Optical Monitoring of Pollution on MV Bushings

The proposed research aims to optically monitor the dry pollution level on transformer bushings and determine the possible leakage current should the dry polluted surface be critically wetted. The research involves the implementation of an image capturing system with appropriate image processing. A lighting array that surrounds the camera, required for one of the imaging techniques, is designed and implemented. Calibration of light position data of the array is detailed. The HV test setup used to acquire leakage current and the methods used to determine bushing pollutant conductivity are presented. The relationship between Equivalent Salt Deposit Density (ESDD) and leakage current is shown to have a logarithmic fitting, as expected from the SANS 60815 grading of pollution severity. The leakage current is characterised at various known pollution levels under wetted conditions as a reference for the neural network to correlate the predicted dry pollution level (from the images) to leakage current under wetted conditions (from test measurements). An example data-set, linking leakage current, conductivity, salinity, pollutant surface coverage and saliency, and ESDD is presented. Furthermore, the methodology relating to implementation and verification is outlined. The standard methods used to classify pollution types and severity are discussed. A brief overview of the dynamics governing bushing flashover under polluted conditions is presented. The actual pollution level and type is quantified using ESDD and Non-Soluble Deposit Density (NSDD). Image segmentation and border extraction are illustrated to output four variables related to surface pollutants: area ratio, coverage, shape factor and eccentricity. The first two parameters are proposed as measures of surface pollution density, while the latter two may assist in pollution type identification. For more accurate pollution type identification, reflectance transformation imaging (RTI) is used. With a saliency mapping resolution of approximately 100 µm, the feature recognition between salt deposits and dust deposits is more readily attained.