现有的工作缺乏对数字技术如何影响不同供应链背景下的风险管理实践的全面概述。为了解决这一差距，本文旨在通过应用文献计量学分析来调查关键研究领域，以识别和可视化数字化对供应链风险管理影响领域的潜在结构。我们进行了文献计量分析，分析了2000年至2024年2月期间数字化对供应链风险管理影响的结构和全球趋势。最初从Web of Science数据库中检索了总共1012个书目记录，其中保留了1001个英文记录进行分析，以确保一致性和可访问性。使用文献计量学分析，我们检查了文献中的关键趋势、主题和相互关系，为该领域的研究如何发展和未来可能采取的潜在方向提供了见解。本研究的发现有助于加深对当前模式和知识差距的理解，为该领域的进一步研究奠定了基础。

{"title":"A comprehensive bibliometric review of digitalization impacts on supply chain risk management","authors":"Hossein Ghanbari , Mostafa Shabani , Emran Mohammadi , Hamidreza Seiti","doi":"10.1016/j.sca.2025.100165","DOIUrl":"10.1016/j.sca.2025.100165","url":null,"abstract":"<div><div>In the age of Industry 4.0, traditional supply chains are transforming into digital supply chains through the integration of advanced technologies such as the Internet of Things (IoT), Cloud Computing, Digital Twin, Artificial Intelligence (AI), and Blockchain Technologies. These technologies enable real-time data sharing, enhanced visibility, increased agility, robust data integrity and security, and more effective decision-making. As global supply chains face increasing uncertainties and complexities, the impact of digitalization on supply chain risk management has gained significant attention from both researchers and practitioners. However, despite this rising interest, the current research status in this field remains somewhat unclear. The existing body of work lacks a comprehensive overview of how digital technologies can influence risk management practices across different supply chain contexts. To address this gap, this paper aims to investigate the key research areas by applying bibliometric analysis to identify and visualize the underlying structure of the field of digitalization’s impact on supply chain risk management. We conducted a bibliometric review to analyze the structure and global trends related to the impact of digitalization on supply chain risk management, covering the period from 2000 to February 2024. A total of 1012 bibliographic records were initially retrieved from the Web of Science databases, with 1001 English-language records retained for analysis to ensure consistency and accessibility. Using bibliometric analyses, we examined key trends, topics, and interrelationships within the literature, providing insights into how research in this area has evolved and potential future directions it may take. The findings of this study contribute to a deeper understanding of current patterns and knowledge gaps, offering a foundation for further research efforts in this field.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100165"},"PeriodicalIF":0.0,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145266092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A textual analytics approach to sustainable supply chain dynamics in European maritime logistics 欧洲海运物流可持续供应链动态的文本分析方法

Supply Chain Analytics

Pub Date : 2025-09-17 DOI: 10.1016/j.sca.2025.100163

George R. Dimakis, George Tsironis, Konstantinos P. Tsagarakis, Yannis Marinakis

This paper offers a comprehensive analysis of 871 European maritime firms, focusing on the spatial distribution of their headquarters, workforce demographics and digital footprint, as measured by LinkedIn follower metrics. To complement the quantitative data, Latent Dirichlet Allocation (LDA) was employed for text mining analysis on company LinkedIn descriptions, revealing emergent themes in innovation, customer-centric philosophy and global integration. The results point to a strong regional concentration of firms in Great Britain and the Netherlands, reflecting historical marine legacies and robust port infrastructures. Furthermore, the prevalence of small to medium-sized enterprises (SMEs) highlights the industry’s fragmented yet resilient structure, while digital presence remains uneven across firm sizes, with only a minority achieving substantial influence and visibility on social media. To summarize, these insights suggest that maritime logistics holds potential to drive systemic improvements in operational coordination, regional development, and global trade connectivity. Enhancing its integration could support more eﬀicient supply chains, mitigate regional disparities, and bolster the industry’s global competitiveness.

本文对871家欧洲海事公司进行了全面分析，重点关注其总部的空间分布、劳动力人口统计和数字足迹（以LinkedIn关注者指标衡量）。为了补充定量数据，使用潜在狄利克雷分配（Latent Dirichlet Allocation， LDA）对公司LinkedIn描述进行文本挖掘分析，揭示了创新、以客户为中心的理念和全球整合方面的新兴主题。研究结果表明，英国和荷兰的公司在区域上高度集中，这反映了历史上的海洋遗产和强大的港口基础设施。此外，中小企业（SMEs）的普遍存在凸显了该行业碎片化但具有弹性的结构，而不同企业规模的数字存在仍然不均衡，只有少数企业在社交媒体上获得了实质性的影响力和知名度。总而言之，这些见解表明，海上物流具有推动业务协调、区域发展和全球贸易连通性系统性改善的潜力。加强其整合可以支持更高效的供应链，缓解地区差异，并增强该行业的全球竞争力。

{"title":"A textual analytics approach to sustainable supply chain dynamics in European maritime logistics","authors":"George R. Dimakis, George Tsironis, Konstantinos P. Tsagarakis, Yannis Marinakis","doi":"10.1016/j.sca.2025.100163","DOIUrl":"10.1016/j.sca.2025.100163","url":null,"abstract":"<div><div>This paper offers a comprehensive analysis of 871 European maritime firms, focusing on the spatial distribution of their headquarters, workforce demographics and digital footprint, as measured by LinkedIn follower metrics. To complement the quantitative data, Latent Dirichlet Allocation (LDA) was employed for text mining analysis on company LinkedIn descriptions, revealing emergent themes in innovation, customer-centric philosophy and global integration. The results point to a strong regional concentration of firms in Great Britain and the Netherlands, reflecting historical marine legacies and robust port infrastructures. Furthermore, the prevalence of small to medium-sized enterprises (SMEs) highlights the industry’s fragmented yet resilient structure, while digital presence remains uneven across firm sizes, with only a minority achieving substantial influence and visibility on social media. To summarize, these insights suggest that maritime logistics holds potential to drive systemic improvements in operational coordination, regional development, and global trade connectivity. Enhancing its integration could support more eﬀicient supply chains, mitigate regional disparities, and bolster the industry’s global competitiveness.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100163"},"PeriodicalIF":0.0,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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 and fractional packing framework for routing and scheduling in healthcare waste supply chains 用于医疗废物供应链中路由和调度的深度强化学习和分级包装框架

Supply Chain Analytics

Pub Date : 2025-09-16 DOI: 10.1016/j.sca.2025.100164

Norhan Khallaf , Osama Abdel‑Raouf , Mohiy Hadhoud , Mohamed Dawam , Ahmed Kafafy

Artificial intelligence (AI) is increasingly utilized in healthcare logistics, including automated systems for collecting hazardous medical waste from hospitals under strict time and capacity constraints. This study compares three routing algorithms: (1) Google Maps Destination using an application programming interface (API), (2) hybrid clustering with Deep Q-Network (DQN), and (3) a hybrid method combining clustering, the fractional knapsack strategy, and DQN. These algorithms aim to optimize route planning and scheduling for medical waste collection vehicles operating under real-world constraints such as limited vehicle capacity and fixed service windows. The routing problem is modeled as both a capacitated vehicle routing problem (CVRP) and a CVRP with time windows (CVRPTW), capturing complexities. A multi-trip routing strategy is integrated into the promising algorithms to assess its impact on performance metrics, including capacity utilization, travel distance, total operational time, and number of trips. Experimental results indicate hybrid approach with clustering, fractional knapsack, and DQN outperforms others. It achieved capacity utilization rates of 96.47 percent for CVRP and 76.01 % for CVRPTW, requiring six vehicles, a 25 % reduction compared to the Google Maps API method, while matching the performance of clustering with DQN under time constraints. The CVRP model improved capacity utilization by 28.9 % over Google Maps API and 85.1 % over clustering with DQN. Although travel distance increased slightly (0.61 % in CVRP and 7.2 % in CVRPTW), total operational time was reduced by 7.6 and 4.6 %. The proposed model also minimized extra trips, requiring none for CVRP and only one for CVRPTW, compared to two additional trips needed by clustering with DQN in both scenarios. These findings highlight the hybrid approach as a robust, efficient solution for medical waste transportation under complex conditions.

人工智能（AI）越来越多地用于医疗保健物流，包括在严格的时间和能力限制下从医院收集危险医疗废物的自动化系统。本研究比较了三种路由算法：(1)谷歌使用应用程序编程接口（API）映射目的地，(2)与Deep Q-Network （DQN）混合聚类，(3)结合聚类，分数背包策略和DQN的混合方法。这些算法旨在优化在车辆容量有限和固定服务窗口等现实约束下运行的医疗废物收集车辆的路线规划和调度。将路径问题建模为有能力车辆路径问题（CVRP）和带时间窗口的车辆路径问题（CVRPTW），以捕获复杂性。将多行程路由策略集成到有前途的算法中，以评估其对性能指标的影响，包括容量利用率、行程距离、总操作时间和行程数。实验结果表明，基于聚类、分数背包和DQN的混合方法优于其他方法。CVRP的容量利用率为96.47%，CVRPTW的容量利用率为76.01 %，需要6辆车，与谷歌Maps API方法相比降低了25 %，同时在时间限制下与DQN的聚类性能相当。CVRP模型比谷歌Maps API提高了28.9 %的容量利用率，比DQN集群提高了85.1% %的容量利用率。虽然旅行距离略有增加（CVRP为0.61 %，CVRPTW为7.2 %），但总操作时间分别减少了7.6和4.6 %。所提出的模型还最小化了额外的行程，CVRP不需要额外的行程，CVRPTW只需要一次行程，相比之下，在两种情况下，使用DQN聚类都需要额外的两次行程。这些发现突出表明，混合方法是复杂条件下医疗废物运输的一种稳健、有效的解决方案。

{"title":"A deep reinforcement learning and fractional packing framework for routing and scheduling in healthcare waste supply chains","authors":"Norhan Khallaf , Osama Abdel‑Raouf , Mohiy Hadhoud , Mohamed Dawam , Ahmed Kafafy","doi":"10.1016/j.sca.2025.100164","DOIUrl":"10.1016/j.sca.2025.100164","url":null,"abstract":"<div><div>Artificial intelligence (AI) is increasingly utilized in healthcare logistics, including automated systems for collecting hazardous medical waste from hospitals under strict time and capacity constraints. This study compares three routing algorithms: (1) Google Maps Destination using an application programming interface (API), (2) hybrid clustering with Deep Q-Network (DQN), and (3) a hybrid method combining clustering, the fractional knapsack strategy, and DQN. These algorithms aim to optimize route planning and scheduling for medical waste collection vehicles operating under real-world constraints such as limited vehicle capacity and fixed service windows. The routing problem is modeled as both a capacitated vehicle routing problem (CVRP) and a CVRP with time windows (CVRPTW), capturing complexities. A multi-trip routing strategy is integrated into the promising algorithms to assess its impact on performance metrics, including capacity utilization, travel distance, total operational time, and number of trips. Experimental results indicate hybrid approach with clustering, fractional knapsack, and DQN outperforms others. It achieved capacity utilization rates of 96.47 percent for CVRP and 76.01 % for CVRPTW, requiring six vehicles, a 25 % reduction compared to the Google Maps API method, while matching the performance of clustering with DQN under time constraints. The CVRP model improved capacity utilization by 28.9 % over Google Maps API and 85.1 % over clustering with DQN. Although travel distance increased slightly (0.61 % in CVRP and 7.2 % in CVRPTW), total operational time was reduced by 7.6 and 4.6 %. The proposed model also minimized extra trips, requiring none for CVRP and only one for CVRPTW, compared to two additional trips needed by clustering with DQN in both scenarios. These findings highlight the hybrid approach as a robust, efficient solution for medical waste transportation under complex conditions.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"12 ","pages":"Article 100164"},"PeriodicalIF":0.0,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0