Application of infrared thermography and extension recognize method to intelligent fault diagnosis of distribution panels

Distribution panels are an important piece of equipment in power systems. Maintaining a loading panel and ensuring security are not easy because the power supply cannot be interrupted in high-tech factories. Distribution panels need fully functional condition monitoring and fault diagnosis systems to prevent accidents and reduce maintenance costs. In this paper, a new scheme is proposed to design an auto-diagnosis tool for electrical distribution panels using infrared thermography to build diagnostic features using the matter-element model. The paper then presents an extension recognize method (ERM) based on extension theory to diagnose the abnormality element by using degrees of correlation between the tested pattern and the matter-element models that have been built up. Test results show that the proposed method can not only recognize the main defect element of the tested panel but also detect useful information for future trends and multi-defect analysis by the correlation indexes. This new approach merits more attention as a tool to be used in the defect recognition problems of distribution panels, especially in high-tech factories in Taiwan. © 2015 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.