首页|基于MTF和AlexNet的电能质量扰动信号分类

基于MTF和AlexNet的电能质量扰动信号分类

扫码查看
针对传统电能质量扰动(power quality disturbances,PQDs)分类方法分类准确率低,分类速度慢等缺点,研究提出了一种结合马尔可夫变迁场(markov transition field,MTF)和卷积神经网络AlexNet的PQDs分类新方法。首先采用MTF方法对7种单一扰动和6 种复合扰动的特征向量进行了图像化处理,将一维扰动信号时间序列转换为具有时间相关性的二维特征图像,然后将特征图像作为AlexNet网络的输入进行自动特征提取,最后实现对不同类型PQDs信号的分类。实验结果表明,上述方法能较准确地对单一和复合PQDs信号进行分类,通过对不同分类方法的比较,验证了该方法的有效性。
Power Quality Disturbance Signal Classification Based on MTF and AlexNet
Considering the shortcomings of the traditional power quality disturbances(PQDs)classification meth-od,such as low classification accuracy and slow classification speed,in this study,a novel PQDs classification method combining Markov transition field and convolutional neural network AlexNet is proposed.Firstly,the MTF method was used to visualize the feature vectors of 7 single disturbances and 6 composite disturbances.The one-dimensional dis-turbance signal time series was converted into a two-dimensional feature image with temporal correlation.Then,the feature image was used as the input of the AlexNet network for automatic feature extraction.Finally,the classification of different types of PQDs signals was achieved.Experimental results show that the proposed method can accurately classify single and compound PQDs signals,and the effectiveness of the proposed method is verified by comparing dif-ferent classification methods.

Power qualityDisturbance classificationMarkov transition fieldConvolutional neural networkDeep learning

韩子萌、张占强、孟克其劳、谢宁宁

展开 >

内蒙古工业大学信息工程学院,内蒙古 呼和浩特市 010080

内蒙古工业大学能源与动力工程学院,内蒙古 呼和浩特市 010051

中国长江三峡集团有限公司科学技术研究院,北京 100038

电能质量 扰动分类 马尔可夫变迁场 卷积神经网络 深度学习

自治区直属高校基本科研业务费项目内蒙古自治区科技计划项目内蒙古自治区科技重大专项计划项目内蒙古自治区科技重大专项计划项目

ZTY20230232020GG02812020ZD00162021ZD0032

2024

计算机仿真
中国航天科工集团公司第十七研究所

计算机仿真

CSTPCD
影响因子:0.518
ISSN:1006-9348
年,卷(期):2024.41(9)
  • 11