A Fault Diagnosis Toolbox Applying Classification and Inference Method

Abstract

This paper presents a MatLab/SIMULINK based toolbox for fault diagnosis. It has been witnessed that while the fault detection methods must be tailored specifically to the process that is to be supervised, the fault diagnosis methods on the other hand are very similar in most applications. Therefore, a MatLab/SIMULINK-based toolbox was developed by the authors which shall be presented in this paper and is available for download. The software is designed such that it can be used with the Real-Time Workshop and can thus be compiled and downloaded to a wide range of rapid control prototyping system. Depending on the type and availability of a-priori knowledge, one can either employ classification or inference methods. Both approaches are supported by development environment. Classification is used whenever there are experimental data available which describe the influence of the faults on the symptoms. The available implementations encompass the Bayes classifier, the k-nearest neighbor and the polynomial classifier. Inference methods are used, whenever rules or expert knowledge describing the influence of the fault on the symptoms are available. In the paper, a Fuzzy-Logic based inference engine is presented, where the symptoms are first fuzzified to account for the uncertainty in the reaction of residuals. Then, the individual symptoms are combined using Fuzzy-Logic AND and OR operators respectively. The mapping of the fuzzy outputs to the diagnosed fault is accomplished by determining the maximum fault possibility among all fault possibilities. The different diagnostic engines have already successfully been applied to a wide range of prototype fault management realizations at the institute and have proven very capable.