Analysis of the RBF ANN-based classifier for the diagnostics of electronic circuit

Abstract

The paper presents the application of the Radial Basis Function (RBF) Artificial Neural Network (ANN) to the diagnostics of the analog circuit. Such networks are in most cases useful in the approximation tasks as the alternative to multilayered perceptrons (MLP) or Support Vector Machines (SVM). In this work the analysis of various RBF ANN-based classifier configurations for the fault detection and identification module are is conducted. The considered parameters included the optimal number of neurons in the hidden layer, coding schemes for the output layer neurons and operation duration during the training and testing the classifier. The efficiency of the diagnostic system is verified using the fifth order lowpass filter. The circuit was also analyzed in terms of the testability, depending on the set of accessible nodes, confronted against the output node only. Experiments cover also accuracy comparison between the RBF, MLP and SVM classifiers. Results show advantages and drawbacks of the RBF ANN-based diagnostic module, compared to other available solutions.