<![CDATA[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]]>
Copyrights © 2014
