US 11,656,298 B2
Deep parallel fault diagnosis method and system for dissolved gas in transformer oil
Yigang He, Hubei (CN); Xiaoxin Wu, Hubei (CN); Jiajun Duan, Hubei (CN); Yuanxin Xiong, Hubei (CN); and Hui Zhang, Hubei (CN)
Assigned to WUHAN UNIVERSITY, Hubei (CN)
Filed by WUHAN UNIVERSITY, Hubei (CN)
Filed on Jan. 28, 2021, as Appl. No. 17/160,415.
Claims priority of application No. 202010134616.3 (CN), filed on Mar. 2, 2020.
Prior Publication US 2021/0278478 A1, Sep. 9, 2021
Int. Cl. G01R 31/62 (2020.01); G01N 33/00 (2006.01); G06N 3/045 (2023.01); G06N 3/044 (2023.01)
CPC G01R 31/62 (2020.01) [G01N 33/0004 (2013.01); G06N 3/045 (2023.01); G06N 3/044 (2023.01)] 16 Claims
OG exemplary drawing
 
1. A deep parallel fault diagnosis method for dissolved gas in transformer oil, comprising following steps executing by a processor:
step 1: performing an operation of a plurality of transformers of a power system of a power grid and obtaining a plurality of groups of monitoring data of dissolved gas in each transformer oil of the plurality of transformers of the power system of the power grid, analyzing a dissolved gas content in each of the groups of monitoring data, obtaining a corresponding fault type label, performing a normalizing processing on each of the groups of monitoring data, and forming a target data set by combining the normalized groups of monitoring data with the corresponding fault type label;
step 2: dividing the target data set into a first training set and a first verification set, training a long short-term memory (LSTM) diagnosis model with the first training set, and verifying the trained LSTM diagnosis model with the first verification set;
step 3: performing image processing on each group of data in the target data set to obtain an image data set, dividing the image data set into a second training set and a second verification set, training a convolutional neural network (CNN) diagnosis model with the second training set, and verifying the trained CNN diagnosis model with the second verification set;
step 4: performing a deep parallel fusion on outputs of softmax layers of the trained LSTM diagnosis model and the trained CNN diagnosis model, respectively, and outputting a final diagnosis result according to a maximum confidence principle; and
step 5: modifying the operation of the plurality of transformers of the power system of the power grid based on the final diagnosis result.