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

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