The Application of Control using Neuro-dynamic Programming with a Feature Map
| Authors: | Yang Dae Ryook, Korea University, Korea, Republic of
Kim Dong Kyu, Korea University, Korea, Republic of
Ahn Joeng Ho, Sungkyunkwan University, Korea, Republic of
Lee Kwang Soon, Sogang University, Korea, Republic of |
|---|
| Topic: | 2.3 Non-Linear Control Systems |
|---|
| Session: | Nonlinear Controller Design |
|---|
| Keywords: | pH neutralization process, the Neuro-Dynamic Programming (NDP), k-nearest neighbor method (kNN), Neural network (NN), Feature map |
|---|
Abstract
For the general nonlinear processes control problem, the most rigorous approach is to use dynamic optimization. However, as the size of the problem grows, the Dynamic Programming approach is suffered from the burden of calculation which is called as 'Curse of Dimensionality'. To overcome this problem, a cost-approximator can be used to obtain the optimal control input policy minimizing the value of cost, called the Neuro-Dynamic Programming (NDP) algorithm. In this study, the NDP algorithm was applied to pH neutralization process in both simulations and experiments. A systematic approach of NDP to a pH neutralization process has been proposed and the performance of the NDP approach has been evaluated through the comparison with PI control. Also, a few related issues such as selection of approximator and feature map of the states are investigated. Copyright © 2005 IFAC
