An Intelligent Fault Diagnosis Method for Open-Circuit Faults in Power-Electronics Energy Conversion System

Wei-Cheng Wang,Chuang Liu,Lei Kou,Jia-Ning Zhou,Quan-De Yuan,Guo-Wei Cai

doi:10.1109/access.2020.3043796

Wei-Cheng Wang, Chuang Liu + Show 4 more

Open Access

https://doi.org/10.1109/access.2020.3043796

Copy DOI

Abstract

Applying the fault diagnosis techniques to power electronic equipments is beneficial to improve the stability and reliability of renewable energy system, because power electronic equipments are a key component of renewable energy system that largely defines their performance. This paper presents a novel intelligent fault diagnosis method for a three-phase power-electronics energy conversion system based on knowledge-based and data-driven methods. Firstly, the three-phase AC currents of the power-electronics energy conversion system are collected and used to analyze. Secondly, the feature transformation, a knowledge-based method, is utilized to preprocess the fault data. After feature transformation, the slopes of current trajectories (transformed features) are not affected by different loads. And then random forests algorithms (RFs), a data-driven method, are adopted to train the fault diagnosis classifier with the processed fault data. Finally, the proposed method is implemented online on an actual three-phase PWM rectifier platform. The results show that the proposed fault diagnosis method can successfully detect and locate the open-circuit faults in IGBTs of the three-phase PWM rectifier. In addition, the proposed method is suitable for most of three-phase power-electronics energy conversion systems.

Highlights

W ITH the development of energy systems, the high proportion of renewable energy is accessed by the energy systems, which bring more challenges and unsteadiness [1]– [3]
ONLINE FAULT DIAGNOSIS EXPERIMENTS FOR THREE-PHASE POWER-ELECTRONICS ENERGY CONVERSION SYSTEM In order to further verify the effectiveness of the proposed diagnosis method, online fault diagnosis experiments are conducted for different open-circuit faults of IGBTs in an actual three-phase PWM rectifier platform
This paper proposes a novel intelligent fault diagnosis method for open-circuit faults of IGBTs in threephase power-electronics energy conversion system based on knowledge-based and data-driven methods

Summary

INTRODUCTION

W ITH the development of energy systems, the high proportion of renewable energy is accessed by the energy systems, which bring more challenges and unsteadiness [1]– [3]. A novel intelligent fault diagnosis method is proposed for threephase power-electronics energy conversion systems, which can reduce dependence of the fault data under different loads, and does not need to set complex thresholds. (2) Presents a unique combination of knowledge-based and data-driven method for three-phase power-electronics energy conversion systems. The Signal is adopted to determine the fault occurrence and the instantaneous measurements of three-phase AC current are employed to locate the fault IGBTs. It can be seen that the positive half-cycle phase current disappears for the open-circuit fault occurred in the lower IGBT Sa2, while the phase current is negative, the rectifier is slightly affected. It is necessary to transform or extract fault features to obtain more effective fault features, so as to reduce the overreliance on fault data under different loads

INTELLIGENT FAULT DIAGNOSIS METHOD BASED ON KNOWLEDGE-BASED AND DATA-DRIVEN APPROACH

FEATURE TRANSFORMATION BASED ON KNOWLEDGE

TRAINING AND EVALUATION OF FAULT DIAGNOSIS CLASSIFIER

10 ΨA5 ΨB5 ΨC5 10 ΨA5 ΨB5 ΨC5

Findings

CONCLUSION