Polymer insulators tend to fail because of the climatic and environmental conditions. The failure occurs when the surface of insulator is contaminated by sea salt or cement dust which lead to partial discharge (PD). Leakage currents will increase by PD that causes deterioration of insulation. To predict the insulation failures, an adaptive neurofuzzy inference system (ANFIS) method using initial color detection processes are proposed to estimate the leakage currents based on the polymer insulator thermal images (infrared signature). In this study, the sodium chloride and kaolin are used as pollutants of the polymer insulator according to IEC 60507 standards. Then, the insulator is tested in the laboratory using AC high voltage applied at 18 kV where the temperature detection is controlled at 26° C and 70% RH (relative humidity). The percentage of colors (Red, Yellow, and Blue) from the thermal image is measured using the color detection method. Correspond to the color percentage, the ANFIS method predicts leakage currents from polymer insulators. Furthermore, this system interprets measured data from insulators that need to be categorized as Safe, Need Maintenance or Harmful. The final application of the system can be a non-contact tool to predict the polymer insulators used by technicians in the field.
Estimated leakage current based on the thermal image of the polymer insulator using the color detection method
