.png){kind=icon}
.png){kind=icon}
Return
Service composition and optimal selection in cloud remanufacturing considering quality heterogeneity
.png){kind=icon}
PRE
AI
L
W
F
W
DOI：10.1016/j.jmsy.2026.04.035.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Cloud remanufacturing leverages advanced digital technologies to enable the intelligent and flexible reuse of end-of-life products. In practice, however, the quality of returned products varies significantly, and this heterogeneity critically affects remanufacturing efficiency and resource allocation. Aiming to solve the problem of quality heterogeneity, this study proposes a novel service composition and optimal selection model that explicitly considers quality differences among returned products. The model introduces a structured quality grading framework, decomposing remanufacturing tasks into subtask cells according to distinct quality grades, thus allowing for fine-grained service matching and resource allocation tailored to specific quality characteristics. To further enhance robustness under inevitable quality grading uncertainties, a resilience index is introduced as a quality-of-service indicator, quantifying the system's adaptability to grading inaccuracies. A multi-objective chaotic evolution optimization algorithm is developed to solve the resulting optimization problem, incorporating tree-based non-dominated sorting and a reference-point-based selection strategy. Comprehensive experiments, using five performance metrics and comparisons with four benchmark multi-objective evolutionary algorithms, demonstrate that the proposed approach consistently outperforms existing methods in convergence efficiency, solution quality, and system stability. This research offers a practical and effective solution for qualityheterogeneous service composition, advancing decision-making precision and operational efficiency in cloud remanufacturing systems.
Keywords:
Cloud remanufacturing
Service composition and optimal selection
Quality heterogeneity
Resilience index
Multi-objective chaotic evolution optimization
Journal
IF:
14.2
Papers:
2.6K
Citations:
1.6W
Organization
Cited Papers