Lifetime Prediction of IGBT by BPNN Based on Improved Dung Beetle Optimization Algorithm

Abstract

The insulated gate bipolar transistor (IGBT) has widespread application in energy storage systems, motor drives, smart grids, household appliances and other various fields. These applications demand accurate evaluation of reliability through lifespan prediction to ensure optimal performance and longevity. This study proposes an innovative IGBT lifespan prediction model using an improved dung beetle optimized back propagation neural network (IDBO-BP). The model integrates chebyshev chaotic mapping and golden sine strategy to address critical limitations of existing methods, including low accuracy, poor computational efficiency and weak dynamic adaptability. Chaotic initialization is applied to enhance population diversity and adaptive golden ratio-modulated step sizes are utilized to refine local search precision. This innovative approach delivers breakthroughs in enhancing prediction accuracy and accelerating computation speed without compromising the system’s global exploration capabilities. Besides, a constant case temperature-controlled AC power cycling test protocol was designed to verify the effectiveness of the improved algorithm. This test features suppression of thermal fluctuation interference and the consideration of both conduction losses and switching losses which better simulate real operating conditions. Experimental results demonstrate higher prediction accuracy of the IDBO-BP model compared to DBO-BP, PSO-BP, and GWO-BP. The ${\mathrm { R}}^{2}$ values of IDBO-BP model surpass the other methods by an average of 4–27 percentage points respectively. Improved stability of IDBO-BP model is confirmed by lower RMSE values with average error reductions of 9.13–32.1 percentage points, which indicate enhanced robustness in handling nonlinear and fluctuating data for IGBT lifetime prediction.