基于粒子群算法的诊断策略优化技术

Optimization of Hierarchical Diagnostic Strategy Based on Particle Swarm Algorithm

摘要:

针对复杂武器装备系统多层次、多功能的特点以及测试性设计这一重大需求,为解决当前普遍采用的诊断策略存在的灵活性差、多故障诊断与不确定性诊断能力弱等问题,提出了一种基于自适应离散粒子群算法的诊断策略优化生成算法;该算法对自适应离散粒子群算法进行改进,引入多样性指标、个体历史最差解、扩散聚合过程和自适应惯性权重等,通过迭代计算得到最优的诊断策略;最后给出了主要步骤,并通过实例验证了算法的可行性。

Abstract:

Aiming at the characteristics of complicated equipment of multi-hierarchy, multi-function and design for testability, optimization of hierarchical diagnostic strategy based on self-adaptive discrete particle swarm algorithm is studied in this paper. This algorithm improves the self-adaptive discrete particle swarm algorithm, introduces variety index, the worst solution of individual history, diffusion and polymerization process and self-adaptive inertia weight,then get the optimal diagnostic strategy by iterative computation. Finally, the main procedures are given, and experimental results show that the algorithm can reach an ideal trade-off between accuracy and computational complexity.