Lithium battery health state estimation method based on feature selection and time sequence attention

The invention discloses a lithium battery health state estimation method based on feature selection and time sequence attention. The lithium battery health state estimation method comprises the following steps: 1, acquiring data sets of battery capacity, voltage, temperature and current of different rounds in multiple charging and discharging cycles of a lithium battery; 2, preprocessing the data related to charging and discharging to obtain health factor data with different characteristics; 2, performing pearson correlation coefficient analysis on different health factor data to obtain health factor data with relatively high correlation; 3, constructing a convolution time sequence attention network model M; and 4, sending related data into the convolution time sequence attention network model M for model training, and finally obtaining a trained convolution time sequence attention network model M '. The lithium battery health state prediction accuracy can be effectively improved, meanwhile, the model is easy