Improved neural network model for induction motor design

An improved model of the artificial neural network for analysis and design of induction motors is presented. Parameters of the machine equivalent circuit are calculated using finite element method for a given motor geometry. The training of the neural network model is based on a decoupled system between geometrical variables and circuit parameters. This method efficiently improved the training and performance of the neural network model which can be used to predict machine performance and solve design optimization problems.

[1]  Lee Soo-Young,et al.  A self-organizing neural network approach for automatic mesh generation , 1991 .

[2]  L. Chang,et al.  Induction motor design using neural network , 1995, Proceedings 1995 Canadian Conference on Electrical and Computer Engineering.

[3]  M. Nurdin,et al.  Synthesis of squirrel cage motors: a key to optimization , 1991 .

[4]  L. Chang,et al.  A neural network-based optimization approach for induction motor design , 1996, Proceedings of 1996 Canadian Conference on Electrical and Computer Engineering.

[5]  F. G. Uler,et al.  Design optimization of electromagnetic devices using artificial neural networks , 1992, 1992. Digests of Intermag. International Magnetics Conference.

[6]  T. Low,et al.  The use of finite elements and neural networks for the solution of inverse electromagnetic problems , 1992, 1992. Digests of Intermag. International Magnetics Conference.

[7]  L. H. Lim,et al.  Finite-element models for cage induction motor analysis , 1989, Conference Record of the IEEE Industry Applications Society Annual Meeting,.

[8]  Michael J. Robinson.  Finite element calculation of equivalent circuit parameters for induction motors , 1988 .

[9]  Peter P. Silvester,et al.  Finite elements for electrical engineers: Frontmatter , 1996 .

[10]  Willy Geysen,et al.  A circuit approach to finite element analysis of a double squirrel cage induction motor , 1990 .

[11]  M. Chari,et al.  Finite Element Solution of Saturable Magnetic Field Problems , 1970 .

[12]  Willy Geysen,et al.  Calculation of the No-Load and Torque Speed Characteristic of Induction Motors Using Finite Elements , 1990 .

[13]  S.R.H. Hoole,et al.  Artificial neural networks in the solution of inverse electromagnetic field problems , 1993 .

[14]  Doo-Jin Park,et al.  Optimum design of single-sided linear induction motor using the neural networks and finite element method , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).