基于BP神经网络的用电器识别系统设计  

The Design of Electrical Appliance Recognition System Based on BP Neural Network

作　　者：程春雨 刘正龙 颜科宇 王海洋 马驰 吴振宇 CHENG Chunyu;LIU Zhenglong;YAN Keyu;WANG Haiyang;MA Chi;WU Zhenyu(Faculty of Electronic Information and Electrical Engineering,Dalian University of Technology,Dalian 116024,China;School of Innovation and Entrepreneurship,Dalian University of Technology,Dalian 116024,China)

机构地区：[1]大连理工大学电子信息与电气工程学部,大连116024 [2]大连理工大学创新创业学院,大连116024

出　　处：《实验科学与技术》2021年第2期11-16,共6页Experiment Science and Technology

基　　金：教育部本科教学质量工程项目(ZL2020088);教育部产学合作协同育人项目(201901080005);辽宁省大学生创新创业训练项目(2019101411600010084);大连理工大学教材出版基金(JC2019007)。

摘　　要：为完成针对用电器使用情况的精确识别研究课题,该文设计了电参数测量装置,主要包括电参数测量电路、无线通讯单元和电源供电单元,电参数测量装置主要用于采集单个用电器工作电流数据并传送给上位机存储留待后续处理。上位机将接收到的数据进行复合数字滤波,并基于BP神经网络通过叠加原理排列组合出多种情况,生成训练数据集,从而实现用电器识别。实验证明:只需采集少量样本即可完成对所有已学习用电器使用情况的识别,并且针对多个用电器同时使用的复杂情况,有着比传统方法更高的准确性。In order to complete the research of accurate identification of the use of electrical appliances,an electrical parameter measuring device that mainly incorporates the electrical parameter measuring circuit,the wireless communication unit and the power supply unit is designed.The electrical parameter measuring device is mainly applied to collect the working current data of a single electrical appliance and transmit it to the upper computer for processing.After the received data is processed by compound digital filter,the upper computer can generate training data-set for the purpose of electrical appliance recognition by a variety of permutations and combinations based on BP neural network through superposition principle.Experimental results show that the recognition of the usage of all learned electrical appliances can be completed with only a small number of samples;the recognition system has higher accuracy than traditional methods in a more complex situation where multiple electrical appliances are used at the same time.

关 键 词：用电器识别 电参数测量 复合数字滤波 神经网络 

分 类 号：TN911.7[电子电信—通信与信息系统]