摘要
为提高航空电子部件模块级故障诊断精度,提出一种新的面向"软聚类"的局部多核学习(LMKL)-超限学习机(ELM)离线诊断方法。通过引入模糊C均值聚类对样本空间进行模糊划分,挖掘聚类内部多样性的同时,实现了对过学习的抑制;将模糊划分产生的隶属度信息融入LMKL-ELM的优化过程,运用基于初始-对偶混合优化问题的三步优化策略克服了局部核权重二次非凸的问题,在l1-范数与l2-范数约束下分别给出了相应的更新方法。将所提方法应用于某型机前端接收机,结果表明:与4种流行的多核诊断方法相比,该方法可有效避免漏警、抑制虚警,在l1-范数和l2-范数约束下,其诊断精度比其他方法的平均值分别提升了4.09%和5.13%。
To improve the accuracy of module-level fault diagnosis for avionics,a new off-line diagnosis method based on softclustering-sensitive Localized Multi-Kernel Learning(LMKL)and Extreme Learning Machine(ELM)is proposed.By introducing fuzzy C-means clustering to partition the sample space,the over-learning is suppressed while mining the diversity within the cluster.The membership information generated by the fuzzy partition is integrated into the optimization process of LMKLELM.A three-step optimization strategy based on the initial-dual hybrid optimization problem is used to overcome the quadratic non-convexity of the local kernel weights.The corresponding updating methods for these weights are given under l1-norm constraint and l2-norm constraint.The proposed method is applied to the front-end receiver.Compared with four popular multi-kernel diagnostic algorithms,the results show that the proposed method can effectively avoid missing alarm and suppress false alarm.The diagnostic accuracy is 4.09%higher in l1-norm and 5.13%higher in l2-norm than the average of other methods.
作者
朱敏
许爱强
李睿峰
戴金玲
ZHU Min;XU Aiqiang;LI Ruifeng;DAI Jinling(Naval Aviation University,Yantai 264001,China)
出处
《航空学报》
EI
CAS
CSCD
北大核心
2019年第12期202-214,共13页
Acta Aeronautica et Astronautica Sinica
基金
国家自然科学基金(11802338)
山东省自然科学基金(ZR2017MF036)~~
关键词
超限学习机
局部多核学习
模糊C均值聚类
故障诊断
航空电子
extreme learning machine
localized multiple kernel learning
fuzzy C-means clustering
fault diagnosis
avionic