A Gain-Scheduling PI Control Based on Neural Networks
This paper presents a gain-scheduling design technique that relies upon neural models to approximate plant behaviour. The controller design is based on generic model control (GMC) formalisms and linearization of the neural model of the process. As a result, a PI controller action is obtained, where...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2017/9241254 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832550954219601920 |
|---|---|
| author | Stefania Tronci Roberto Baratti |
| author_facet | Stefania Tronci Roberto Baratti |
| author_sort | Stefania Tronci |
| collection | DOAJ |
| description | This paper presents a gain-scheduling design technique that relies upon neural models to approximate plant behaviour. The controller design is based on generic model control (GMC) formalisms and linearization of the neural model of the process. As a result, a PI controller action is obtained, where the gain depends on the state of the system and is adapted instantaneously on-line. The algorithm is tested on a nonisothermal continuous stirred tank reactor (CSTR), considering both single-input single-output (SISO) and multi-input multi-output (MIMO) control problems. Simulation results show that the proposed controller provides satisfactory performance during set-point changes and disturbance rejection. |
| format | Article |
| id | doaj-art-1601c13f27114c09a5c2ade074ed7266 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2017-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-1601c13f27114c09a5c2ade074ed72662025-02-03T06:05:19ZengWileyComplexity1076-27871099-05262017-01-01201710.1155/2017/92412549241254A Gain-Scheduling PI Control Based on Neural NetworksStefania Tronci0Roberto Baratti1Dipartimento di Ingegneria Meccanica, Chimica e dei Materiali, Università degli Studi di Cagliari, Via Marengo 2, 09123 Cagliari, ItalyDipartimento di Ingegneria Meccanica, Chimica e dei Materiali, Università degli Studi di Cagliari, Via Marengo 2, 09123 Cagliari, ItalyThis paper presents a gain-scheduling design technique that relies upon neural models to approximate plant behaviour. The controller design is based on generic model control (GMC) formalisms and linearization of the neural model of the process. As a result, a PI controller action is obtained, where the gain depends on the state of the system and is adapted instantaneously on-line. The algorithm is tested on a nonisothermal continuous stirred tank reactor (CSTR), considering both single-input single-output (SISO) and multi-input multi-output (MIMO) control problems. Simulation results show that the proposed controller provides satisfactory performance during set-point changes and disturbance rejection.http://dx.doi.org/10.1155/2017/9241254 |
| spellingShingle | Stefania Tronci Roberto Baratti A Gain-Scheduling PI Control Based on Neural Networks Complexity |
| title | A Gain-Scheduling PI Control Based on Neural Networks |
| title_full | A Gain-Scheduling PI Control Based on Neural Networks |
| title_fullStr | A Gain-Scheduling PI Control Based on Neural Networks |
| title_full_unstemmed | A Gain-Scheduling PI Control Based on Neural Networks |
| title_short | A Gain-Scheduling PI Control Based on Neural Networks |
| title_sort | gain scheduling pi control based on neural networks |
| url | http://dx.doi.org/10.1155/2017/9241254 |
| work_keys_str_mv | AT stefaniatronci againschedulingpicontrolbasedonneuralnetworks AT robertobaratti againschedulingpicontrolbasedonneuralnetworks AT stefaniatronci gainschedulingpicontrolbasedonneuralnetworks AT robertobaratti gainschedulingpicontrolbasedonneuralnetworks |