.png){kind=icon}
.png){kind=icon}
Return
A novel robust multi-objective evolutionary optimization algorithm based on surviving rate
.png){kind=icon}
OA
AI
DOI：10.1007/s40747-025-01822-y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-objective evolutionary optimization is widely utilized in industrial design. Despite the success of multi-objective evolutionary optimization algorithms in addressing complex optimization problems, research focusing on input disturbances remains limited. In many manufacturing processes, design parameters are vulnerable to random input disturbances, resulting in products that often perform less effectively than anticipated. To address this issue, we propose a novel robust multi-objective evolutionary optimization algorithm based on the concept of survival rate. The algorithm comprises two stages: the evolutionary optimization stage and the construction stage of the robust optimal front. In the former stage, we introduce the survival rate as a new optimization objective. Subsequently, we seek a robust optimal front that concurrently addresses convergence and robustness by employing a non-dominated sorting approach. Furthermore, we propose a precise sampling method and a random grouping mechanism to accurately recover solutions resilient to real noise while ensuring population's diversity. In the latter stage, we introduce a performance measure that integrates both robustness and convergence to guide the construction of the robust optimal front. Experimental results demonstrate the superiority of the proposed algorithm in terms of both convergence and robustness compared to existing approaches under noisy conditions.
Keywords:
Multiobjective optimization
Robust optimization
Evolutionary optimization
Uncertainty
Journal
IF:
4.6
Papers:
2.1K
Citations:
6.6K