Abstract:

In view of the problem of high failure efficiency of IGBT(Insulated Gate Bipolar Transistor) modules in inverters, which are most prone to damage and aging, and the device degradation process is difficult to predict, a neural network prediction model combining LSTM(Long Short-Term Memory) and chaotic sparrow is proposed. By introducing the two-dimensional Pearson correlation coefficient method to obtain the combined degradation features, the LSTM-based voltage degradation prediction model is constructed. The model is used to adaptively extract the internal correlations of degradation features to realize the screening of key information and digging deep degradation features. In the feasible domain of sparrow search algorithm, Gaussian random numbers with normal distribution and chaotic sequence corresponding to Tent mapping are introduced to improve the accuracy and stability of prediction. The learning rate, number of neurons and batch-size of the model are optimized to find the optimal value to match the network topology. The LSTM with the optimal structural parameters is used to predict each original data separately and obtain the final degradation prediction value. The accelerated degradation data set of NANS experimental center is analyzed and compared with the conventional prediction algorithm to verify the effectiveness and accuracy of the proposed algorithm.

Key words: chaos sparrow search algorithm, LSTM, parameter optimization, prediction of degradation trends, IGBT, Gaussian variation, predictive models, Tent mapping