• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Energy Conversion & Management >Adaptive online state-of-charge determination based on neuro-controller and neural network
【24h】

Adaptive online state-of-charge determination based on neuro-controller and neural network

机译：基于神经控制器和神经网络的自适应在线荷电状态确定

获取原文
获取原文并翻译 | 示例
       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper presents a novel approach using adaptive artificial neural network based model and neuro-controller for online cell State of Charge (SOC) determination. Taking cell SOC as model's predictive control input unit, radial basis function neural network, which can adjust its structure to prediction error with recursive least square algorithm, is used to simulate battery system. Besides that, neuro-controller based on Back-Propagation Neural Network (BPNN) and modified PID controller is used to decide the control input of battery system, i.e., cell SOC. Finally this algorithm is applied for the SOC determination of lead-acid batteries, and results of lab tests on physical cells, compared with model prediction, are presented. Results show that the ANN based battery system model adaptively simulates battery system with great accuracy, and the predicted SOC simultaneously converges to the real value quickly within the error of ±1 as time goes on.
机译：本文提出了一种基于自适应人工神经网络的模型和神经控制器的在线电池荷电状态（SOC）确定的新方法。以电池SOC为模型的预测控制输入单元，采用径向基函数神经网络通过递推最小二乘算法将其结构调整至预测误差，从而对电池系统进行仿真。除此之外，基于反向传播神经网络（BPNN）和改进的PID控制器的神经控制器用于确定电池系统的控制输入，即电池SOC。最后将该算法用于铅酸蓄电池的SOC测定，并与模型预测结果进行对比，给出了物理电池实验室测试的结果。结果表明，基于ANN的电池系统模型可以高精度地自适应地模拟电池系统，并且随着时间的推移，预测的SOC会在±1的误差范围内同时迅速收敛到实际值。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号