Analysing the 2-D surface tracking patterns by using cellular neural networks

Surface tracking is one of the major breakdown mechanisms observed on polymeric outdoor insulators. Continuous discharges on the surface of the insulator cause hot spots on certain points, which finally lead to carbonised tracking paths crossing the surface between the high voltage and earth electrodes. This paths (patterns) are greatly influenced in size and shape by the external environmental conditions. The lifetime of an insulator can be increased by cleaning up its contaminated surface before a total breakdown occurs. However in most cases we do not know exactly which of the environmental factors reduced the service life of the insulator. In this study, polyester resin based insulators are investigated and the results are evaluated using Cellular Neural Network (CNN) approaches. CNN is an analog parallel computing paradigm defined in space and characterized by locally connection between processing elements. CNN with a complex dynamic behaviour have found interesting applications in image processing and pattern recognition. Since CNN proved to be an effective way in categorising different tracking patterns, using this approach we will be able to determine the environmental conditions which. The insulators experienced throughout their service life. At the end this can help us to design our insulator specifically for a certain location, and hence increase the useful lifetime of the insulator.