.png){kind=icon}
.png){kind=icon}
Return
Risk-prediction-based robust multi-objective evolutionary algorithm for reverse supply chain with demand uncertainty
.png){kind=icon}
PRE
AI
H
H
J
DOI：10.1016/j.swevo.2026.102484.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Journal
IF:
8.5
Papers:
2.1K
Citations:
1.0W
Organization
No organization information available
Cited Papers