Lithium ion battery remaining service life prediction method based on correlation analysis and VMD-LSTM

The invention discloses a lithium ion battery residual life prediction method based on correlation analysis and VMD-LSTM. Belongs to the technical field of lithium ion battery capacity detection. The method comprises the following specific steps: calculating correlation coefficients between characteristic parameters and the battery capacity by taking the discharge power, the constant-current charging time, the discharge average temperature, the discharge cutoff voltage and the ratio of the constant-current charging time to the constant-voltage charging time of the lithium ion battery as the characteristic parameters of the battery capacity; and selecting the characteristic parameter with the strongest correlation as the HI for predicting the lithium ion battery RUL. And meanwhile, signal decomposition is carried out on the selected HI by utilizing VMD, the HI is decomposed into three modal components of global attenuation, local regeneration and other noise, and the three modal components are used as the HI t