Fault Diagnosis of Power Electronic Circuit Based on Random Forests Algorithm

Power electronic equipments are taking more and more important part in many fields such as power supply, power system and renewable energy source and etc. Acted as power supply or motor driver, the power electronic equipment has a great impact on the systems´ reliability. So the studies on the fault diagnosis for power electronics circuit have significant theory value and practical value. Based on random forests, a new on-line fault diagnosis method for power electronic circuit is put forward in the paper. Although there are several existed techniques for faults diagnosis of power electronic circuit, the research on random forests algorithm (RFA) is meaningful and necessary because of its fast execution speed, the characteristic of tree classifier, and high process-speed. A three-phase SCR rectifier circuit with inductive load is used as an example to illustrate the new approach of fault diagnosis. The result of the application indicates that the method can diagnose faults of three-phase rectifier effectively.This diagnosis method also can be promoted to other form circuit, and possesses vast application foreground.