Identification of short circuit fault location in voltage source inverters based on rough set theory

Fault diagnosis is a complex problem that concerns effective decision-making. However, with the increased complexity of equipments and enrichment in data collection methods, the task of fault diagnosis has become increasingly difficult and its complexity almost unmanageable using traditional techniques. In this paper, a Method of the Rules Extraction for Detection and Identification of Short Circuit Fault Location in Voltage Source Inverters Based on Rough Set Theory is presented. The rough set reduction technique is applied to find all reducts. After that the principles of hypergraph was applied to determine the minimal transversal of reducts. Finally, a set of generalized rules for Short Circuit Fault Location was extracted. The extracted rules are performed with basic logic functions so a digital diagnostic circuit can be obtained. The results show that the presented method can effectively detect and identify the location of faults and do not depend on switch parameters, increase the efficiency and accuracy of diagnosis and can avoid the fault diagnosis dimensional disaster problem.