NEURAL NETWORK WITH DYNAMIC PROGRAMMING FOR TIME-OPTIMAL CONTROL OF CONICAL TANK LEVEL

N.S. Bhuvaneswari,∗ G. Uma,∗∗ and T.R. Rangaswamy∗

Keywords

Nonlinear process, conical tank, conventional control, neural net work with dynamic programming, timeoptimal control

Abstract

The objective of this paper is to investigate and find a solution by designing the intelligent controller for controlling conical tank level using neural network with dynamic programming (DP). A mathematical step-by-step procedure known as DP method is used to obtain the optimal valve position path in the level control problem and is trained by neural network, based on the back-propagation algorithm. The DP procedure allows the set point to be reached as fast as possible without overshoot. A prototype of conical tank level system has been built and implementation of DP-based neural network control algorithm is performed. Finally the performance is compared with conventional control.

Important Links:



Go Back