A Hybrid Case-Based Reasoning and Neural Network Approach to Online Intelligent Fault Diagnosis

In traditional help desk service centres of manufacturing companies, diagnosis of machine faults relies heavily on the service engineers’ knowledge and experience. This method poses a problem of training and maintaining a pool of expert service engineers. With the advancement of Internet technology and artificial intelligence techniques, it is possible to deliver online customer service support over the World Wide Web. This paper describes a hybrid case-based reasoning (CBR) and artificial neural network (ANN) approach for intelligent fault diagnosis. Instead of using traditional CBR technique for indexing, retrieval and adaptation, the hybrid CBR-ANN approach integrates ANN with the CBR cycle to extract knowledge from service records of the customer service database and subsequently recall the appropriate service records using this knowledge during the retrieval phase. The system learns with user feedback to improve its performance.