An effective method to improve Electronic Equipment Condition Monitoring Based on KPCA-EDA and MMSH-SVDD

Abstract

In order to improve the validity of electronic equipment condition monitoring, overcome the shortage of normal KPCA (Kernel Principal Component Analysis) and SVDD (Support Vector Data Description) monitoring model, a method on electronic equipment condition monitoring based on KPCA-EDA (KPCA- Estimation of Distribution Algorithm ) and MMSH-SVDD (Maximal Margin Separating Hypersphere SVDD Mode ) is put forward. Firstly, the feature of original monitoring data is extracted by KPCA-EDA algorithm, and a group of features with enough state identifying information are obtained; then the MMSH-SVDD model is trained by the normal state and a little bit of fault state features, and the unknown state feature is applied to the trained model; Finally, a filter circuit is taken as an example in simulations, the result shows that this method is the effective method improve the performance of electronic equipment condition monitoring. DOI : http://dx.doi.org/10.11591/telkomnika.v12i5.4332