An Efficient Expert System for Machine Fault Diagnosis

An efficient expert system for machine fault diagnosis is developed. A new search method is proposed in this system to improve the efficiency of the diagnostic process. First of all, a diagnostic tree (a decision tree) is built by domain experts according to the functions of the devices in the machine. Then, the diagnostic priorities of nodes (devices) in the tree are determined based on a fuzzy group multiple attribute decision making method. A meta knowledge base for fault diagnosis is generated automatically based on the determined priorities to guide the diagnostic process. After that, a domain knowledge base that hypothesises possible faults for each device in the tree is generated by domain experts and/or manuals. At last, the inference process starts based on the meta knowledge base and hypothesises which device is the possible cause of failure. To validate the system performance, an illustrative example (VCR troubleshooting) is presented for demonstration purposes.