AUTHOR=Kou Lei , Gong Xiao-dong , Zheng Yi , Ni Xiu-hui , Li Yang , Yuan Quan-de , Dong Ya-nan 

TITLE=A Random Forest and Current Fault Texture Feature–Based Method for Current Sensor Fault Diagnosis in Three-Phase PWM VSR

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2021.708456

DOI=10.3389/fenrg.2021.708456

ISSN=2296-598X

ABSTRACT=Three-phase PWM voltage-source rectifier (VSR) systems have been widely used in various energy conversion systems, where currents sensors are the key component for states monitoring and system control. The current sensors faults may bring hidden danger or damage to the whole system, therefore, this paper proposed a random forests (RFs) and currents fault texture features based method for currents sensors fault diagnosis in three-phase PWM VSR systems. First, the three-phase AC currents of three-phase PWM VSR are collected to extract the currents fault texture features, and no additional hardware sensors are needed to avoid causing additional unstable factors. Then, the currents fault texture features are adopted to train the random forests currents sensors fault detection and diagnosis (CSFDD) classifier, which is a data-driven CSFDD classifier. Finally, the effectiveness of the proposed method is verified by simulation experiments, the result shows that the currents sensors faults can be detected and located successfully, and it can effectively provide fault locations for maintenance personnel to keep the stable operation of the whole system.