基于FPGA和BP神经网络的电池管理系统设计

Battery management system design based on FPGA and BP neural network

在研究锂电池动态性能的基础上,通过大量数据仿真和实际数据测量及修正,设计了电动汽车电池管理系统。基于FPGA内核,采用SOPC嵌入式系统技术,移植UC/OS-II嵌入式实时操作系统,实现了对电动汽车锂电池数据采集、数据通信、均衡管理和自动保护等功能。结合电池实时电压和电流,采用BP神经网络对电池荷电状态(SOC)及健康状态(SOH)进行准确估算,为电动汽车运行提供了监控措施和安全保障。

On the basis of the dynamic performance study of Li-lion battery, the battery management system was designed through the measurement and revise of various simulation and experiment data. Based on the core of FPGA, the SOPC embedded system and explanting embedded real time operating system of UC/OS-II were used to realize the functions of data collection, data communication, balanced management and automatic protection of the electric car＇s Li-lion. Based on the real-time data of voltage and current, the BP neural network was used to accurately estimate the state of charge （SOC） and state of health （SOH） of battery, providing supervision measure and safety guarantee for the operation of electric car.