Data Driven Condition Monitoring Model of Power Transformer for Diagnosing Incipient Faults in Smart City Network

Authors: Rahul Soni, Bhinal Mehta, Mihir Bhatt, Raymon Antony Raj, Bishal Silwal, Rahman Azis Prasojo, M. M. F. Darwish, Norazhar Abu Bakar, Sherif S. M. Ghoneim

Corresponding Author: Rahul Soni

Abstract

Power transformers are an indispensable part of smart city infrastructure and one of the most expensive components of this kind of infrastructure. The insulation of the transformers is formed by mineral oil and cellulose, both of which can degrade due to multiple stresses (electrical/mechanical/thermal/chemical). This paper proposes a new computational model for asset decision making, taking into account several important variables such as dissolved gas analysis (DGA), water content, furan, interfacial tension, and degree of polymerization. Contour plots and surface viewers are also used to analyze different stresses on its insulating structure. Gas ratio techniques, Duval Triangle technique, Degree of polymerization and furans based paper deterioration, moisture and IFT based insulation degradation and other dissolved gas analysis based diagnostic procedures are used and its shows the higher accuracy analysis and efficiency for incipient faults diagnosis and analysis with AI based computational intelligence.

Keywords

Classification