基于ANN方法的锂离子电池放电容量预测

Prediction of discharge capacity of lithium ion batteries based on artificial neural network method

锂离子电池放电容量的预测和估计是电池管理系统中一个非常重要的内容。某一个状态下锂离子电池的放电容量是放电电流、电压、温度以及过去电池充放电的历史等参数的函数。运用ANN方法即人工神经网络方法 ,可逼近任何多输入输出参数函数的性能 ,预测不同放电电流和电压下锂离子电池放电容量的大小。结果表明 ,ANN方法具有足够的精度 ,可用来预测锂离子电池的放电容量。

The prediction of discharge capacity of lithium ion batteries was one of the main tasks of battery management system.The discharge capacity of a lithium ion batteries was related with many parameters, including discharge current, voltage, temperature, and the past charge and discharge history. The ANN (artificial neural network) method, which could be used to approach nonlinear function with many input and output parameters, was used to estimate the discharge capacity of lithium ion batteries when changing the discharge current and voltage. The computed result showed the ANN method was a quite accurate algorithm, and could be used in prediction of discharge capacity of lithium ion batteries.