Mahalanobis Distance Based Approach for Anomaly Detection of Analog Filters Using Frequency Features and Parzen Window Density Estimation

Abstract

Analog filters play a very important role in insuring the availability of electronic systems. Early detection of anomalies of analog filters can prevent the impending failures and enhance reliability. The complex architecture and the tolerances of multiple components make it very difficult to detect anomalies in analog filters. To address this concern, A Mahalanobis distance (MD) based anomaly detection method for analog filters is proposed in this paper. The conventional frequency features and the moment of frequency response are selected as the feature vector. Mahalanobis distance is used to transform the frequency feature vector to one dimensional MD data. The anomaly detection threshold is obtained based on probability density of the health MD data sets which is estimated by Parzen window density estimation method. The efficiency of the proposed method has been verified by two case studies. In the case studies, a comprehensive indicator constructed by miss alarm and false alarm is used to obtain an optimal anomaly detection threshold. One class SVM (OCSVM) based anomaly detection method is used as a comparison with our approach. The results illustrate that: (1) the proposed frequency features can effectively clarify the degradation of analog filters; (2) the proposed MD based approach can detect anomalies in analog filters effectively at an early time stage. (3) the proposed MD based approach can detect anomalies in analog filters more accurately than OCSVM based method.