Abstract: This paper proposed an assessing service transformer health model using data that has been collected by a real-time data acquisition and analysis device collocated with the transformer. The online data is provided to the operator in near real-time over the Internet and the operators can evaluate directly the status of the distribution transformer, then giving proper responds. The top oil temperature, vibration and transformer loading are chosen as monitored parameters. The condition of the considered service transformer is determined out using machine learning algorithms. The structure of this algorithm will be presented specifically in the paper. A case study is implemented on a stimulated service transformer to evaluate the effectiveness of the proposed model
Keywords: transformer health, machine learning, energy monitoring
[1] N. M. Rao, R. Narayanan, B. R. Vasudevamurthy, and S. K. Das, "Performance requirements of present-day distribution transformers for Smart Grid," in 2013 IEEE Innovative Smart Grid Technologies-Asia (ISGT Asia), 2013, pp. 1-6.
[2] A. E. B. Abu-Elanien, M. M. A. Salama, and M. Ibrahim, "Determination of transformer health condition using artificial neural networks," in 2011 International Symposium on Innovations in Intelligent Systems and Applications, 2011, pp. 1-5.[3] E. Aburaghiega, M. E. Farrag, and M. M. Gouda, "On-line Condition Monitoring of Power Transformer Health Status Enforced by Temperature and Electrical Signatures," in 2019 21st International Middle East Power Systems Conference (MEPCON), 2019, pp. 521-526.
[4] J. R. Agüero, "Applications of smart grid technologies on power distribution systems," in 2012 IEEE PES Innovative Smart Grid Technologies (ISGT), 2012, pp. 1-1.
[5] A. D. Ashkezari, H. Ma, T. K. Saha, and C. Ekanayake, "Application of fuzzy support vector machine for determining the health index of the insulation system of in-service power transformers," IEEE Transactions on Dielectrics and Electrical Insulation, vol. 20, pp. 965-973, 2013.
