Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Temperature rise estimation of substation connectors using data-driven models case: thermal conveccion response

Autor
Giacometto, Francisco javier; Capelli, F.; Sala, E.; Riba, J.; Romeral, L.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
41st Annual Conference of the IEEE Industrial Electronics Society
Any de l'edició
2015
Data de presentació
2015-11-11
Llibre d'actes
Proceedings of 41th Annual Conference on IEEE Industrial Electronics Society (IECON 2015)
Pàgina inicial
003957
Pàgina final
003962
DOI
https://doi.org/10.1109/IECON.2015.7392717 Obrir en finestra nova
Repositori
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7392717&refinements%3D4228349981%26filter%3DAND%28p_IS_Number%3A7392066%29 Obrir en finestra nova
URL
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7392717 Obrir en finestra nova
Resum
A wide study regarding the suitability of data-driven modelling applied to the prediction of thermal convection responses on substation connectors is presented in this paper. The study starts with the compilation of a database with thermal profiles obtained from a finite element method simulation (FEM). Afterwards, we applied partitioning methods in order to increase the number of data sets used for modelling and later evaluate the stability of the learning algorithms. After the modeling process...
Paraules clau
Errors, Heat Convection, Industrial Electronics, Learning Algorithms, Data-driven Model, Fem Simulations, High Voltage, Normality Tests, Partitionning Methods, Thermal Convections
Grup de recerca
MCIA - Centre MCIA Innovation Electronics
PERC-UPC - Centre de Recerca d'Electrònica de Potència UPC

Participants