Transformer Mechanical Integrity Evaluation Via Unsupervised Neural Network (UNN) In Smart Grid Network

• Main Authors: Zul Hasrizal, Bohari, Mohd Hafiz, Jali, Mohamad Faizal, Baharom, Mohamad Na'im, Mohd Nasir, Nik Mohd Fariz, Mohd Nawi, Yasmin Hanum, Md Thayoob
• Format: Article
• Language: English
• Published: Institute Of Electrical And Electronics Engineers Inc. (IEEE) 2016
• Subjects: T Technology (General); TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utem.edu.my/id/eprint/17703/1/Transformer%20Mechanical%20Integrity%20Evaluation%20Via%20Unsupervised%20Neural%20Network%20%28UNN%29%20In%20Smart%20Grid%20Network.pdf; http://eprints.utem.edu.my/id/eprint/17703/; http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7482178

This paper describes the classification of mechanical integrity of transformers using unsupervised neural networks (UNN). Transformers are the integral part of electrical system or smart grid networks since the last century. Self-Organizing Maps (SOM) is one type of UNN the widely used to do assessment on any system such as biomedical engineering, load contingency analysis and etc. The application of CIGRE standard and SOM in the research are enhancing the ability to do mechanical integrity assessment on the transformers for condition monitoring. Motivation for this research is to fill in the gap of excess FRA raw data for better assessment. This research proved that the new proposed method using SOM integrated with CIGRE standard able to do mechanical examination especially on core, winding and magnetic part of the transformer compared to current OMICRON SFRAnalyzer tool that employed Chinese Standard.