Online Adaptive Control of Non-linear Plants Using Neural Networks with Application to Temperature Control System

Although the neural inverse model controllers have demonstrated high potential in the non-conventional branch of non-linear control, their sensitivity to parameter variations and/or parameter uncertainties usually discourage their applications in industry. Indeed, when the controlled system is subject to parameter variations or uncertainties, unsatisfactory tracking performances are obtained. To overcome this problem, a neural inverse model is added to the control scheme and an online update of the weights is provided. Simulations have been carried out to show the robustness of this control algorithm. Moreover, this adaptive neural inverse model controller is implemented on a temperature control system. Good tracking performances are obtained for different set points regulation. The large parameter variations and disturbances have no effect on the tracking performance since they have been compensated online.