Formalism to design a neural network: Application to an induction machine drive coupled to a non linear mechanical load

This search deals with the control of a process in order to take into accou nt non linearities without parameters identification. Neural networks prope rties are exploited for the modelling of non linear features, and a formali sm is proposed to design a neural model which can be used directly as a con troller. We apply this formalism to the modelling of a non linear mechanica l load torque feature coupled to an induction machine in order to design a speed controller. A partial and a global neural method are presented. In or der to overcome modelling errors or any process changes, an adaptive on lin e method is proposed. At last, simulation and experimental results are pres ented.