New energy automobile lithium battery life prediction method based on optimization algorithm

Abstract

The invention provides a new energy automobile lithium battery life prediction method based on an optimization algorithm. The method comprises the steps of firstly collecting the temperature, the discharge depth and the charge rate of a lithium battery, the temperature of an environment where the lithium battery is located and the change rate of the temperature of the environment where the lithium battery is located within a period of time as lithium battery health state data; then, according to a lithium battery discharge curve rule, the lithium battery health state data is sent into an improved particle swarm algorithm based on a grey wolf algorithm, and lithium battery data of an optimal solution is output; and finally, sending the lithium battery data of the optimal solution into an LSTM prediction algorithm, establishing a life prediction model, predicting the actual life of the lithium battery according to the target life of the lithium battery, and finally outputting the predicted life of the lithium battery. The method is accurate in prediction result.

Description

technical field [0001] The invention belongs to the technical field of new energy vehicle lithium batteries in the field of new energy vehicle batteries, and particularly relates to a life prediction method for new energy vehicle lithium batteries based on an optimization algorithm. Background technique [0002] The factors that affect the battery state of health include temperature, depth of discharge and charging rate, etc., but these indicators cannot directly represent the degree of performance degradation of the battery, and there are certain difficulties in online detection. The actual capacity of the battery refers to the storage capacity of the battery when the battery is fully charged. Electric energy can be directly characterized. Existing lithium battery life prediction methods can be divided into failure physical models and data-driven models. The failure physical model is to represent the process of lithium battery performance degradation by establishing a math...

AI Technical Summary

Problems solved by technology

[0003] In view of the above problems, the present invention provides a new energy vehicle lithium battery life prediction method based on an optimization algorithm. By optimizing the parameters of the lithium battery, the local characteristics and the global degradation trend in the battery health index are adaptively separated to solve the problem. Solved the problem of violent fluctuations caused by the rebirth of battery energy indicators; constructed a deep neural network temperature model, established a temperature compensation model, and obtained reliable lithium battery life prediction results

Images