Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Control modelling of coupled shell and tube heat exchangers using combined neural network and fuzzy logic
Control of the temperature of the outlet fluid in heat exchanger network is very important to maintain safety of equipment and meet the optimal process requirement. Conventional PID controllers have the limitations of meeting up with wide range of precision temperature control requirements, and then...
Saved in:
| Format: | Conference Proceeding |
|---|---|
| Published: |
2022
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
MARC
| LEADER | 00000njm a2000000a 4500 | ||
|---|---|---|---|
| 001 | oai:repository.ui.edu.ng:123456789/9564 | ||
| 042 | |a dc | ||
| 720 | |a Petinrin, M. O. |e author | ||
| 720 | |a Oke, O. S. |e author | ||
| 720 | |a Adebayo, A. S. |e author | ||
| 720 | |a Towoju, O. A. |e author | ||
| 720 | |a Ismail, O. S. |e author | ||
| 260 | |c 2022 | ||
| 520 | |a Control of the temperature of the outlet fluid in heat exchanger network is very important to maintain safety of equipment and meet the optimal process requirement. Conventional PID controllers have the limitations of meeting up with wide range of precision temperature control requirements, and then the predictive controllers have recently emerged as promising alternatives for advanced process control in heat exchanger systems and other industrial applications. This paper focuses on the control of output temperature of coupled shell and tube heat exchanger by combining fuzzy logic and Neural Network control system. To achieve effective control, transfer functions from the energy balance equations of the heat exchanger unit and other components were obtained. Simulation of the control process was carried out using Simulink interface of MATLAB. The time response analysis in comparison with variants of conventional PID controllers shows that combination of Neural Network and fuzzy logic controllers can efficiently improve the performance of the shell and tube heat exchanger system while in with 0.505% overshoot and less settling time of 12.74 s, and in parallel with the same overshoot of 0.505% and settling time of 11.37 s. The demonstration of the lower error indices of the neuro-fuzzy controlled system also indicated its better performance. | ||
| 024 | 8 | |a ui_inpro_petinrin_control_2022 | |
| 024 | 8 | |a In: Ozkaya, U. (eds.) Proceedings of the 3rd International Conference on Applied Engineering and Natural Sciences, held between 20th-23th July, at Konya, Turkey. pp. 1502-1507 | |
| 024 | 8 | |a http://ir.library.ui.edu.ng/handle/123456789/9564 | |
| 653 | |a Neural network | ||
| 653 | |a Fuzzy logic | ||
| 653 | |a PID controller | ||
| 653 | |a Feedforward | ||
| 653 | |a Heat exchanger | ||
| 245 | 0 | 0 | |a Control modelling of coupled shell and tube heat exchangers using combined neural network and fuzzy logic |