Currently, multilevel inverters (MIs) are very popular in many industrial and renewable energy applications. Fast and accurate fault diagnosis is very important for improving their reliability. The present study proposes a fault diagnosis method based on the probabilistic principle component analysis (PPCA) and support vector machine (SVM) to control switches in single phase five-level voltage controlled cascaded H-Bridge MI (CHMI). The output voltage signals under different fault conditions of the CHMI are taken as fault features by using the phase-shift pulse width modulation technique. PPCA is used to optimize the data and reduce the dimension of the fault features. Finally, SVM classifier is used to diagnose the different fault modes. An experimental setup of CHMI is designed to validate the proposed fault diagnosis method. The simulation and experimental results show that by using PPCA-SVM, the accuracy of the fault location can be improved, and the time require for the fault diagnosis in CHMI can be reduced.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.