Minimum Permeance Estimation of Variable Reluctance Machines by Using Neural Networks

Erkan Mese

doi:10.3390/mca1020087

Abstract

A new approach was studied in this paper to calculate minimum permeance (Pmin) of variable reluctance machines (VRM). Finite element method (FEM) and neural network (NN) were employed together for estimation. The data collected by an electromagnetic finite element software (Flux 2D) were used to train NN. Trained NN was tested by another data set which are not in the training data set. Total estimation error in the test set was observed less than 2.5%. A similar study was performed with the data set collected using flux tube analysis (FTA). In this case, much larger data set was constructed by FTA since this method allows to generate larger data set. After training NN by this data set, it was tested by a test set generated by FTA. The total estimation error was observed less than 5%.

Highlights

The variable-reluctance machine (VRM) is a concentrated windings of simple doubly salient synchronous machine used as form, but the salient poles of the rotor carry aerospace motors, generators in wind energy no windings of any kind
Since FTA is an analytical way to calculate Pmin, data set generation using this method is very easy and allows us to generate much larger data set than finite element method (FEM) does
Larger data set was generated by using flux tube analysis

Summary

I.Introduction

The variable-reluctance machine (VRM) is a concentrated windings of simple doubly salient synchronous machine used as form, but the salient poles of the rotor carry aerospace motors, generators in wind energy no windings of any kind. : finite element method (FEM) and flux tube the rotor poles bb' would move into analysis (FTA). Accuracy in the calculation, finite element method (FEM) is the most commonly used numerical analysis technique. 35 Pmin data were generated by using Flux-2D for different kl and k2 values ranging between (1.05-2.05) and (0.1251.0), respectively. The Pmin=f{er, 0s, RI, Rs, Lrph, ro, rsbi) relation was used to produce this data set It was generated at the same time with the data set Type II. Since FTA is an analytical way to calculate Pmin, data set generation using this method is very easy and allows us to generate much larger data set than FEM does. By using the backpropagation algorithm for different type of configurations and data set, the following trainings were performed.

Training and Testing for data set Type I

Training and Testing for data set TypeID

Training and Testing for data set Type II

Findings

6.Conclusions