Analog circuits fault diagnosis using multi-valued Fisher's fuzzy decision tree (MFFDT)

Fault diagnosis of analog circuits is more challenging compared with digital circuits as a result of the parametric deviation and the difficulty in signal discretization. There still lacks effective approaches to realize reliable fault detection and isolation for a comprehensive diagnosis. A new fault diagnosis technique called multi-valued Fisher's fuzzy decision tree (MFFDT) is proposed in this paper to solve the problem. This technique uses the decision tree as the diagnosis model and incorporates the Fisher's linear discriminant principles. The fuzzification mechanism is devised to discretize the input monitoring data. The proposed MFFDT method is composed of two aspects: decision tree training and real fault diagnosis processes. The former uses the benchmark data to train a decision tree, while the latter sends the monitoring data into the decision tree to generate diagnosis results. The proposed method is validated using simulated data and the real-time data for an active filter circuit and an audio amplifying circuit. The comparative analysis is also presented to evaluate diagnosis performances. Copyright (C) 2015 John Wiley & Sons, Ltd.