Power battery life prediction method and system

Abstract

The invention discloses a power battery life prediction method and system. The power battery life prediction method is realized based on a time sequence model and transfer learning. Specifically, themethod is based on a transfer learning mode, a third service life curve is obtained by using power battery service life test data, and then a service life offset curve is obtained by using a first service life curve and the third service life curve obtained by actual battery sample data; and finally, superposition correction is performed on the third service life curve by utilizing the service life offset curve so as to obtain a predicted life curve of the power battery. Therefore, on the basis of limited actual battery sample data, a purpose of obtaining a corresponding relation between the power battery life and the actual use in the complete life cycle of the power battery is achieved, and the predicted life curve is obtained by superposing and correcting the first life curve and the third life curve so that the predicted life curve is closer to the actual situation, and accuracy of predicting the power battery life is improved.

Description

technical field [0001] The present application relates to the technical field of vehicle engineering, and more specifically, to a method and system for predicting the life of a power battery. Background technique [0002] Battery life (State of Health, SOH), also known as battery capacity, health, and performance status, is simply the ratio of the performance parameters to the nominal parameters after the battery has been used for a period of time. The new battery is 100%, and it is completely scrapped. 0%. It can also be understood as the ratio of the capacity released by the battery from a fully charged state at a certain rate to the cut-off voltage and its corresponding nominal capacity, or the limit capacity of the battery. [0003] In the failure prediction and health management (Prognostic and Health Management, PHM) system of the automobile industry, the power battery life prediction is an important part. The methods for power battery life prediction in the prior art...

AI Technical Summary

Problems solved by technology

[0003]In the Prognostic and Health Management (PHM) system of the automobile industry, the power battery life prediction is an important part. The methods of battery life prediction mainly include: electrochemical analysis method, ampere-time method, impedance method, time series model, machine learning and other methods. Among them, the electrochemical analysis method, ampere-hour method and impedance method all need to invade the interior of the power battery. The power battery is destructive to different degrees, and the test time is long and the adaptability is poor; therefore, the use of time series model and machine learning to realize the life prediction of power battery can avoid the above problems, but no matter whether the time series model or machine learning is used Both methods are limited by the lack of actual samples or data of the power battery, which makes the prediction accuracy of the two methods for the life of the power battery unsatisfactory.

Images