基于STM32的非侵入式负荷监测系统设计  

Design of Non-invasive Load Monitoring System Based on STM32

作　　者：陆磊 梁喆[1] LU Lei;LIANG Zhe(College of Electrical and Information Engineering,Anhui University of Science and Technology,Huainan Anhui 232001,China)

机构地区：[1]安徽理工大学电气与信息工程学院,安徽淮南232001

出　　处：《佳木斯大学学报（自然科学版）》2021年第4期38-42,共5页Journal of Jiamusi University：Natural Science Edition

基　　金：国家自然科学基金项目(61873004);安徽省科技重大专项(201903a07020013);国网公司科学技术项目(SGAHDK00DJJS1900077)。

摘　　要：传统的侵入式负荷监测方法在实际应用中安装复杂,成本高,无法满足日益发展的电力系统需求。为此设计了一种基于STM32的非侵入式负荷监测系统,系统以STM32F103芯片为主控制器,利用AD8629放大器和ADS1256芯片进行高精度电信号采样,通过USB与上位机通信,在Labview界面中进行实时显示,并建立卷积神经网络算法模型进行负荷识别。将嵌入式系统与辨识算法进行结合,通过实验验证了用电负荷监测与识别的可行性,且系统实时性好,测量精度高,成本低,有较强的实用性。The traditional intrusive load monitoring methods are complex to install in practical applications,high cost and can′t meet the growing demand of power system.A non-invasive load monitoring system based on STM32 is designed.The system takes STM32 F103 as its main controller,uses AD8629 amplifier and ADS 1256 clip for high-precision electrical signal sampling,communicates with PC through USB,displays real-time in Labview interface,and establishes a convolution neural network algorithm model for load identification.Combining embedded system with identification algorithm,the feasibility of power load monitoring and identification is verified through experiments.The system has good real-time performance,high measurement accuracy,low cost and strong practicability.

关 键 词：负荷监测 非侵入式 嵌入式 卷积神经网络 

分 类 号：TM933[电气工程—电力电子与电力传动]