基于小波变换与神经网络的非侵入式家电负荷监测研究  

Research on Non-Intrusive Load Monitoring Based on Wavelet Transform and Neural Network

作　　者：张媛 王飞[2] 张照锋[1] 崔秀华[1] 翟琳 ZHANG Yuan;WANG Fei;ZHANG Zhaofeng;CUI Xiuhua;ZHAI Lin(School of Electronic Information,Nanjing Vocational College of Information Technology,Nanjing Jiangsu 210023,China;College of Artificial Intelligence and Automation,Hohai University,Nanjing Jiangsu 210024,China)

机构地区：[1]南京信息职业技术学院电子信息学院,江苏南京210023 [2]河海大学人工智能与自动化学院,江苏南京210024

出　　处：《电子器件》2024年第3期749-756,共8页Chinese Journal of Electron Devices

基　　金：江苏省高等学校基础科学(自然科学)面上项目(21KJB520014)。

摘　　要：智能家电智能化程度越来越高,同一电器对应的工作模式也越来越多。目前家电的非侵入式负荷监测仅仅采用传统家电单一负荷曲线进行研究,极大局限了非侵入式负荷监测技术的应用推广。为此,以智能洗衣机不同工作模式为例,研究了同一家电不同模式下的用电负荷特征,采集了智能家电中洗衣机不同工作模式下的用电负荷数据,通过小波变换的方法对负荷曲线进行平滑与特征信息提取,并基于统计学思想对表征特征信息的特征向量进行了评价,建立神经网络模型对不同工作模式的负荷曲线进行了识别,通过MATLAB平台仿真,证明了基于小波分析特征提取及神经网络特征识别的方法在非侵入式智能家电负荷监测中的可行性,识别准确率较高,具有良好的应用推广价值。Smart home appliances are becoming more and more intelligent,and the working mode is also becoming more and more various.At present,the non-invasive load monitoring of household appliances only adopts the single load curve of traditional household appliances,which greatly limits the application and popularization of non-invasive load monitoring technology.Therefore,different working modes of smart washing machine are taken as an example to study the power load characteristics of the same household appliance in different working modes,the power load data of the washing machine in smart household appliance in different working modes are collected,the load curve is smoothed,the feature information is extracted through the method of wavelet transform,and the feature vector representing the feature information is evaluated based on the idea of statistics.A neural network model is established to identify the load curves of different working modes.Through MATLAB platform simulation,it is proved that the method based on wavelet analysis feature extraction and neural network feature recognition is feasible in non-invasive intelligent home appliance load monitoring,the proposed method is with high accuracy and good application value.

关 键 词：非侵入式 负荷监测 小波分析 神经网络 

分 类 号：TM925.02[电气工程—电力电子与电力传动] TP183[自动化与计算机技术—控制理论与控制工程]