Development of a machine troubleshooting expert system via fuzzy multiattribute decision-making approach

Abstract Most current machine fault diagnosis systems emphasize on the correctness of the hypothesized result; however, in time-constrained situations, the efficiency of the diagnostic process becomes more important and should not be overlooked. This paper presents an Integrated Machine Troubleshooting Expert System (IMTES) that enhances the efficiency of the diagnostic process, improves the completeness and consistency of the knowledge base, and assists users in developing and maintaining their diagnostic systems. IMTES consists of five modules: a diagnostic tree module establishes the hierarchical structure regarding the function or connectivity of the diagnostic system, a fuzzy multiattribute decision-making module determines the most efficient diagnostic process and creates a “meta knowledge base” to control the diagnosis process, a knowledge base module captures the human expertise and deep knowledge to diagnose the possible machine fault, an inference engine module controls the diagnosis process and deals with the uncertainty from the user input and knowledge base itself, and a learning module uses the failure-driven learning method to train the knowledge base from the past actual cases. The system has been successfully implemented on MS-Windows environment, and it is written in MS Visual BASIC. To validate the system performance, IMTES is compared to EXACT, an expert system for automobile air-compressor troubleshooting, using 50 sample cases. The result shows that IMTES can reduce the number of queries by 20.7%.