Naslov
Wide & Deep Machine Learning Model for Transformer Health Analysis

Autori
Sarajcev, Petar ; Jakus, Damir ; Nikolic, Matej

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
4th International Conference on Smart and Sustainable Technologies (SpliTech 2019) / Rodrigues, Joel J.P.C. ; Nizetic, Sandro - Split : Fakultet elektrotehnike, strojarstva i brodogradnje Sveučilišta u Splitu, 2019

Skup
4th International Conference on Smart and Sustainable Technologies (SpliTech)

Mjesto i datum
Bol, Hrvatska; Split, Hrvatska, 18.06.2019. - 21.06.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Artificial neural network ; Bayesian learning ; Health Index ; Joint learning ; Probit regression ; Transformer

Sažetak
Transformer health index (HI) is a powerful tool for quantifying the overall health of a power transformer, due to the fact that it appraises its condition based on different criteria that are related (often in complex ways) to the long-term degradation factors that cumulatively lead to its end-of-life. Several authors have proposed different approaches to the HI calculation, e.g., analytical expressions, binary logistic regression, fuzzy logic models, support vector machines, and artificial neural networks. This paper proposes using Bayesian "Wide & Deep" machine learning model for the HI calculation, where the wide model part is the Bayesian ordered robust "probit" regression, while the deep part is the Bayesian artificial neural network. Both model parts are trained simultaneously within the Bayesian setting, using the so-called "joint learning" process with a Markov-chain Monte Carlo algorithm. Model is demonstrated using the actual transformer data.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika

Napomena
IEEE Catalog Number: CFP19F09‐USB ; ISBN 978‐953‐290‐089‐71

POVEZANOST RADA