Abstract: This paper investigates the aircraft maintenance task scheduling problem, integrating labor costs and uncertainty costs into a unified optimization framework. A multi-objective optimization model for maintenance duration and robustness, named NSGA-II-Adaptive, is proposed. The model employs a novel approach combining critical path weights with buffer attenuation effects to define robustness values, and enhances the crossover and mutation processes of NSGA-II through adaptive methods. The algo-rithm was tested on benchmark datasets of various scales and compared with NSGA-IIs, NSGA-II-LSA, and the standard NSGA-II. Experimental results demonstrate that the proposed algorithm outperforms the counterparts in four performance met-rics: convergence speed, number of non-dominated solutions (NDS), spacing metric (SP), and coverage metric (C). Further vali-dation through a real-world aircraft maintenance case study reveals that the algorithm reduces comprehensive deviations by 63%, 77.6%, and 77.9% compared to NSGA-IIs, NSGA-II-LSA, and NSGA-II respectively. These findings confirm the model's prac-tical applicability and effectiveness in addressing real-world maintenance scheduling challenges.

Key words: Aircraft Maintenance, Task Scheduling, Multi-objective Optimization, Scheduled Maintenance, NSGA-II