A Novel Method for Output Characteristics Calculation of Electromagnetic Devices using Multi-kernel RBF Neural Network

Authors

  • Feng Ding Department of Mechanical and Electronic Engineering Xi’an Technological University, Xi’an, 710021, China
  • Yunyun Gao Department of Mechanical and Electronic Engineering Xi’an Technological University, Xi’an, 710021, China
  • Jianhui Tian Department of Mechanical and Electronic Engineering Xi’an Technological University, Xi’an, 710021, China

Keywords:

Electromagnetic device, finite element, multi-kernel radial basis function, neural network, optimal design

Abstract

The action performance and reliability of electromagnetic devices is critical to the entire working system. In this paper, a new method for calculating the output characteristics of electromagnetic devices is proposed. This method uses the multi-kernel radial basis function neural network (MK-RBFNN) approximation modeling by the finite element calculation results at the key nodes. It obtains the output response of the electromagnetic device under different coil voltages and air gaps. The key of establishing a MK-RBFNN is to obtain the weight coefficients of each single-kernel radial basis function (RBF) model by using a heuristic weighting strategy. When the electromagnetic output characteristics is calculated in the optimization design of the electromagnetic device, this method solves the problem that the traditional method is difficult to balance the calculation accuracy and speed. The effectiveness of the method is verified by the calculation results of the electromagnetic torque of a typical electromagnetic relay.

Downloads

Download data is not yet available.

Author Biographies

Feng Ding, Department of Mechanical and Electronic Engineering Xi’an Technological University, Xi’an, 710021, China

Feng Ding received his M.E. degree and the Ph.D. degree in Mechanical Engineering from Xi'an Jiaotong University, China. He is a Professor of the Department of Mechanical and Electronic Engineering, Xi'an Technological University, China. His research interests include condition monitoring, intelligent diagnosis and prognostics, reliability engineering.

Yunyun Gao, Department of Mechanical and Electronic Engineering Xi’an Technological University, Xi’an, 710021, China

Yunyun Gao is a M.E. candidate in the Department of Mechanical and Electronic Engineering, Xi’an Technological University, Xi’an, China. His research interests include structural design, simulation and optimization of mechanical equipment, and numerical algorithm theory.

Jianhui Tian, Department of Mechanical and Electronic Engineering Xi’an Technological University, Xi’an, 710021, China

Jianhui Tian received his Ph.D. degree in Mechanical Design and Theory from Hunan University, China. He is an Associate Professor of the Department of Mechanical and Electronic Engineering, Xi'an Technological University, China. His research interests include engineering optimization design and simulation technology

References

A. Saha and, T. Ray, “Practical robust design optimization using evolutionary algorithms,” Journal of Mechanical Design, vol. 133, no. 10, pp. 101012.1-101012.19, Oct. 2011.

M. Amrhein and T. Krein, “Induction machine modeling approach based on 3-D magnetic equivalent circuit framework,” IEEE Trans. Magn., vol. 25, no. 2, pp. 339-347, May 2010.

L. Encica, J. Makarovic, E. A. Lomonova, and A. J. A. Vandenput, “Space mapping optimization of a cylindrical voice coil actuator,” IEEE Transactions on Industry Application, vol. 42, no. 6, pp. 1437-1444, Nov. 2006.

B. Xia, Z. Ren, and C.-S. Koh, “Utilizing kriging surrogate models for multi-objective robust optimization of electromagnetic devices,” IEEE Trans. Magn., vol. 50, no. 2, pp. 835-838, Feb. 2014.

Y. Xuerong, D. Jie, W. Yingqi, and Z. Guofu, “An approximate calculation model for electromagnetic device based on user-defined interpolating function,” Journal of Magnetics, vol. 19, no. 4, pp. 378-384, Dec. 2014.

H. A. Tayebi, M. Ghanei, K. Aghajani, and M. Zohrevandi, “Modeling of reactive orange 16 dye removal from aqueous media by mesoporous silica/crosslinked polymer hybrid using RBF, MLP and GMDH neural network models,” Journal of Molecular Structure, vol. 1178, pp. 514-523, Feb. 2019.

H. K. Ghritlahre and R. K. Prasad, “Exergetic performance prediction of solar air heater using MLP, GRNN and RBF models of artificial neural network technique,” Journal of Environmental 862 ACES JOURNAL, Vol. 35, No. 8, August 2020 Management, vol. 223, pp. 566-575, Oct. 2018.

N. Benbouza, F. Z. Louai, and N. Nait-Said, “Application of meshless Petrov Galerkin (MLPG) method in electromagnetic using radial basis functions,” 4th IET Conference on Power Electronics, Machines and Drives, May 2008.

Q. Junfei, M. Xi, and L. Wenjing, “An incremental neuronal-activity-based RBF neural network for nonlinear system modeling,” Neurocomputing, vol. 302, pp. 1-11, Aug. 2018.

J. W. Perram, “Criterion for the validity of D'Alembert's equations of motion,” Advances in Quantum Chemistry, vol. 75, pp. 103-116, 2017.

M. Stein, “Large sample properties of simulations using Latin hypercube sampling,” Technometrics, vol. 29, no. 2, pp. 143-151, 1987.

A. Capozzoli, O. Kilic, C. Curcio, and A. Liseno, “The success of GPU computing in applied electromagnetics,” ACES Journal, vol. 33, no. 2, pp. 148-151, Feb. 2018.

Z. Guofu, W. Qiya, and R. Wanbin, “An output space-mapping algorithm to optimize the dimensional parameter of electromagnetic relay,” IEEE Trans. Magn., vol. 47, no. 9, pp. 2194-2199, Sep. 2011.

R. K. Gordon and W. E. Hutchcraft, “The use of multiquadric radial basis functions in open region problems,” ACES Journal, vol. 21, no. 2, pp. 127- 134, July 2006.

R. K. Gordon and W. E. Hutchcraft, “Comparison of solution accuracy using different sets of radial basis functions,” 25th Annual Review of Progress in ACES, pp. 413-418, Mar. 2009.

Downloads

Published

2020-08-01

How to Cite

[1]
Feng Ding, Yunyun Gao, and Jianhui Tian, “A Novel Method for Output Characteristics Calculation of Electromagnetic Devices using Multi-kernel RBF Neural Network”, ACES Journal, vol. 35, no. 8, pp. 855–863, Aug. 2020.

Issue

2020: Vol 35 Iss 8

Section

Articles