Title:On Modeling the Dynamic Thermal Behavior of Electrical Machines using Genetic Programming and Artificial Neural NetworksAuthor(s):Ciprian Zavoianu, Martin Kitzberger, Gerd Bramerdorfer, Susanne Saminger-PlatzAbstract:We describe initial attempts to model the dynamic thermal behavior of electrical machines by evaluating the ability of linear and non-linear (regression) modeling techniques to replicate the performance of simulations carried out using a lumped parameter thermal network (LPTN) and two different test scenarios. Our focus falls on creating highly accurate simple models that are well-suited for the real-time computational demands of an envisioned symbiotic interaction paradigm. Preliminary results are quite encouraging and highlight the very positive impact of integrating synthetic features based on exponential moving averages.Booktitle:17th International Conference on Computer Aided Systems Theory, Las Palmas de Gran Canaria, SpainPage Reference:page 319-326, 8 page(s)Publishing:2/2019