Abstract | ||
---|---|---|
The fault detection of insulators is very important because these insulators, as insulation controls, play an important role in transmission lines. Under the background that the unmanned aerial vehicle (UAV) instead of manual inspection has become the trend for power line inspection, the automatic recognition of insulator faults from big data of aerial images is undoubtedly a key issue that must be solved. In this paper, a method using the deep convolutional neural network (DCNN) to detect insulator self-shattering is proposed. Compared with the traditional method, the proposed method can extract fault features from aerial images automatically and can recognize insulator self-shattering under the big data condition. The experiments of a testing set with 341 real-world images captured from a UAV show that the correct identification rate can reach 98.53%, which suggests that the model outperforms existing methods in detecting insulator self-shattering. The proposed method can be further improved when the training dataset is supplemented and updated in applications. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/s11042-018-6610-4 | Multimedia Tools and Applications |
Keywords | Field | DocType |
Deep learning, Insulators, Flaw detection, Pattern recognition, Convolutional neural network | Computer vision,Pattern recognition,Convolutional neural network,Fault detection and isolation,Computer science,Electric power transmission,Artificial intelligence,Deep learning,Big data,Insulator (electricity) | Journal |
Volume | Issue | ISSN |
78.0 | 8 | 1573-7721 |
Citations | PageRank | References |
1 | 0.39 | 13 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yanli Yang | 1 | 1 | 0.39 |
Lijuan Wang | 2 | 3 | 6.45 |
Ying Wang | 3 | 147 | 63.35 |
Xiuzhuang Mei | 4 | 1 | 0.39 |