Jia Xin, Zhang Jinglei, Wen Xianbin. Infrared faults recognition for electrical equipments based on dual supervision signals deep learning[J]. Infrared and Laser Engineering, 2018, 47(7): 703003-0703003(7). doi: 10.3788/IRLA201847.0703003
Citation:
|
Jia Xin, Zhang Jinglei, Wen Xianbin. Infrared faults recognition for electrical equipments based on dual supervision signals deep learning[J]. Infrared and Laser Engineering, 2018, 47(7): 703003-0703003(7). doi: 10.3788/IRLA201847.0703003
|
Infrared faults recognition for electrical equipments based on dual supervision signals deep learning
- 1.
Tianjin Key Laboratory for Control Theory & Applications in Complicated System,Tianjin 300384,China;
- 2.
School of Electrical and Electronic Engineering,Tianjin University of Technology,Tianjin 300384,China;
- 3.
Key Laboratory of Computer Vision and System,Ministry of Education of China,Tianjin University of Technology,Tianjin 300384,China
- Received Date: 2018-02-13
- Rev Recd Date:
2018-03-17
- Publish Date:
2018-07-25
-
Abstract
In order to improve the accuracy of infrared fault image recognition for electrical equipment, an infrared fault image recognition method for electrical equipment based on double supervised signal deep learning was proposed. Firstly, a Slic super pixel segmentation algorithm was adopted to merge the similar pixel regions into blocks. According to the luminance information provided by the improved HSV space transformation, the temperature abnormal regions were determined. Secondly, the connected areas and the corresponding device of this region were separated. Finally, based on the GoogLeNet convolution neural network model, fault features of infrared images for electrical equipments were extracted, then trained and supervised by two kinds of signals, i.e., the softmax loss and the center loss signal. Among an established 700 infrared fault of electrical equipment images dataset, 500 of which are for training, and 200 for testing. Experiments results show that the test accuracy rate can reach to 98.6% which enhanced 1% when being compared with the classic method simply using the single softmax loss. The algorithm can accurately locate five kinds of electrical equipments which include the transformer bushing, current transformer, surge arrester, isolating switch, insulators, as well as identify the corresponding faults.
-
References
[1]
|
Lin Ying, Guo Zhihong, Chen Yufeng. Convolutional-recursive network based current transformer infrared fault image diagnosis[J]. Power System Protection and Control,2015,43(16):87-94. (in Chinese) |
[2]
|
Wei Gang, Feng Zhongzheng, Tang Yue, et al. The infrared diagnostic technology of power transmission devices and experimental study[J]. Electrical Engineering, 2013, 14(6):75-78. (in Chinese) |
[3]
|
Wang Jialin, Cui Haoyang, Xu Yong, et al. Infrared image diagnosis method of transformer substation equipment base on SOM neural network[J]. Journal of Shanghai University of Electric Power, 2016, 32(1):78-82. (in Chinese) |
[4]
|
Zhang Difei, Zhang Jinsuo, Yao Keming, et al. Infrared ship-target recognition based on SVM classification[J]. Infrared and Laser Engineering, 2016, 45(1):0104001. (in Chinese) |
[5]
|
Xie Saining, Ross Girshick, Piotr Dollr, et al. Aggregated residual transformations for deep neural networks[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2017:1492-1500. |
[6]
|
Wang Wanguo, Tian Bing, Liu Yue, et al. Study on the electrical devices detection in UAV images based on region based convolutional neural networks[J]. Journal of Geo-Information Science, 2017, 19(2):256-263. (in Chinese) |
[7]
|
Liu Bin, Zhang Jian. Partial discharge recogniton in power transformers based on convolutional neural networks[J]. High Voltage Apparatus, 2017, 53(5):70-74. (in Chinese) |
[8]
|
Wang Juan, Wang Ping, Wang Gang. Stippled direct part mark location based on self-adaptive super-pixels segmentation[J]. Acta Automatica Sinica, 2015, 41(5):991-1003. (in Chinese) |
[9]
|
Liu Wei, Christian Szegedy, Jia Yangqing, et al. Going deeper with convolutions[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2015:1-9. |
[10]
|
Wen Yandong, Zhang Kaipeng, Li Zhifeng, et al. A discriminative feature learning approach for deep face recognition[C]//European Conference on Computer Vision, 2016:499-515. |
-
-
Proportional views
-