摘要
太阳能光伏产业近年发展迅速,准确诊断光伏组件故障位置及类型可以提升运维人员的工作效率。提出一种基于卷积神经网络-长短期记忆模型(Convolutional Neural Networks-Long Short Term Memory,CNN-LSTM)的深度学习诊断模型,利用电站原有设备就可完成检测任务。首先提出了一种依据电流值的组件故障分类方式;然后,检测模型根据光伏阵列布局特点设计了一种特征提取算法,分别提取光伏阵列电流横向与纵向特征,来获取空间与时间上的特性;再通过CNN网络来对横向特征做进一步的提取与纵向特征的压缩,以解决特征种类单一及训练缓慢的问题;最终进入LSTM神经网络来完成对光伏组件的故障诊断。
The solar photovoltaic industry has developed rapidly in recent years.Accurate diagnosis of the location and type of PV module faults can improve the efficiency of operation and maintenance personnel.In this paper,a deep learning diagnostic model based on convolutional neural networks-long short term memory(CNN-LSTM)is proposed,which can be used to complete the detection task.In this paper,a fault classification method based on current performance is established.The algorithm firstly designs a feature extraction algorithm based on the layout characteristics of the PV array,and extracts the lateral and vertical features of the PV array current to obtain the spatial and temporal characteristics.The CNN network further extracts the lateral features and compresses the vertical features to solve the problem of single feature types and slow training.Finally,the LSTM neural network is used to complete the fault diagnosis of the PV modules.
作者
程起泽
陈泽华
张雲钦
蒋文杰
刘晓峰
沈亮
Cheng Qize;Chen Zehua;Zhang Yunqin;Jiang Wenjie;Liu Xiaofeng;Shen Liang(College of Data Science,Taiyuan University of Technology,Taiyuan 030001,China;Jinneng Clean Energy Co.,Ltd.,Taiyuan 030001,China)
出处
《电子技术应用》
2020年第4期66-70,共5页
Application of Electronic Technique
基金
国家重点研发计划资助项目(2018YFB1404500)。
