基于IAO-ELM的DC-DC电路软故障诊断  

Soft Fault Diagnosis of DC-DC Circuit Based on IAO-ELM

作　　者：黄郑 HUANG Zheng(School of Electrical and Information Engineering,Anhui University of Science&Technology,Huainan 232001,China)

机构地区：[1]安徽理工大学电气与信息工程学院,安徽淮南232000

出　　处：《电子质量》2024年第2期32-39,共8页Electronics Quality

摘　　要：针对DC-DC电路软故障诊断精确度差的问题,提出了一种基于改进的天鹰算法(IAO)-优化极限学习机(ELM)的故障诊断方法。采用变分模态分解的方法对原始的故障信号进行分解重构,提取时频域特征作为特征向量。使用SPM混沌映射、透镜反向学习、自适应权重和柯西变异策略改进天鹰算法,提升其寻优性能。采用IAO对ELM的输入权值和隐含层偏置进行优化,得到IAO-ELM诊断模型,提高分类精度。结果显示,IAO-ELM诊断模型的准确率为99.375%,能有效地实现DC-DC电路软故障诊断。Aiming at the problem of poor accuracy of soft fault diagnosis in DC-DC circuit,a fault diagnosis method based on improved aquila optimizer and optimized extreme learning machine(IAO-ELM)is proposed.The original fault signal is decomposed and reconstructed by the VMD method,and the features in the time-frequency domain are extracted as the feature vector.SPM chaotic mapping,lens reverse learning,adaptive weight and Cauchy mutation strategy are used to improve the aquila optimizer and improve its optimization performance.The input weights and implicit layer bias of ELM are optimized by IAO,and the IAO-ELM diagnostic model is obtained to improve the classification accuracy.The results show that the accuracy of IAO-ELM diagnosis model is 99.375%,which can effectively realize the soft fault diagnosis of DC-DC circuit.

关 键 词：DC-DC电路 故障诊断 天鹰算法 极限学习机 变分模态分解 

分 类 号：TN108.7[电子电信—物理电子学]