The development and application of the ontology for tractor fault diagnosis

This paper develops an ontology for tractor fault diagnosis, and designs the algorithms for reasoning and explanation; furthermore, it applies the ontology to develop an expert system for tractor fault diagnosis. First of all, the ontology is developed with the method of fault tree analysis, which supports bidirectional reasoning. Then, the algorithm of reasoning is designed based on connected tractor fault trees, which is actually a directed acyclic graph structure in this case. Meanwhile, the algorithm of explanation is designed based on backward reasoning, which could provide explanations for the deduced results. Finally, the ontology-based expert system is designed and implemented with web technologies. The expert system could provide service for tractor fault diagnosis via internet to tractor maintenance personnel and tractor drivers who locate in the wide rural areas in China.