The paper is concerned with a design and a validation of a neurocontroller
for a pulse magnetiser for magnetising permanent magnets. The goal is to re
gister the peak time and crest current in order to pick up an optimal inter
mittent duty conditions regime for the magnetiser. This is usually done by
solving a set of coupled ordinary differential equations describing current
waveforms and the temperature rise in the magnetising winding. The neuroco
ntroller is based on a one-layer feedforward neural network which is traine
d using the Levenberg-Marquardt learning rule. We present the results produ
ced by the neurocontroller and we compare them with the numerical and measu
rement results. The neurocontroller is intended to serve later as a part of
a global optimising algorithm.