Swarm and Evolutionary Computation最新文献_第7页

An enhanced consensus-guided homotopy-inspired QPSO method for multimodal optimization problems 多模态优化问题的改进共识引导同伦启发QPSO方法

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-07-28 DOI: 10.1016/j.swevo.2026.102493

Feng-Jiao Zheng, Yong-Feng Zhang, Zhenbin Zhang

{"title":"An enhanced consensus-guided homotopy-inspired QPSO method for multimodal optimization problems","authors":"Feng-Jiao Zheng, Yong-Feng Zhang, Zhenbin Zhang","doi":"10.1016/j.swevo.2026.102493","DOIUrl":"10.1016/j.swevo.2026.102493","url":null,"abstract":"<div><div>Quantum-behaved particle swarm optimization (QPSO) is a prominent swarm intelligence algorithm that has been widely used to solve diverse kinds of optimization problems. QPSO employs a quantum-inspired probabilistic position update mechanism driven by swarm cooperation. However, QPSO still suffers from premature convergence and insufficient optimization accuracy when tackling complex multimodal optimization problems. To deal with these disadvantages, an enhanced consensus-guided homotopy-inspired QPSO (CGQPSO) algorithm is presented. In the proposed CGQPSO, a consensus-guided framework is designed to improve the search efficiency. Additionally, in order to improve the optimization accuracy of the algorithm, a local refinement mechanism is incorporated after the consensus stage. Furthermore, to better balance the exploration ability of individuals and the global search capability of the algorithm, the local attractor is redefined based on the inspiration from the homotopy continuation method. For maintaining the diversity of the population, the bidirectional quantum sampling is applied to update individual locations. According to the results obtained by CGQPSO and nine other optimization algorithms on 29 benchmark functions under different dimensions, it is found that CGQPSO significantly outperforms the compared algorithms in approximately 80 % of the statistical comparisons across all evaluated dimensions, as further confirmed by the Friedman test. The proposed CGQPSO demonstrates its potential for solving complex multimodal optimization problems.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102493"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A topology-aware direction-adaptive multitask evolutionary algorithm 拓扑感知方向自适应多任务进化算法

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-08-10 DOI: 10.1016/j.swevo.2026.102497

Yuxin Chen, Lizhong Yao, Rui Li, Pengjie Qin, Peng Jiang, Jun Yi

{"title":"A topology-aware direction-adaptive multitask evolutionary algorithm","authors":"Yuxin Chen, Lizhong Yao, Rui Li, Pengjie Qin, Peng Jiang, Jun Yi","doi":"10.1016/j.swevo.2026.102497","DOIUrl":"10.1016/j.swevo.2026.102497","url":null,"abstract":"<div><div>In evolutionary multitask optimization, search-direction-based knowledge transfer has attracted increasing attention because it can exploit directional information generated during evolution to promote cross-task collaboration. Although such methods can effectively use search information generated during evolution, existing designs still have limitations in transfer triggering, direction reliability, and coordinate alignment. Therefore, directional information from other tasks may be imposed on target individuals that are not yet suitable to receive it, and the received information may be ineffective for these individuals. To address the above problems, this paper proposes a topology-aware direction-adaptive multitask evolutionary algorithm (TADA-MTEA). First, an adaptive local aggregation assessment mechanism is developed to screen target individuals suitable for receiving cross-task information. It uses the shared-nearest-neighbor measure to quantify neighborhood compactness and dynamically adjusts the compactness criterion according to the cross-task transfer success rate, thereby determining whether each target individual is suitable for receiving cross-task information. Second, an evolutionary direction fusion and alignment mechanism is constructed to transform directional information from other tasks into reliable transfer directions adapted to the target individual. According to the reliability of the incoming directional information, it adaptively fuses the gradient-guided direction with the local best-guided differential vector, and then maps the fused direction to the target local coordinate system using the rotation estimated by orthogonal Procrustes analysis. Finally, experimental results on benchmark suites and real-world cases show that TADA-MTEA achieves competitive and robust performance across different multitask scenarios.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102497"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148730825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Q-learning-driven multi-objective algorithm for dynamic hybrid flow shop rescheduling with setup and new job arrivals 基于q学习的动态混合流水车间重调度多目标算法

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-07-28 DOI: 10.1016/j.swevo.2026.102495

Yaju Chen, Junqing Li, Huilin Wang, Yeqiu Yan, Li Wei, Haonan Song

{"title":"A Q-learning-driven multi-objective algorithm for dynamic hybrid flow shop rescheduling with setup and new job arrivals","authors":"Yaju Chen, Junqing Li, Huilin Wang, Yeqiu Yan, Li Wei, Haonan Song","doi":"10.1016/j.swevo.2026.102495","DOIUrl":"10.1016/j.swevo.2026.102495","url":null,"abstract":"<div><div>In real production environments, sequence-dependent setup times and the random arrival of new jobs often coexist. To this end, this paper investigates the dynamic rescheduling problem in a hybrid flow shop with sequence-dependent setup times and new job arrivals,which is solved by a dynamic Q-learning enhanced non-dominated sorting genetic algorithm (DQ-NSGA-II). First, a multi-objective optimization model is constructed, aiming to simultaneously optimize total energy cost, carbon trading cost, and weighted earliness/tardiness penalties. Second, the decoding process is restructured for dynamic job insertions, and a hybrid initialization strategy combining multi-objective heuristics with random solutions is designed to balance exploration and exploitation. Third, an adaptive crowding distance mechanism is introduced to improve the distribution uniformity of the Pareto optimal set in the objective space. Furthermore, to effectively address dynamic disruptions, a partial rescheduling strategy is designed, and a stability metric is incorporated to balance the trade-off between scheduling performance improvement and system stability. Finally, the proposed DQ-NSGA-II is compared in detail with three high-performance algorithms. Experimental results demonstrate that the proposed method can generate high-quality and well-distributed Pareto optimal sets, exhibiting superior responsiveness and stability.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102495"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148642248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A multi-agent framework powered by large language models for automatic heuristic design 一个由大型语言模型支持的多智能体框架，用于自动启发式设计

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-07-26 DOI: 10.1016/j.swevo.2026.102487

Jiancong Yang, Xinan Chen, Rong Qu, Zishang Qiu, Ruibin Bai

{"title":"A multi-agent framework powered by large language models for automatic heuristic design","authors":"Jiancong Yang, Xinan Chen, Rong Qu, Zishang Qiu, Ruibin Bai","doi":"10.1016/j.swevo.2026.102487","DOIUrl":"10.1016/j.swevo.2026.102487","url":null,"abstract":"<div><div>Heuristic design for combinatorial optimization problems has long relied on human expertise and repeated trial-and-error. Recent large language model (LLM)-based approaches to Automatic Heuristic Design have made notable progress. Most existing methods still remain within performance-driven generate-and-evaluate loops, where mechanism-level validation and cross-generational knowledge accumulation are only weakly developed. To address this limitation, we propose ARES (AI Research Ensemble System). ARES organizes Automatic Heuristic Design as a validation-driven and knowledge-accumulative multi-module collaborative workflow. It consists of a Theorist for mechanism-level analysis, an Experimenter for candidate generation, and a Critic module for structural ablation and parameter-scanning-based validation. It also introduces a Strategy Table to support cross-generational inheritance of mechanism-level design experience. Experiments on six representative combinatorial optimization problems show that ARES attains the best mean performance among the compared methods under the reported settings. Across these six structurally diverse problems, ARES also shows consistent improvements within the evaluated benchmark set.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102487"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148642695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A hybrid genetic algorithm for the Dual-Resource Constrained Job Shop Scheduling Problem with Mobile Robots 移动机器人双资源约束作业车间调度问题的混合遗传算法

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-08-06 DOI: 10.1016/j.swevo.2026.102494

Yu Wang, Hu Qin, Yuwen Li, Nan Huang

{"title":"A hybrid genetic algorithm for the Dual-Resource Constrained Job Shop Scheduling Problem with Mobile Robots","authors":"Yu Wang, Hu Qin, Yuwen Li, Nan Huang","doi":"10.1016/j.swevo.2026.102494","DOIUrl":"10.1016/j.swevo.2026.102494","url":null,"abstract":"<div><div>This paper investigates the Dual-Resource Constrained Job Shop Scheduling Problem with Mobile Robots (DRCJSPMR), where machine processing, worker allocation, and robot transportation are tightly coupled. The strong interdependence among these resources makes the problem significantly more challenging than classical job shop scheduling. To address this problem, we first formulate a mixed-integer linear programming (MILP) model, and then develop a topology-driven solution framework that exploits the directed acyclic graph (DAG) structure of scheduling constraints. The problem is reformulated as the search for feasible topological sequences combined with resource assignment decisions, enabling an efficient decoding procedure that generates schedules with earliest feasible start times under precedence constraints. Based on this representation, a hybrid genetic algorithm (HGA) is designed to effectively explore the structured search space, incorporating problem-specific operators and a transport–processing combination strategy to further reduce the search space and improve computational efficiency. Computational experiments on 32 benchmark JSPMR instances and 80 large-scale instances demonstrate that the proposed approach achieves high solution quality and efficiency. Compared with existing methods, the proposed acceleration strategy reduces computational time by approximately 26% and improves the objective value by about 5%, while exhibiting a significantly faster convergence rate.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102494"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148730830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hybrid microgrid optimization for smart cities using Botox algorithm and motif-based heterogeneous attention network 基于Botox算法和基于图案的异构关注网络的智慧城市混合微电网优化

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-07-27 DOI: 10.1016/j.swevo.2026.102492

T. Sathesh Kumar, T. Venkatesan, Selvakumar K

{"title":"Hybrid microgrid optimization for smart cities using Botox algorithm and motif-based heterogeneous attention network","authors":"T. Sathesh Kumar, T. Venkatesan, Selvakumar K","doi":"10.1016/j.swevo.2026.102492","DOIUrl":"10.1016/j.swevo.2026.102492","url":null,"abstract":"<div><div>Hybrid Microgrid Systems (HMGSs), which integrate solar, wind, biomass, and conventional power grid (PG) resources, are essential for developing sustainable, efficient, and resilient energy infrastructures in smart cities. However, their large-scale deployment is challenged by grid stability issues, energy management (EM) complexities, and storage limitations, particularly when renewable energy (RE) output is insufficient or highly variable. To overcome these drawbacks, this paper suggests a hybrid BOA-MBHAN technique that incorporates the Botox Optimization Algorithm (BOA) with a Motif-Based Heterogeneous Graph Attention Network (MBHAN). The framework enhances the economic, operational, and environmental performance of HMGSs by improving energy distribution, increasing reliability, and reducing both the Levelized Cost of Energy (LCOE) and carbon emissions. BOA has been used in adaptive control and optimization of grid stability through dynamic response to changes in power supply and MBHAN is used to predict the system performance under different operating conditions to maintain balanced energy demand and optimal energy flow. The suggested approach is implemented in MATLAB and compared to existing approaches, such as African Vultures Optimization Approach (AVOA), Modified Bio-Inspired Optimization Algorithm (MBIOA), Particle Swarm Optimization (PSO), Grasshopper Optimization Algorithm (GOA), and Adaptive Local Attractor-based Quantum Behaved PSO (ALA-QPSO). Comparative outcomes prove that the BOA-MBHAN framework improves cost-effectiveness and environmental sustainability, achieving an LCOE as low as $0.30/kWh and reducing CO<sub>2</sub> emissions to 199,016 kg/year, outperforming all competing techniques. These results validate the framework’s potential to support smarter, cleaner, and more resilient urban energy systems.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102492"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148657380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A fractional-order hybrid optimization algorithm for NARX motion modeling of pneumatic soft grippers 气动软爪NARX运动建模的分数阶混合优化算法

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-08-12 DOI: 10.1016/j.swevo.2026.102500

Zixin Huang, Junjie Lu, Ziang Wei, Peng Huang

{"title":"A fractional-order hybrid optimization algorithm for NARX motion modeling of pneumatic soft grippers","authors":"Zixin Huang, Junjie Lu, Ziang Wei, Peng Huang","doi":"10.1016/j.swevo.2026.102500","DOIUrl":"10.1016/j.swevo.2026.102500","url":null,"abstract":"<div><div>The intelligent grasping and sorting of phosphorus ores are challenging due to the irregular shapes and varying sizes of the ores. Traditional rigid robotic grippers exhibit limited adaptability in handling such materials without damage. Pneumatic soft robots, inspired by biological compliance, offer a promising alternative for flexible and adaptive grasping. This paper presents the design of a pneumatic soft gripper specifically developed for phosphorus ores (PSGPO) and investigates the modeling of its inherent nonlinear hysteresis behavior. An experimental platform is constructed to characterize the motion responses of the PSGPO under various pressure excitation patterns. Based on the collected data, a nonlinear autoregressive with exogenous inputs (NARX) model employing a neural network as the output function is established to capture the dynamic relationship between pneumatic input and bending displacement. To effectively train the neural network and optimize its high-dimensional parameters, a hybrid optimization strategy combining a fractional-order sparrow search algorithm with the Levenberg–Marquardt method (FO-SSA-LM) is proposed. The fractional-order memory mechanism enhances the global search capability, while the LM algorithm ensures rapid local convergence. Experimental results demonstrate that the proposed model accurately predicts the complex motion behaviors of the PSGPO. Compared with the LM and PSO-LM methods, the proposed FO-SSA-LM reduces the training-set RMSE by 29.05% and 21.81%, respectively. Furthermore, validation on multiple independent datasets confirms its generalizability.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102500"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148730827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GPU-accelerated Differential Evolution with gradient polishing and decorrelation-based convergence control 基于梯度抛光和去相关收敛控制的gpu加速差分进化

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-07-29 DOI: 10.1016/j.swevo.2026.102488

Adam Glick, Antonio Mastroberardino

{"title":"GPU-accelerated Differential Evolution with gradient polishing and decorrelation-based convergence control","authors":"Adam Glick, Antonio Mastroberardino","doi":"10.1016/j.swevo.2026.102488","DOIUrl":"10.1016/j.swevo.2026.102488","url":null,"abstract":"<div><div>Differential Evolution (DE) is widely used for global optimization in simulation-based parameter estimation, but its performance degrades when objective evaluations require solving stiff or unstable dynamical systems. In such settings, numerical divergence and stagnation can waste substantial computational effort and hinder convergence. To address this, we present a fully tensorized, GPU-accelerated optimization framework that tightly integrates global exploration with fine-grained local refinement. Central to our approach is the Batched GPU Solver of Ordinary Differential Equations (BGSODE), which introduces an alive-masking strategy to dynamically identify and terminate divergent trajectories during parallel population evaluation, effectively mitigating the costs of stiff dynamics. The framework is further enhanced by an elite gradient-based polishing phase governed by a data-driven, decorrelation-based stopping criterion that monitors the statistical independence of top solutions to avoid redundant evaluations. Computational experiments on nonlinear parameter estimation problems demonstrate that the proposed framework delivers robust optimization performance and achieves substantial speedups of up to <span><math><mrow><mn>55</mn><mo>×</mo></mrow></math></span> over conventional implementations. By accelerating both the evolutionary layer and the underlying simulation mechanics, the integrated method reduces classical differential evolution runtime by up to 98.2% without sacrificing solution accuracy.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102488"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148642252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A multi-source surrogate-assisted evolutionary algorithm for expensive optimization: An optinformatics perspective 昂贵优化的多源代理辅助进化算法：最优化视角

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-07-30 DOI: 10.1016/j.swevo.2026.102491

Laiqi Yu, Yinan Guo, Liang Feng, Zexuan Zhu, Ziqi Wei, Yaqing Hou

{"title":"A multi-source surrogate-assisted evolutionary algorithm for expensive optimization: An optinformatics perspective","authors":"Laiqi Yu, Yinan Guo, Liang Feng, Zexuan Zhu, Ziqi Wei, Yaqing Hou","doi":"10.1016/j.swevo.2026.102491","DOIUrl":"10.1016/j.swevo.2026.102491","url":null,"abstract":"<div><div>Surrogate-Assisted Evolutionary Algorithms (SAEAs) have emerged as a powerful paradigm for solving Expensive Optimization Problems (EOPs). However, existing SAEAs often struggle to fully exploit the evolutionary knowledge embedded in the limited historical data during the optimization process, which impedes their ability to locate high-quality solutions for complex EOPs. To address this challenge, this work develops a knowledge-driven framework for expensive optimization from an <em>optinformatics</em> perspective, aiming to extract implicit yet useful knowledge and adaptively utilize it to drive the evolutionary process. Accordingly, we propose a Multi-source Surrogate-Assisted Evolutionary Algorithm (MSAEA) that systematically synthesizes three types of evolutionary knowledge, namely performance, spatial, and temporal knowledge, extracted respectively from the objective space, decision space, and evolutionary sequence. MSAEA adaptively exploits this knowledge to drive three tailored optimization components: a two-stage global surrogate-guided search, an adaptive focusing search, and an adaptive diversity search. Extensive experiments on the classical benchmark problems, the CEC 2017 test suite, and real-world applications demonstrate that MSAEA significantly outperforms state-of-the-art SAEAs, achieving superior solution quality and robustness.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102491"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148642253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Risk-prediction-based robust multi-objective evolutionary algorithm for reverse supply chain with demand uncertainty 基于风险预测的需求不确定逆向供应链鲁棒多目标进化算法

IF 9.6 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2026-08-01 Epub Date: 2026-07-22 DOI: 10.1016/j.swevo.2026.102484

Honggui Han, Hao Zhou, Jingjing Wang, Ying Hou

{"title":"Risk-prediction-based robust multi-objective evolutionary algorithm for reverse supply chain with demand uncertainty","authors":"Honggui Han, Hao Zhou, Jingjing Wang, Ying Hou","doi":"10.1016/j.swevo.2026.102484","DOIUrl":"10.1016/j.swevo.2026.102484","url":null,"abstract":"<div><div>Reverse supply chain (RSC) planning is essential for sustainable resource recovery and circular economy. However, the uncertainty of recycling demand triggers cascading risk amplification across RSC networks, leading to cost escalation and recovery demand losses. To address this issue, a robust multi-objective evolutionary algorithm based on risk prediction (RMOEA-RP) is proposed, which can adaptively adjust evolutionary strategies to suppress the risk propagation. Firstly, a cascading risk predictor based on an autoregressive model is built to quantify the sequential propagation of demand uncertainty, enabling the evaluation of node risk backlog. Secondly, a time-aware adaptive evolutionary strategy is designed based on risk scenario similarity to accelerate the evolutionary process via transferring robust solutions under historical risk scenarios to the current scenario. Thirdly, a risk diversion strategy is introduced to refine the planning scheme prior to risk propagation through the reallocation of orders from high-risk nodes to low-load nodes. Finally, the comparative experiments are carried out and operational optimization results demonstrate that the RMOEA-RP can effectively suppress the cascading risk caused by the demand uncertainty, significantly reducing the total costs and demand losses of reverse supply chain planning.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"107 ","pages":"Article 102484"},"PeriodicalIF":9.6,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148642693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0