Data driven prognostics for predicting remaining useful life of IGBT

Abstract

Power electronic devices such IGBT (Integrated Gate Bipolar Transistor) are used in wide range of applications such as automotive, aerospace and telecommunications. The ability to predict degradation of power electronic components can minimise the risk of their failure while in operation. Research in this area aims to develop prognostics strategies for predicting degradation behaviour, failure modes and mechanisms, and remaining useful life of these electronic components. In this paper, data driven prognostics approaches based on Neural Network (NN) and Adaptive Neuro Fuzzy Inference System (ANFIS) models are developed and used to predict the degradation of an IGBT device. IGBT life data under thermal overstress load condition with square signal gate voltage bias, available from NASA prognostics data repository, is used to demonstrate the proposed data-driven prognostics strategy. The monitored collector-emitter voltage is used to identify the pattern and duration of different phases in the applied voltage load. The NN and ANFIS models are trained with a subset of the test data to predict remaining useful life (RUL) of the IGBT device under varying load test profiles. The predictive capability and performance of the models is observed and analysed.

Built-In Self-Test (BIST) Methods for MEMS: A Review

“…If the modified coefficients lead to a sensor output that is in the acceptable range, the sensor output is used for further measurements (recovered from failure state); otherwise, the sensor needs to be replaced in the next maintenance. The data from the sensor coefficient recalibration algorithm can not only be utilized for monitoring the health state of each sensor, but also for prognosis, thereby enabling the calculation of the residual useful life (RUL) and end of life (EOL) of the MEMS [ 96 , 97 , 98 ].…”

IGBT Remaining Useful Life Prediction Based on Particle Filter With Fusing Precursor

“…Ahsa et al [9], proposed a data-driven prediction method based on a neural network (N.N.) and an adaptive neuro-fuzzy inference system (ANFIS) model for the degradation of IGBT devices.…”

A review of data-driven prognostic for IGBT remaining useful life

“…9 Trajectory of V CE,ON using APF and SIR PF with different number of particles [23] diversity in samples to reduce estimation variance and a smaller error 17.8% was found. Ahsa et al [27] adopted two machine learning methods, neural network (NN) and adaptive neuro fuzzy inference system (ANFIS). Relatively accurate prediction can be made based on information beyond half-life.…”

“…Fig. 10 Structure of ANFIS [27] Fig. 11 The process of RUL estimation based on fuzzy logic [29] Fig.…”