Articles & Issues

Conflict of Interest: In relation to this article, we declare that there is no conflict of interest.

This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/bync/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

All issues

비선형 공학문제에 대한 인공신경망 이론의 내삽특성에 관한 연구

A Study on Interpolating Behavior of Neural Networks for Nonlinear Engineering Problems

정상헌 이광순

Jeong SH Lee KS

HWAHAK KONGHAK, February 1993, 31(1), 54-61(8), NONE

Download PDF

Abstract

인공신경망 이론의 내삽특성을 기존의 회귀모델과 비교하기 위하여 임의로 선정한 세 가지 공학문제에 대해 수치모사를 행하였다. 이산시간대 비선형 공정의 동특성 모델을 찾는 두 가지 사례에서는 재귀최소자승법(recur-sive least-squares estimation)에 의한 회귀모델이 수렴속도나 내삽정확성 면에서 월등하게 우수한 결과를 보였다. 과열증기 PVT-diagram의 mapping 문제에서는 인공신경망을 이용한 방법으로는 수렴된 결과를 얻을 수 없었다. 비선형 공정의 모델링 문제에 관한 한 전통적인 회귀모델이 아직 더 나은 결과를 보이고 있으며, 인공신경망이 일반적인 자가학습 모델링방법으로 쓰이기에는 더 많은 개선이 필요하다.

Numerical studies have been conducted for three arbitrarily chosen engineering problems to compare the interpolating performance of the artificial neural networks with that of the existing regression models. In two example problems modeling nonlinear dynamic processes, the regression models combined with the recursive least-squares estimation showed much better performance in interpolating accuracy as well as convergence rate. In the mapping problem of a PVT-diagram of superheated steam, the neural net-works failed to converge. As far as nonlinear modeling problems are concerned, the conventional regression models still seem to work better, whereas the artificial neural networks have to be improved more before they can play as generic self-learning modelers.

Keywords

References

Bhat N, McAvoy TJ, Comput. Chem. Eng., 14(4-5), 573 (1990)
Chen F, IEEE Contr. Syst. Mag., April, 44 (1990)
Lippmann RP, IEEE ASSP Mag., April, 4 (1987)
Miller T, Sutton RS, Werbos PJ, "Neural Metworks for Control," MIT Press, Cambridge, Massachusetts (1990)
Psaltis D, Sideris A, Yamamura AA, IEEE Contr. Syst. Mag., April, 17 (1988)
Sandler SI, "Chemical and Engineering Thermodynamics," 2nd ed., John Wiley & Sons, Icn., NY, pp. 589-594 (1989)