Abstract: In the field of power equipment quality management, it is of great significance to establish an intelligent power equipment quality risk prevention and control method to promote the construction of digital power grid. Aiming at the problems that the existing power equipment quality risk prevention and control cannot be intelligent and automated, a quantitative index for power equipment quality assessment is firstly proposed. On this basis, a power equipment quality prediction model based on VMD-EWT-LSTM is established. Firstly, the variable modal decomposition method is used to decompose the complex sequence into a number of simple subsequences, and at the same time the empirical wavelet decomposition algorithm is used to decompose the residual sequences, for the obtained subsequences, the long and short-term memory network is used to establish the prediction model for the various subsequences, and the prediction results are summed up to obtain the final prediction results. Simulation results show that the established prediction model has higher prediction accuracy compared with other prediction models, its RMSE, MAE, MAPE are 0.174, 0.143 and 13.360, respectively, which lays the foundation for the establishment of the power equipment quality risk prevention and control model, and is of great significance for the promotion of the construction of digital power grid.