摘要
为了提高故障分类的准确性,提出了一种混沌差分进化模糊C-均值故障识别方法(CDEFCM,cha-otic differential evolution fuzzy C-mean)。该方法利用差分进化算法高效的全局搜索能力以及混沌序列的均匀遍历特性,克服了模糊C-均值算法(FCM,fuzzy C-mean)对初始值敏感的缺点及遗传算法易收敛到局部极值点的缺陷,用该方法进行故障聚类分析,可以准确地识别故障。以某飞控系统舵回路常见故障为例进行了仿真验证,结果表明该方法能有效地识别出故障。
In order to improve the accuracy of fault classification, a chaotic differential evolution fuzzy C-mean （CDEFCM） fault diagnosis scheme is presented. Due to the efficient global search capability of differential evolution algorithm and the traversal characteristic of chaotic sequence, this method can overcome the problems of initial value sensitiveness with fuzzy C-mean algorithm （FCM） and local convergence with genetic algorithm. Through faults clustering analysing, this algorithm can fulfill failure recognition. The proposed scheme is applied to aircraft actuator system fault diagnsis. The results show that the proposed method can effectively identify actuator failures.
出处
《测控技术》
CSCD
北大核心
2009年第5期90-93,共4页
Measurement & Control Technology
关键词
故障诊断
舵回路
混沌差分进化
FCM算法
fault diagnosis
actuator loop
chaotic differential evolution
FCM algorithm
