功率变换电路电解电容器故障预测方法研究  

Research on failure prediction method of electrolytic capacitor used in power conversion circuit

作　　者：孙凤艳[1] 王友仁[1] 崔江[1] 林华[1] 

机构地区：[1]南京航空航天大学自动化学院测试计量技术及仪器,南京210016

出　　处：《电子测量与仪器学报》2010年第1期29-33,共5页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(编号:60672034)资助项目

摘　　要：本文对功率变换电路中电解电容故障预测方法进行了研究,提出了一种基于快速傅立叶变换(FFT)与最小二乘支持向量机(LS-SVM)相结合的故障预测方法。通过对电解电容失效机理进行研究,建立其等效电路故障模型,并选择等效串联电阻(ESR)作为寿命特征参数、输出纹波电压和电容电流作为监测信号;通过FFT对监测信号进行频域分析,计算ESR;利用LS-SVM对ESR回归建模、预测。将提出的方法应用于Buck电路,对电解电容的故障进行预测。实验结果表明,该方法可以准确的对电解电容故障进行预测。Failure prediction method of electrolytic capacitor used in power converter circuit has been studied in this paper. A method based on Fast Fourier Transform （FFT） and Least Squares Support Vector Machines （LS-SVM） for the prediction of electrolytic capacitor＇s failure is proposed. Firstly, through the study of electrolytic capacitor＇s failure mechanism, the equivalent circuit model was established. Secondly, ESR was selected as the life characteristic parame- ter, the output ripple voltage and the capacitor current were selected as monitoring signals. Then the monitoring signals were transformed to frequency-domain space using FFT and ESR was calculated. Finally, the LS-SVM regression was used to establish the trend of the characteristic parameter over time and to predict the future values. The proposed method is applied to Buck converter and predict the failure of electrolytic capacitor. The experimental results showed that the method can be effectively applied in electrolytic capacitor failure prediction.

关 键 词：电解电容器 故障预测 寿命特征参数 最小二乘支持向量机 快速傅立叶变换 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置]