结合自适应模糊推理和神经网络的物联网混合发电系统  

The IoT hybrid generation system based on ANFIS and ANN

作　　者：萧威 殷志祥 叶子 杨静 XIAO Wei;YIN Zhixiang;YE Zi;YANG Jing(School of Electrical and Information Engineering,Anhui University of Science&Technology,Huainan 232001,China;Guohua Energy Investment Co.,Ltd.,Beijing 100007,China;School of Mathematics,Physics and Statistics,Shanghai University of Engineering Science,Shanghai 201620,China;State Grid General Aviation Co.,Ltd.,Beijing 102209,China;School of Mathematics and Big Data,Anhui University of Science&Technology,Huainan 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 [2]国华能源投资有限公司,北京100007 [3]上海工程技术大学数理与统计学院,上海201620 [4]国网通用航空有限公司,北京102209 [5]安徽理工大学数学与大数据学院,安徽淮南232001

出　　处：《现代电子技术》2022年第5期97-102,共6页Modern Electronics Technique

基　　金：国家自然科学基金项目(61702008)。

摘　　要：为了较好地预测可再生能源的发电输出,对模型效率进行分析,在物联网系统的基础上,提出一种基于人工神经网络(ANN)与自适应网络模糊推理系统(ANFIS)的混合预测模型。首先,利用压电传感器、体热电转换器和太阳能板用于可再生能源发电,并将其连接到能量存储电路,以产出电能;然后,使用ESP8266模块连接数据和云服务器,利用ANN和ANFIS混合模型处理从可再生能源中生成的所有电能,将3个不同模块采集得到的数据集用于模型的训练和测试;最后,利用采集到的数据开发4个模型,通过均方根误差(RMSE)和相关系数(R;)分析模型的效率,以选择最合适的模型。实验结果表明,所提模型具有较好的RMSE和R;性能,其模糊信息较少,结果误差较小,具有一定的应用价值。In order to better predict the power output of renewable energy and analyze the efficiency of the model,a hybrid prediction model based on artificial neural network(ANN) and adaptive network based fuzzy inference system(ANFIS) is proposed on the basis of the Internet of Things(IoT). Piezoelectric sensors,bulk thermoelectric converters and solar panels are used for renewable energy generation and connected to the energy storage circuit to generate electricity. The ESP8266 module is used to connect the data and the cloud server. The hybrid model based on ANN and ANFIS is used to process all of the electric energy generated by renewable energy. The data sets collected by three different modules are used for the training and testing of the model. The collected data are used to develop four models. The root mean square error(RMSE)and correlation coefficient(R;)are used to analyze the efficiency of the model,so as to select the most suitable model. The experimental results show that the proposed model has better RMSE and R;performance. Its fuzzy information is less and its error is smaller,so it has a certain application value.

关 键 词：混合预测模型 物联网 人工神经网络 自适应网络模糊推理系统 云服务器 传感器 可再生能源 能量存储电路 

分 类 号：TN99-34[电子电信—信号与信息处理] TM615[电子电信—信息与通信工程]