中文摘要：

通过电路板搭建锂电池电压、电流、温度实时检测平台,在上位机界面实时监测锂电池参数的信息.根据检测到的数据,利用LM（Levenberg-Marquardt）算法,提出了基于BP神经网络的锂电池剩余电量（State of Charge,SoC）计算模型,模型以锂电池参数采集平台采集到的电压、电流数据为输入,电池的SoC为输出,利用实验室实测到的数据进行模型实验.结果表明：该模型具有较高的精度,并且泛化性能好,对于SoC的预测具有可行性.

英文摘要：

By using the circuit board to structure the battery parameters detection platform, such as voltage, current and temperature, and sending the parameters to computer. A model ofestimating the state ofcharge oflithium battery based on BP neural network was put forward. The input vector needed two factors--- voltage and current, and the output vector was the SoC of lithium battery. A test was done on the model by using the data measured in laboratory. The result of the test shows that the data calculated by the model is accurate and the model has good generalization ability, which is feasible for SoC prediction.