A Flexible Ultraviolet Image Defect Diagnosis based on Multi-Param Fusion for External Insulation Equipment

In this paper, we propose a flexible ultraviolet image defect diagnosis based on multi-param fusion for external insulation equipment. Different from the traditional method relying on photon number and descriptive judgment basis, the proposed method combines a variety of algorithms to automatically extract discharge information related to external insulation equipment step by step, and obtains clear diagnosis rules through a decision tree, which can effectively eliminate the influence of noise, small spot, humidity, detection distance and other factors, and provides a reliable judgment basis for the defect diagnosis of ultraviolet image. The experimental results show the performance of our method. We use 5000 images to check the equipment part detection performance, and 2000 UV fusion images to validate our diagnosis method. The experimental results show that our method can provide a useful way to quantitative diagnosis of UV image defects for external insulation equipment.