Title: The development and application of the ontology for tractor fault diagnosis

Authors: Chunyin Wu; Qing Ouyang; Shouhua Yu; Chengjian Deng; Xiaojuan Mao; Tiansheng Hong

Addresses: College of Mathematics and Informatics, South China Agricultural University, Guangzhou, 510642, China ' College of Mathematics and Informatics, South China Agricultural University, Guangzhou, 510642, China ' College of Mathematics and Informatics, South China Agricultural University, Guangzhou, 510642, China ' College of Mathematics and Informatics, South China Agricultural University, Guangzhou, 510642, China ' College of Mathematics and Informatics, South China Agricultural University, Guangzhou, 510642, China ' College of Engineering, South China Agricultural University, Guangzhou, 510642, China

Abstract: 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.

Keywords: ontology; expert system; tractor; fault diagnosis; fault tree analysis; FTA; web; agricultural machinery; China.

DOI: 10.1504/IJCSE.2017.086010

International Journal of Computational Science and Engineering, 2017 Vol.15 No.1/2, pp.112 - 122

Received: 12 Jan 2016
Accepted: 10 Jul 2016

Published online: 21 Aug 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article