Studies on the use of neural networks in nonlinear control strategies
Reactor temperature control is very important as it affects chemical process operations and the product quality. Although PID controller, which is the linear controller and widely used in the chemical process industries, is able to control the temperature, the operating range is limited. Furthermore...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Society of Chemical Engineers, Japan
2001
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/7080/ http://www.scopus.com/inward/record.url?eid=2-s2.0-0035302511&partnerID=40&md5=8fcbfc7d7cfa9d12be0f9a7ed2b98ea1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.um.eprints.7080 |
|---|---|
| record_format |
eprints |
| spelling |
my.um.eprints.70802019-08-02T02:37:35Z http://eprints.um.edu.my/7080/ Studies on the use of neural networks in nonlinear control strategies Kuttisupakorn, P. Hussain, Mohd Azlan Petcherdask, J. TA Engineering (General). Civil engineering (General) TP Chemical technology Reactor temperature control is very important as it affects chemical process operations and the product quality. Although PID controller, which is the linear controller and widely used in the chemical process industries, is able to control the temperature, the operating range is limited. Furthermore, its control performance when plant/model mismatches exist is not guaranteed. Recently, various advanced control techniques have been succesfully applied to highly nonlinear systems. These include the Generic Model Control (GMC) and the Inverse-Model Control (IMC) techniques. However these methods still require reasonable and accurate process model and parameters, which are difficult to guarantee in many cases. For this reason we have used neural networks in conjunction with these methods to overcome this problem for the control of the reactor in this study. The neural network is used as a function estimator in the GMC method and as a model and controller in the IMC-PI method. Various simulations involving set point tracking and disturbance rejection under nominal and model-mismatch cases were performed using these hybrid methods. The results of these hybrid controllers were found to be better than the conventional PID and GMC methods in most cases. These results justify the use of the neural networks in such hybrid strategies as well as show their versatility in incorporating into the nonlinear control methods to cater for model mismatches and difficult to control process systems. Society of Chemical Engineers, Japan 2001 Article PeerReviewed Kuttisupakorn, P. and Hussain, Mohd Azlan and Petcherdask, J. (2001) Studies on the use of neural networks in nonlinear control strategies. Journal of Chemical Engineering of Japan, 34 (4). pp. 453-465. ISSN 0021-9592 http://www.scopus.com/inward/record.url?eid=2-s2.0-0035302511&partnerID=40&md5=8fcbfc7d7cfa9d12be0f9a7ed2b98ea1 Doi 10.1252/Jcej.34.453 |
| institution |
Universiti Malaya |
| building |
UM Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Malaya |
| content_source |
UM Research Repository |
| url_provider |
http://eprints.um.edu.my/ |
| topic |
TA Engineering (General). Civil engineering (General) TP Chemical technology |
| spellingShingle |
TA Engineering (General). Civil engineering (General) TP Chemical technology Kuttisupakorn, P. Hussain, Mohd Azlan Petcherdask, J. Studies on the use of neural networks in nonlinear control strategies |
| description |
Reactor temperature control is very important as it affects chemical process operations and the product quality. Although PID controller, which is the linear controller and widely used in the chemical process industries, is able to control the temperature, the operating range is limited. Furthermore, its control performance when plant/model mismatches exist is not guaranteed. Recently, various advanced control techniques have been succesfully applied to highly nonlinear systems. These include the Generic Model Control (GMC) and the Inverse-Model Control (IMC) techniques. However these methods still require reasonable and accurate process model and parameters, which are difficult to guarantee in many cases. For this reason we have used neural networks in conjunction with these methods to overcome this problem for the control of the reactor in this study. The neural network is used as a function estimator in the GMC method and as a model and controller in the IMC-PI method. Various simulations involving set point tracking and disturbance rejection under nominal and model-mismatch cases were performed using these hybrid methods. The results of these hybrid controllers were found to be better than the conventional PID and GMC methods in most cases. These results justify the use of the neural networks in such hybrid strategies as well as show their versatility in incorporating into the nonlinear control methods to cater for model mismatches and difficult to control process systems. |
| format |
Article |
| author |
Kuttisupakorn, P. Hussain, Mohd Azlan Petcherdask, J. |
| author_facet |
Kuttisupakorn, P. Hussain, Mohd Azlan Petcherdask, J. |
| author_sort |
Kuttisupakorn, P. |
| title |
Studies on the use of neural networks in nonlinear control strategies |
| title_short |
Studies on the use of neural networks in nonlinear control strategies |
| title_full |
Studies on the use of neural networks in nonlinear control strategies |
| title_fullStr |
Studies on the use of neural networks in nonlinear control strategies |
| title_full_unstemmed |
Studies on the use of neural networks in nonlinear control strategies |
| title_sort |
studies on the use of neural networks in nonlinear control strategies |
| publisher |
Society of Chemical Engineers, Japan |
| publishDate |
2001 |
| url |
http://eprints.um.edu.my/7080/ http://www.scopus.com/inward/record.url?eid=2-s2.0-0035302511&partnerID=40&md5=8fcbfc7d7cfa9d12be0f9a7ed2b98ea1 |
| _version_ |
1643687961921847296 |
| score |
13.211869 |