LITHIUM-BATTERY TEMPERATURE FIELD SPATIO-TEMPORAL MODELING METHOD BASED ON EMD-LSTM

Disclosed in the present invention is a lithium-battery temperature field spatio-temporal modeling method based on an EMD-LSTM. The method comprises: converting high-dimensional spatio-temporal data into low-dimensional spatio-temporal data by using a KWLTSA dimension reduction method, and acquiring a spatial basis function; projecting the low-dimensional spatio-temporal data onto the spatial basis function, so as to obtain a corresponding low-order time coefficient; decomposing the low-order time coefficient by using an EMD algorithm, so as to obtain an IMF component and a residual component; respectively performing LSTM training on the IMF component and the residual component, so as to obtain a prediction time coefficient; and performing spatio-temporal reconstruction on the prediction time coefficient and the spatial basis function, so as to obtain a lithium-battery temperature field spatio-temporal modeling model. The present invention solves the problems of it being difficult to apply a traditional spati