For ensuring the safe operation of IGBT, Artificial Intelligence technology can be used to predict the life of IGBT. Aiming at problem that the remaining life prediction method of IGBT lacks accuracy due to the difficulty in selecting parameters of LSTM model, a WOA is proposed to optimize the LSTM remaining life prediction model. WOA algorithm is used to optimize the number of hidden neurons and learning rate of LSTM, which provides better parameters for LSTM training. The prediction model of WOA-LSTM IGBT residual life is established by Python, and compared with LSTM. The experimental results show that the RMSE of WOA-LSTM is 0.1838, the MAE is 0.1483, and the MAPE is 0.0103, which has higher prediction accuracy and better prediction stability than the traditional LSTM model, and is beneficial to realize the state detection and life prediction research of IGBT.
Research on Life Prediction of Inverter IGBT Based on WOA Optimized LSTM Model
11.10.2023
2589205 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
IGBT Life Prediction Based on CNN1D-LSTM Hybrid Model
TIBKAT | 2022
|IGBT Life Prediction Based on CNN1D-LSTM Hybrid Model
British Library Conference Proceedings | 2022
|IGBT Life Prediction Based on CNN1D-LSTM Hybrid Model
Springer Verlag | 2022
|IGBT based inverter design for vehicle application
Tema Archiv | 2010
|Sensorless control system with IGBT-Inverter
Kraftfahrwesen | 1993
|