Lithium-ion battery SOC estimation based on deep reinforcement learning Kalman filter
基于深度强化学习卡尔曼滤波锂离子电池SOC估计

摘要

随着全世界各国的汽车制造业快速发展和各国排放标准要求提高，电动汽车发展快速崛起，引起了世界上各个国家政府和环保组织的高度重视。我国作为汽车大国，我国针对电动汽车发展也高度关注。续航时间与行驶安全是新型汽车性能研究的主要方向。电动汽车取代传统汽车，关键点在于提高车用锂电池的性能。在锂电池性能研究方面，锂电池的SOC估计的准确度是锂电池的研究中一个重要内容。准确估计锂电池SOC能提升锂电池的使用时间，提升电池的充放电性能。

Abstract

With the rapid development of the automobile manufacturing industry in various countries around the world and the improvement of emission standards in various countries, the rapid rise of the development of electric vehicles has aroused the great attention of governments and environmental protection organizations in the world. As an automobile country, China is also highly concerned about the development of electric vehicles. Endurance and driving safety are the main research directions of new vehicle performance. Electric vehicles replace traditional cars, the key point is to improve the performance of lithium batteries for vehicles. In the research of lithium battery performance, the accuracy of SOC estimation of lithium battery is an important content in the research of lithium battery. Accurate estimation of lithium battery SOC can improve the service life of lithium batteries and improve the charge and discharge performance of batteries.