Power equipment fault image recognition disaster exploration system and method based on multiple DCNN networks

The invention discloses a multi-DCNN network-based power equipment fault image recognition disaster-exploration system. A data set preparation module which is used for obtaining an image data set of damaged power equipment, dividing the image data set into a training set and a test set, and then carrying out the preprocessing of the training set and the test set; an image feature extraction module extracts global features and local features of the preprocessed training set; a feature fusion module obtains joint features; and a classification network training module diagnoses the images in the test set by using the test set and the convolutional neural network of the DCNN in which the hierarchical structure of a convolutional layer, a full connection layer and a pooling layer is determined, and confirms the image fault labels of the images in the test set. According to the invention, the problems of low fault detection speed and low accuracy of key components of power equipment in a post-disaster field in the