Division of Information Technology, Engineering and the Environment
School of Electrical and Information Engineering
School of Electrical and Information Engineering
Magnetic Hysteresis Models Using Knowledge Based Techniques 1996-
The project initiated under a previous research development grant has led to
development of a novel technique to describe magnetisation process by means
of artificial neural networks (NN).
A multi-layer feed-forward NN architecture was used with the back
propagation algorithm and single layer of hidden processing units with
nonlinear sigmoid processing function.
A custom made C++ program was written to train NN by configuring with
suitable weights and to generate resulting mapping of magnetisation
variables.
The accuracy of approximation was good once a near optimum NN. The
configuration was found by adjusting number of hidden processing units and
number of iteration steps.
One PhD was accomplished, further PhD and MEng projects are being
accomplished.
The Project was supported by Research Development Grant, University of South
Australia, 1996-98.
