SUPPORT VECTOR MACHINES FOR STATOR GROOVE SHAPE DETECTION IN ROTARY ELECTRIC MACHINES


Creative Commons License

Noğay H. S.

7 th INTERNATIONAL CONGRESS ON ENGINEERING AND TECHNOLOGY MANAGEMENT, 16 April 2022, pp.480-488

  • Publication Type: Conference Paper / Full Text
  • Page Numbers: pp.480-488
  • Bursa Uludag University Affiliated: Yes

Abstract

Abstract: Electrical machines are magnetic and electromechanical systems that work entirely with magnetism. Losses due to magnetism in rotating electrical machines affect the working performance. The most difficult to intervene and the most neglected magnetic leakages in rotating electrical machines are the groove leakage fields in the stator groove air gap. The stator groove shapes and the placement of the stator coil edges in the grooves are important factors that directly affect the groove leakage fluxes and thus the motor power and performance. Therefore, groove leakage should also be taken into account when deciding on the stator groove shapes while designing rotating electrical machines. In this study, a multi-classification detection study, which can be useful in deciding the groove shape by considering the groove leaks, was carried out using the support vector machines (SVM) model. As a result of the test with five-fold cross-validation, it was understood that the SVM method could contribute to the stator slot selection and design of rotary electric machines. Keywords: SVM, ML, Groove, Leakage Field