The invention provides a method for estimating the state of charge of a battery pack based on cloud-side collaboration, relates to the technical field of electric batteries, and achieves the estimation of the state of charge of the battery pack through the collaborative management and information interaction of a cloud control platform and a vehicle-end battery management system. The vehicle end battery management system uploads collected data to the cloud control platform and stores the data in a historical database, the cloud control platform selects a representative battery by establishing an E-Q graphic model, and meanwhile, the data in the historical database is used for training an LSTM neural network model and outputting the data to the vehicle end battery management system; the vehicle end battery management system is based on an estimation model trained at the cloud end and uses an extended Kalman filtering algorithm to realize accurate real-time state-of-charge estimation, the cloud control platform stores and analyzes big data, completes tasks with complex calculation, and retrains, optimizes and corrects a vehicle end model regularly to ensure the accuracy of the vehicle end model.
本发明提供一种基于云边协同的电池组荷电状态估计方法,涉及电电池技术领域,本发明通过云控平台与车端电池管理系统的协同管理和信息交互,实现电池组的荷电状态估计,车端电池管理系统将采集的数据上传到云控平台并储存在历史数据库,云控平台通过建立E‑Q图形模型选出代表性电池,同时将历史数据库中的数据对LSTM神经网络模型进行训练,并输出到车端电池管理系统,车端电池管理系统基于云端训练好的估计模型,并使用扩展卡尔曼滤波算法实现准确的实时荷电状态估计,云控平台对大数据进行存储、分析,完成计算复杂的任务,并定期对车端模型进行再训练优化更正,保证车端模型的准确性。
Battery pack state-of-charge estimation method based on cloud edge collaboration
一种基于云边协同的电池组荷电状态估计方法
2024-06-14
Patent
Electronic Resource
Chinese