Research on data processing of power terminal plug and play system based on convolutional neural network

The purpose of this study is to use convolutional neural network (CNN) to improve the data processing capability of power terminal plug and play system, and realize intelligent equipment identification and fault diagnosis. Firstly, real-time data of power terminal equipment, including voltage, current and power signals, is collected and pre-processed to improve data quality through de-noising and normalization. Then, the CNN architecture suitable for power data processing is designed, including input layer, convolution layer, pooling layer, fully connected layer and output layer, and ReLU activation function and cross entropy loss function are used. Large-scale power system data sets are used for model training, parameters are adjusted by optimization algorithms, and model performance is evaluated by cross-validation and test data. Experimental results show that the CNN-based system is superior to traditional methods in feature extraction, recognition accuracy and real-time performance.