| 朱晓青,马定寰,李圣清,吴文凤,明瑶,张煜文.基于BP神经网络的微电网蓄电池荷电状态估计[J].电子测量与仪器学报,2017,31(12):2042-2048 |
| 基于BP神经网络的微电网蓄电池荷电状态估计 |
| Estimation of state of charge for micro grid battery based on BP neural network |
| |
| DOI：10.13382/j.jemi.2017.12.023 |
| 中文关键词: 微电网 蓄电池 荷电状态 BP神经网络 增强型学习率自适应算法 |
| 英文关键词:micro grid battery state of charge BP neural network new adaptive algorithm |
| 基金项目:国家自然科学基金(61673165)、湖南省自然科学基金(2017JJ4024)、湖南省教育厅开放基金 (15k036)、湖南省重点实验室(2016TP1018)资助项目 |
|
|
| Author | Institution |
| Zhu Xiaoqing | College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China |
| Ma Dinghuan | College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China |
| Li Shengqing | College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China |
| Wu Wenfeng | College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China |
| Ming Yao | College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China |
| Zhang Yuwen | College of Electrical and Information Engineering, Hunan University of Technology, Zhuzhou 412007, China |
|
| 摘要点击次数: 2105 |
| 全文下载次数: 6387 |
| 中文摘要: |
| 由于微电网蓄电池工作时的电力特性具有明显的非线性和不规则性，依靠传统数学方法难以准确估计其荷电状态(state of charge，SOC)。针对上述问题，构建了BP神经网络拓扑结构，并采用增强型学习率自适应算法对网络的传统学习模式加以改进，学习时神经网络模型中各神经元间权值得到合理调整，并且提高了误差收敛效率。仿真结果表明，估计结果在预设精度要求的范围之内，平均误差不超过4%，证明经过优化学习算法的BP神经网络模型对蓄电池荷电状态的精确估计是有效可行的。 |
| 英文摘要: |
| The electric characteristic of micro grid’s battery has obvious nonlinearity and irregularity at work, it is difficult to accurately estimate the using the traditional mathematical methods. According to the problem above, the topology of back propagation (BP) neural network is constructed, and the network model is trained with new adaptive algorithm to improve the traditional learning model, the weights among neurons in the neural network model are adjusted reasonably, and the error is reduced with higher efficiency. The simulation result shows that the estimated results are within the scope of pre set accuracy, the average error is less than 4%. It indicates that the BP neural network using the optimized algorithm can accurately estimate the state of charge, the attempt is effective and feasible. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
