A battery life prediction method for hybrid electric vehicles based on operating condition recognition

Abstract

The invention discloses a hybrid electric vehicle battery life prediction method based on working condition identification. The method comprises two parts of working condition identification and battery life prediction methods. Characteristic parameters of working conditions are trained by adopting a random forest model to realize identification of real-time working conditions; energy management control strategies under routes based on urban area, suburban area and highway working conditions are generated respectively for a hybrid electric vehicle, and the sums of the fuel consumption costs and the battery life attenuation costs of stages are taken as an optimized objective function; solution is carried out based on a dynamic programming algorithm, and a support vector machine (SVM) is utilized to divide the whole vehicle working mode; and the neural network model is trained by utilizing an optimization result of a corresponding working mode under each route, and a corresponding neuralnetwork-based energy management control strategy is established to realize battery life prediction. According to the hybrid electric vehicle battery life prediction method based on the working condition identification, the battery life is predicted in real time, the battery life is prolonged while the fuel economy of a whole vehicle is guaranteed, and the use cost of the vehicle is reduced.

Description

technical field [0001] The invention belongs to the field of hybrid electric vehicle battery life, more precisely, the invention relates to a hybrid electric vehicle battery life prediction method based on working condition identification. Background technique [0002] There are multiple power sources in hybrid electric vehicles, and it is necessary to reasonably coordinate the working status of each power source to meet the power requirements of the vehicle, and then give full play to its energy-saving advantages. Among them, the performance of the power battery directly affects the performance of the drive motor, thereby affecting the performance of the vehicle. Fuel economy and emission performance are the keys to achieve vehicle performance. [0003] The current research on battery life mainly focuses on building a battery life model under a single working condition based on data under a single experimental condition, and seldom considers the relationship between fuel ec...

AI Technical Summary

Problems solved by technology

The battery life model can be divided into model method and data-driven method. The model method is based on the battery operating mechanism and aging model, but the complexity is high and the prediction error is large; the data-driven method is based on a large amount of experimental data to build a battery life model. , can only accurately describe the battery life in a single experiment or under a single working condition

The actual driving conditions of hybrid electric vehicles are complex and changeable. Simply using the above two battery life models cannot accurately predict the real-time remaining service life of the battery, and the adaptability to the working conditions is poor, making it difficult to build a real-time prediction model for battery life. The key to improving battery performance and improving vehicle fuel economy

[0004] At present, the research on working condition identification is mainly focused on identifying the working condition category in real time, switching the control strategy under the corresponding category, and then improving the fuel economy of the whole vehicle. For example, the Chinese patent publication number is CN106004865A, and the publication date is 2016-10-12. A mileage adaptive hybrid electric vehicle energy management method based on working condition identification is disclosed. For plug-in hybrid electric vehicles, by identifying working conditions and adapting to different driving mileage and working conditions, the fuel economy of the whole vehicle is improved, but This method does not take into account the impact of battery life attenuation on fuel economy; while the research on energy management considering battery life attenuation mainly focuses on predicting battery life under a single working condition. For example, the Chinese patent publication number is CN107878445A, and the publication date is 2018 -04-06, a hybrid electric vehicle energy management method considering battery life is disclosed, the battery life decay is considered in the offline global optimization control, and the battery life is improved, without considering the impact of changes in driving conditions on battery life impact; the existing public patents do not fully consider the relationship between the actual complex and changeable driving conditions and battery life prediction, making it difficult to accurately predict the capacity of hybrid electric vehicle batteries under actual driving conditions. It is impossible to accurately determine the remaining service life of the battery, which will lead to a decrease in the performance of the battery, which is not conducive to improving the fuel economy of the vehicle. This patent has formulated a battery life prediction method based on working condition identification for hybrid electric vehicles. It is of great significance to save energy and improve the adaptability of the system to the actual driving conditions

Images