A Deep Learning Network based Robust Fault Diagnosis Method for IGBT Open Circuit
Authors:
- 17 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2366-2371
Abstract
This paper proposes an IGBT open-circuit fault diagnosis method that can maintain high accuracy under diverse operation conditions and circuit parameter variances. Different aspects of uncertainties are analyzed in the component parameters, operation conditions, and measurement errors of a three-phase inverter case study. A lightweight Convolutional Neural Network (CNN) is applied based on an obtained dataset covering a wide range of inverter operation scenarios and uncertainties. The comparisons with benchmarked conventional fault diagnosis method and with different machine learning methods are presented. The results verify the improved accuracy in open-circuit diagnosis considering complex operation conditions and meanwhile with reduced detection time in certain scenarios.Keywords
Funding Information
- China Scholarship Council
This publication has 19 references indexed in Scilit:
- A model-based power switch fault diagnosis strategy for cascaded H-Bridge converterMicroelectronics Reliability, 2023
- Stability Analysis and Robust Parameter Design of DC-Voltage Loop for Three-Phase Grid-Connected PV Inverter Under Weak Grid ConditionIEEE Transactions on Industrial Electronics, 2023
- Open-Circuit Fault Diagnosis of NPC Inverter Based on Improved 1-D CNN NetworkIEEE Transactions on Instrumentation and Measurement, 2022
- A Multiple Open-Circuit Fault Diagnosis Method for Two-Level Three-Phase Voltage Source Converters Based on Average-Phase Voltage ModelIEEE Journal of Emerging and Selected Topics in Power Electronics, 2021
- Inductor Saturation Compensation in Three-Phase Three-Wire Voltage-Source Converters Via Inverse System DynamicsIEEE Transactions on Industrial Electronics, 2021
- A Data-Driven Method for IGBT Open-Circuit Fault Diagnosis Based on Hybrid Ensemble Learning and Sliding-Window ClassificationIEEE Transactions on Industrial Informatics, 2020
- An Improved Fault Diagnosis Method of Rotating Machinery Using Sensitive Features and RLS-BP Neural NetworkIEEE Transactions on Instrumentation and Measurement, 2019
- Performance Comparison of Fault-Tolerant Three-Phase Induction Motor Drives Considering Current and Voltage LimitsIEEE Transactions on Industrial Electronics, 2018
- Fault-Tolerant Multilevel Topology Based on Three-Phase H-Bridge Inverters for Open-End Winding Induction Motor DrivesIEEE Transactions on Energy Conversion, 2017
- A humidity-dependent lifetime derating factor for DC film capacitors2015