Attribute extraction and sensitivity analysis for classification of polymeric insulators ultraviolet images

Summary

The ultraviolet camera inspection provides information related to the corona discharges localization, concentration and intensity, based on the correlation between the visual image and emitted photons. In this work, a computational algorithm based on digital image processing is presented. It takes as input frames extracted from the video recorded by a UV camera, during the inspection of polymeric insulators (230 kV, in this study). The methodology consists of the development of several digital image processing routines to adapt images and quantify the attributes of interest extracted. The image adaptation routines seek to segment in an image the faculae that represent discharges caused by corona effect, to integrate faculae from multiple frames in only one image, to eliminate what is considered noise and to segment the shape of the insulator into parts of interest. The attribute quantification routines are designed for faculae area, perimeter, form factor and persistence, in addition to their distances of the 230 kV polymeric insulator parts of interest. As result of the development of these routines, a computational algorithm for attribute extraction is obtained. Finally, a sensitivity analysis of the parameters used in the algorithm is made in order to delimit its conditions of use. The application of the algorithm was performed in an aged isolator, processing 64 combinations of noise limit and number of frames. In order to determine which number of frames and noise limit would be suitable, it was adopted as metric to look for the lowest gradient value of the attributes surfaces. The surfaces of area, perimeter and persistence of the faculae attributes were presented in function of the two mentioned parameters, successfully characterizing the faculae. In conclusion, the methodology for extracting attributes from the UV image faculae of insulators was successfully developed. This methodology aims to improve the classification of insulators by determining suitable number of frames and noise limits for UV videos.

Additional informations

Keywords

corona, digital image processing, ultraviolet camera, polymeric insulators, superficial discharges.