Data-Driven Fault Classification for Non-Inverting Buck–Boost DC–DC Power Converters Based on Expectation Maximisation Principal Component Analysis and Support Vector Machine Approaches

Yichuan Fu, Zhiwei Gao, Haimeng Wu, Xiuxia Yin, Aihua Zhang

Research output: Contribution to conferencePaperpeer-review

6 Downloads (Pure)

Abstract

Data-driven fault classification for power converter systems has been taking more into considerations in power electronics, machine drives, and electric vehicles. It is challenging to classify the different topologies of faults in the real time monitoring control systems. In this paper, a data-driven and supervised machine learning-based fault classification technique is adopted by combining and consolidating with Expectation Maximisation Principal Component Analysis (EMPCA) and Support Vector Machine (SVM) to substantiate the availability of fault classification. The proposed methodology is applied to the non-inverting Buck–Boost DC–DC power converter systems subjected to the incipient fault and serious fault, respectively. Finally, the feasibility of the approach is validated by intensive simulations and comparison studies.
Original languageEnglish
Number of pages6
Publication statusAccepted/In press - 21 Aug 2021
Event1st IEEE International Power Electronics and Application Symposium - Shanghai, China
Duration: 12 Nov 202115 Nov 2021

Conference

Conference1st IEEE International Power Electronics and Application Symposium
Abbreviated titleIEEE PEAS'2021
CountryChina
CityShanghai
Period12/11/2115/11/21

Fingerprint

Dive into the research topics of 'Data-Driven Fault Classification for Non-Inverting Buck–Boost DC–DC Power Converters Based on Expectation Maximisation Principal Component Analysis and Support Vector Machine Approaches'. Together they form a unique fingerprint.

Cite this