ÇİĞDEM GÜNDOĞAN TÜRKER, FERİHA ERFAN KUYUMCU, NURHAN TÜRKER TOKAN

Performance of support vector regression machines on determining the magnetic characteristics of the E-core transverse flux machine

The E-core transverse flux machine (ETFM) has major advantages with its different and unique structure in conventional electrical machines. It is a combination of transverse flux and reluctance principle. In this work, support vector regression machines (SVRMs) are used to obtain the magnetic characteristic parameters of the ETFM for the first time and it is compared with its artificial neural network model. The data for the training and testing of the SVRMs are obtained from experimental measurements. It is proven that SVRMs can conveniently be used in the modeling of the magnetic behaviors of highly nonlinear ETFM with better accuracy and efficiency.

Anahtar Kelimeler:

E-core transverse flux machine, magnetic characteristics, artificial neural network, support vector regression machines

Performance of support vector regression machines on determining the magnetic characteristics of the E-core transverse flux machine

Keywords:

E-core transverse flux machine, magnetic characteristics, artificial neural network, support vector regression machines,

PDF

___

Conclusion
ETFMs have a unique structure and major advantages in electrical machines.
Determination of the very nonlinear magnetization characteristics (flux linkage and torque) of ETFMs is quite important for accurate performance prediction, modeling, and design verification.