摘要
针对现有用电器识别系统计算复杂、成本居高不下等问题,基于STM32设计了一个高精度的用电器识别实验装置。首先,设计前端信号调理及同步采样电路,通过电流互感器和ADS8688对网侧电流进行采样。其次,构建特征融合模型和损失函数,对用电器的时域和频域波形进行多特征融合。最后,对各种用电器进行混合识别实验。测试结果表明,该装置在多种大功率用电器的组合实验中识别率高达100%,在小功率用电器组合实验中识别率稳定在95%以上,在大功率用电器和小功率用电器的高动态识别实验中识别准确率高达90%以上,达到了预期设计要求。
In response to the high computational complexity and high cost of existing electrical appliance recognition systems,a highprecision electrical appliance analysis and recognition experimental device is designed based on STM32.Firstly,design a front-end signal conditioning and synchronous sampling circuit,which samples the grid side current through a current transformer and ADS8688.Then a feature fusion model and a loss function are constructed to fuse the time-domain and frequency-domain waveforms of electrical appliances with multiple features.Finally,a hybrid recognition experiment was conducted on electrical appliances used in the network.The test results show that the recognition rate is as high as 100%in the combination experiment of multiple high power appliances,and stable at over 95%in the combination experiment of low power appliances.In the high dynamic recognition experiment of high power appliances and low power appliances,the recognition accuracy is as high as 90%,meeting the expected design requirements.
作者
白迪
雷瑶瑶
杨春勇
朱会宗
陈少平
Bai Di;Lei Yaoyao;Yang Chunyong;Zhu Huizong;Chen Shaoping(College of Electronics and Information Engineering,South-Central Minzu University,Wuhan,430074,China;Hubei Key Laboratory of Intelligent Wireless Communications,South-Central Minzu University,Wuhan,430074,China)
出处
《中国现代教育装备》
2023年第23期39-42,共4页
China Modern Educational Equipment
基金
国家自然科学基金(编号:62201621)
教育部协同育人项目(编号:220604307014714)
中央高校专项基金(编号:CZQ23049)。
关键词
电流互感器
损失函数
多特征融合
用电器识别
current transformer
loss function
multi-feature fusion
electrical identification
