Abstract: The disclosure provides a deep parallel fault diagnosis method and system for dissolved gas in transformer oil, which relate to the field of power transformer fault diagnosis. The deep parallel fault diagnosis method includes: collecting monitoring information of dissolved gas in each transformer substation and performing a normalizing processing on the data; using the dissolved gas in the oil to build feature parameters as the input of the LSTM diagnosis model, and performing image processing on the data as the input of the CNN diagnosis model; building the LSTM diagnosis model and the CNN diagnosis model, respectively, and using the data set to train and verify the diagnosis models according to the proportion; and using the DS evidence theory calculation to perform a deep parallel fusion of the outputs of the softmax layers of the two deep learning models.

Abstract: The disclosure provides a deep parallel fault diagnosis method and system for dissolved gas in transformer oil, which relate to the field of power transformer fault diagnosis. The deep parallel fault diagnosis method includes: collecting monitoring information of dissolved gas in each transformer substation and performing a normalizing processing on the data; using the dissolved gas in the oil to build feature parameters as the input of the LSTM diagnosis model, and performing image processing on the data as the input of the CNN diagnosis model; building the LSTM diagnosis model and the CNN diagnosis model, respectively, and using the data set to train and verify the diagnosis models according to the proportion; and using the DS evidence theory calculation to perform a deep parallel fusion of the outputs of the softmax layers of the two deep learning models.

Abstract: The disclosure discloses an analog circuit fault feature extraction method and system based on an optimal wavelet basis function, and belongs to the field of electronic circuit engineering and computer vision, and the method comprises the steps of obtaining output signals of an analog circuit during different faults; sequentially applying wavelet transformation methods based on different wavelet basis functions to extract features of output signals; for each feature, calculating the center position of each fault, the distance from each fault data point to the center position, the farthest position of the fault data point and the average position of the fault data points; and determining an optimal wavelet basis function for analog circuit fault feature extraction according to a score discriminating method.