The present invention belongs to the field of battery pack thermal management technology, a real-time monitoring method for the internal temperature of the battery pack based on the theory of compressed sensing, and for the same type of battery pack, based on the experimental data of the temperature of all position points under the condition of charge and discharge and different loads; The neural network algorithm in deep learning was used to train a simulated temperature field model suitable for the battery pack. The model can then be invoked by the software, and the effect of predicting the temperature state of all points of interest of the battery pack can be achieved by sensing the temperature at some specific positions in the battery pack, so as to complete the global real-time monitoring of the internal temperature of the battery pack.

 动力电池.pdf