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 R2 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.

SiC MOSFETs face prominent reliability issues due to higher voltage resistance requirements and continued device miniaturization. The lifetime prediction of SiC MOSFET plays a crucial role in improving the reliability of devices and systems. However, existing methods still face challenges in terms of adaptability, stability, and accuracy due to the complexity of the failure process in SiC MOSFET. This article proposes an improved grey wolf optimizer-based long short-term memory (IGWO-LSTM) model for SiC MOSFET lifetime prediction. The model introduces a Tent chaotic mapping to generate an initial population with optimal distribution, ensuring comprehensive search space coverage and enhancing dynamic search adaptability. Then, a nonlinear control parameter strategy and the principle of particle swarm optimization (PSO) are added. The feature extraction capability of the model is strengthened, and the exploration and exploitation phases are dynamically balanced. The optimizations enable faster discovery of the global optimum while maintaining solution quality, thereby improving prediction accuracy and stability. Finally, power cycling experiments were conducted on two types of SiC MOSFETs with different internal resistances to validate the effectiveness of the proposed model. The proposed IGWO-LSTM model achieves high prediction accuracy, with R² values of 96.2%, 94.8%, 94.1%, and 93.9% for four SiC MOSFETs, and RMSE values as low as 0.0117, 0.0143, 0.0152, and 0.0158, respectively. This represents an average improvement in R² by 16%, 8%, and 4%, and a reduction in RMSE by up to 67.03%, 50.39%, and 31.57% compared with other intelligent models. Similarly, IGWO-LSTM achieves reductions in MAE of approximately 68%, 50%, and 30%, with corresponding reductions in MAPE of about 70%, 48%, and 26%, respectively. The results demonstrate superior performance in prediction accuracy, stability, and adaptability of the proposed model.