Power battery thermal runaway prediction method based on big data

The invention relates to the technical field of new energy automobiles, in particular to a power battery thermal runaway prediction method based on big data, and the method comprises the steps: keeping long-term collection of terminal voltages of all monomers in a detection vehicle PACK through the big data of a new energy automobile, carrying out the cleaning of the data, building a one-dimensional linear mathematical model, and carrying out the prediction of thermal runaway of a power battery. And calculating according to the mathematical model to obtain a current value set and a slope value set of all monomer fitting curves. The current value is used for evaluating the severity of the internal short circuit, and the slope is used for evaluating the change rate of the internal short circuit. And evaluating the risk of thermal runaway of the power battery caused by the internal short circuit according to the severity and the change rate. In order to realize automatic identification of a computer, the scheme