Remaining Useful Life Estimation of Insulated Gate Biploar Transistors (IGBTs) Based on a Novel Volterra k-Nearest Neighbor Optimally Pruned Extreme Learning Machine (VKOPP) Model Using Degradation Data.

Zhen Liu,Chenglin Yang,Xiuyun Zhou,Xianping Zeng,Wenjuan Mei

doi:10.3390/s17112524

Abstract

The insulated gate bipolar transistor (IGBT) is a kind of excellent performance switching device used widely in power electronic systems. How to estimate the remaining useful life (RUL) of an IGBT to ensure the safety and reliability of the power electronics system is currently a challenging issue in the field of IGBT reliability. The aim of this paper is to develop a prognostic technique for estimating IGBTs’ RUL. There is a need for an efficient prognostic algorithm that is able to support in-situ decision-making. In this paper, a novel prediction model with a complete structure based on optimally pruned extreme learning machine (OPELM) and Volterra series is proposed to track the IGBT’s degradation trace and estimate its RUL; we refer to this model as Volterra k-nearest neighbor OPELM prediction (VKOPP) model. This model uses the minimum entropy rate method and Volterra series to reconstruct phase space for IGBTs’ ageing samples, and a new weight update algorithm, which can effectively reduce the influence of the outliers and noises, is utilized to establish the VKOPP network; then a combination of the k-nearest neighbor method (KNN) and least squares estimation (LSE) method is used to calculate the output weights of OPELM and predict the RUL of the IGBT. The prognostic results show that the proposed approach can predict the RUL of IGBT modules with small error and achieve higher prediction precision and lower time cost than some classic prediction approaches.

Highlights

As power electronic equipment has come into widespread use, insulated gate bipolar transistor (IGBT) fully controlled power electronic devices, combining the facile drive of MOSFET with the low conduction loss of a bipolar junction transistor (BJT), and possess good switching performance, have found wide application in industrial automotive, traction, and solar inverter areas [1,2,3].knowing whether an IGBT is in a normal state is critical to the safe operation of the system [4].Generally, the performance of a system may gradually decline as IGBTs contain numerous materials with different coefficients of thermal expansion (CTE) with many interfaces, which can wear out and cause overstress failures [5]
Before using the proposed Volterra k-nearest neighbor OPELM prediction (VKOPP) algorithm to predict the IGBT remaining useful life (RUL), this algorithm is compared with the original optimally pruned extreme learning machine (OPELM), Volterra and other typical machine learning algorithms to verify the validity, feasibility, and generalization
Model, weighted hidden Markov autoregressive model (WHMAR) [41], RBF neural network model (RBFNN), OPELM, Volterra, pruned lazy learning model (LLpruned) [43], least squares support vector machines (LSSVM) [44], and the VKOPP model proposed in this paper

Summary

Introduction

As power electronic equipment has come into widespread use, insulated gate bipolar transistor (IGBT) fully controlled power electronic devices, combining the facile drive of MOSFET with the low conduction loss of a bipolar junction transistor (BJT), and possess good switching performance, have found wide application in industrial automotive, traction, and solar inverter areas [1,2,3].knowing whether an IGBT is in a normal state is critical to the safe operation of the system [4].Generally, the performance of a system may gradually decline as IGBTs contain numerous materials with different coefficients of thermal expansion (CTE) with many interfaces, which can wear out and cause overstress failures [5]. As power electronic equipment has come into widespread use, insulated gate bipolar transistor (IGBT) fully controlled power electronic devices, combining the facile drive of MOSFET with the low conduction loss of a bipolar junction transistor (BJT), and possess good switching performance, have found wide application in industrial automotive, traction, and solar inverter areas [1,2,3]. Knowing whether an IGBT is in a normal state is critical to the safe operation of the system [4]. The performance of a system may gradually decline as IGBTs contain numerous materials with different coefficients of thermal expansion (CTE) with many interfaces, which can wear out and cause overstress failures [5]. One is condition monitoring and fault diagnosis for an IGBT. In [6], Choi et al proposed a condition monitoring method

Objectives

Methods

Results

Conclusion