A Contactless Insulator Contamination Levels Detecting Method Based on Infrared Images Features and RBFNN
| Autor: | Zhenyuan Zhang, Diansheng Luo, Tianguang Lu, Hong Ying He, Yijia Cao, Wei-Jen Lee |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Infrared image
010302 applied physics Artificial neural network Infrared Computer science business.industry Noise reduction Computer Science::Neural and Evolutionary Computation 020208 electrical & electronic engineering Feature extraction Image processing Pattern recognition 02 engineering and technology Image segmentation Contamination 01 natural sciences Industrial and Manufacturing Engineering Control and Systems Engineering 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Image noise Artificial intelligence Electrical and Electronic Engineering Gradient descent business |
| Zdroj: | IAS |
| ISSN: | 1939-9367 0093-9994 |
| DOI: | 10.1109/tia.2018.2889835 |
| Popis: | A contactless method uses infrared image features and radial basis function neural network (RBFNN) to detect contamination levels for porcelain insulators is proposed in this paper. First, theory evidence for contamination levels detection by infrared images is inferred. Then, the denoising and image segmentation is implemented to suppress the image noise and eliminate the affection of the background. Nine color moment features related to the contamination levels are extracted from the insulator images. Finally, an RBFNN is constructed to identify the contamination levels. The images features and ambient relative humidity are taken as the inputs of the RBFNN. For improve the precision of the detection, a new method based on the statistical probability of the values of each contamination feature component is proposed to select the initial hidden center parameters for RBFNN hidden nodes. An improved learning algorithm combined with the gradient descent algorithm and a random number control factor are proposed to modify the hidden center parameters and the weights vectors. Testing results show that the selected color moment features are effective on the contamination levels representation and the constructed RBFNN performs better than back propagation neural network (BPNN) and generalized regression neural network (GRNN) on contamination levels identification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|