Safety warning method of electric vehicle power battery

Abstract

The invention discloses a safety warning method of an electric vehicle power battery, which comprehensively evaluates the safety of the battery from two perspectives of battery performance degradationand possible failures, and gives a safety rating. In the evaluation of battery performance degradation, a degradation model prediction method based on particle filter is adopted, the remaining life of the current battery is predicted through estimating the model parameters, and a degradation index of the battery is given combined with the health status of the battery; and a method based on the BPneural network is used, and the history and real-time data of the battery BMS system are used as inputs, so as to extract the states associated with various critical faults and predict the possibility of various faults. After the two aspects of the safety assessment results are combined, comprehensive safety warning information is given. Compared with the current method of evaluating the safety of the battery only from the perspective of the remaining life or the health state, a more reliable evaluation result can be given.

Description

Technical field [0001] This application belongs to the technical field of new energy vehicles, and in particular relates to a safety warning method for electric vehicle power batteries. Background technique [0002] As the number of new energy vehicles continues to grow, the demand for power batteries has also increased. Lithium-ion battery systems have become an integral component of electric vehicles and distributed microgrid energy storage systems. Although the manufacturing technology and packaging level of batteries continue to improve, along with the uncertain factors of power battery manufacturing technology level and vehicle operating conditions, power battery voltage will inevitably be too high or too low, and the current will be too large or too small during operation. , the temperature is too high or too low, harsh operating environment, aging, abuse, etc. during use, which may lead to related failures. Undetected battery failure can adversely affect the battery...

AI Technical Summary

Problems solved by technology

[0006] SVM itself has some shortcomings: the number of support vectors is sensitive to the error boundary, the penalty factor and loss function are complex and difficult to determine; the prediction results lack the ability to express uncertainty

However, it is only used for life prediction at present, and the safety of batteries has not been comprehensively evaluated.

Images