Pruning and Extraction of Qualitative Fault Diagnosis Rules from a Neural Network

Abstract

Artificial neural networks have been shown to be an effective tool for process fault diagnosis. However, a main criticism is that details of how fault diagnosis decisions are made are embedded in the complex input-output mapping performed by a network, and are in general difficult to obtain. In this paper, statistical techniques and relationships between fuzzy systems and standard radial basis function networks, are exploited to prune a trained network and to extract qualitative rules that explain the network operation for fault diagnosis. The procedures are demonstrated in an application to the diagnosis of a range of both soft and hard faults in a simulated, complex, chemical process.