| 基于鲸鱼算法优化极限学习机的微电网故障诊断 |
| |
| 引用本文： | 卢雪琴,李长安,吴忠强.基于鲸鱼算法优化极限学习机的微电网故障诊断[J].陕西电力,2022,0(2):15-21. |
| |
| 作者姓名： | 卢雪琴 李长安 吴忠强 |
| |
| 作者单位： | （1.燕山大学工业计算机控制工程河北省重点实验室，河北秦皇岛 066004；2.燕山大学河北省重型机械流体动力传输与控制重点实验室，河北秦皇岛 066004） |
| |
| 摘 要： | 提出一种基于鲸鱼算法优化极限学习机的微电网故障诊断方法。首先利用小波包分解对三相故障电压进行分析，计算小波包能量熵组成特征向量作为数据样本；然后通过鲸鱼算法优化极限学习机建立诊断模型对故障类型进行识别和诊断。最后利用鲸鱼算法优化极限学习机的输入权值和隐层神经元阈值，解决了输入权值和隐层神经元阈值随机初始化易影响网络性能的问题，可进一步提高网络的学习速度和泛化能力，有利于进行全局寻优。仿真结果表明，与BP神经网络、RBF神经网络和ELM相比，基于鲸鱼算法优化极限学习机建立的故障诊断模型学习速度更快、泛化能力更强、识别精度更高。
|
| 关 键 词： | 微电网 小波包分解 极限学习机 鲸鱼算法 故障诊断 |
Microgrid Fault Diagnosis Based on Extreme Learning Machine Optimized by Whale Algorithm |
| |
| LU Xueqin,LI Chang’an,WU Zhongqiang.Microgrid Fault Diagnosis Based on Extreme Learning Machine Optimized by Whale Algorithm[J].Shanxi Electric Power,2022,0(2):15-21. |
| |
| Authors: | LU Xueqin LI Chang’an WU Zhongqiang |
| |
| Affiliation: | （1. Key Lab of Industrial Computer Control Engineering of Hebei Province， Yanshan University， Qinhuangdao 066004，China； 2. Key Laboratory of Advanced Forging & Stamping Technology and Science of Ministry of Education of China， Yanshan University， Qinhuangdao 066004， China） |
| |
| Abstract: | ?The paper proposes a microgrid fault diagnosis method based on extreme learning machine （ELM）optimized by whale algorithm. Firstly， the three-phase fault voltage is analyzed by wavelet packet decomposition， and the feature vector composed of wavelet packet energy entropy is calculated as data samples. Then the whale algorithm is used to optimize the extreme learning machine， establishing a diagnostic model to identify and diagnose the fault type of the microgrid. Finally， the input weights and hidden layer neuron thresholds of the extreme learning machine is optimized with the whale algorithm ， solving the problem that the random initialization of the input weights and hidden layer neuron thresholds easily affects the network performance， and further improving the learning speed and generalization ability of the network. It is conducive to global optimization. The simulation results show that compared with BP neural network， RBF neural network and ELM， the fault diagnosis model based on the extreme learning machine optimized by the whale algorithm has faster learning speed， stronger generalization ability and higher recognition accuracy. |
| |
| Keywords: | microgrid wavelet packet decomposition extreme learning machine whale algorithm fault diagnosis |
|
| 点击此处可从《陕西电力》浏览原始摘要信息 |
|
点击此处可从《陕西电力》下载全文 |
