Adaptive and optimal control of a non-linear process using intelligent controllers

A time-optimal control for set point changes and an adaptive control for process parameter variations using neural network for a non-linear conical tank level process are proposed in this work. Time-optimal level control was formulated using dynamic programming algorithm and basic properties of the solutions were analysed. It was found that the control is of bang–bang type and there is only one switching. In this method, a mathematical step-by-step procedure is used to obtain the optimal valve position path with one switching and is trained by neural network, based on the back-propagation algorithm. The dynamic programming procedure allows the set point to be reached as fast as possible without overshoot. An adaptive system is also designed and proved to be useful in adjusting the trained parameter of the dynamic programming based neural network for the process parameter variations. A prototype of conical tank level system has been built and implementation of dynamic programming based neural network control algorithm for set point changes and implementation of adaptive control for process parameter variations are performed. Finally, the performance is compared with conventional control. The results prove the effectiveness of the proposed optimal and adaptive control schemes.