This paper deals with the development a neural controller (a control s
ystem using a neural network) and its application for the temperature
control of an experimental semi-batch pilot-plant reactor equipped wit
h a monofluid heating-cooling system. The neural controller design met
hodology is based on the process inverse dynamics modelling : the lear
ning data base is generated in an open-loop structure and the learning
of the neural network is carried out by considering the future proces
s outputs as the reference set-point. The first results presented deal
with an ideal simulated system modelled by a first order system. They
demonstrate the importance to take the time-delay of the plant into a
ccount. The second part is concerned with the real time application of
such a technique to the temperature control of a semi-batch pilot-pla
nt reactor and shows the real capability of the neural networks in pro
cess control.