| Title |
Fuzzy Model Predictive Control: Complexity Reduction for Implementation in Industrial Systems |
| Authors |
Escaño J.M. , Bordons C. , Witheephanich K. , GÓMEZ-ESTERN AGUILAR, FABIO |
| External publication |
No |
| Means |
Int. J. Fuzzy Syst. |
| Scope |
Article |
| Nature |
Científica |
| JCR Quartile |
1 |
| SJR Quartile |
2 |
| JCR Impact |
4.40600 |
| SJR Impact |
0.75800 |
| Web |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85069722057&doi=10.1007%2fs40815-019-00693-z&partnerID=40&md5=1d6e5fb8cb41c5c7e77f2a9f97e04539 |
| Publication date |
01/01/2019 |
| ISI |
000493567300002 |
| Scopus Id |
2-s2.0-85069722057 |
| DOI |
10.1007/s40815-019-00693-z |
| Abstract |
In this paper, a new fuzzy logic-based control-design technique is presented. The method aims at reducing the complexity of Takagi-Sugeno Fuzzy systems via the reduction of fuzzy rules. This reduction is obtained by finding a function basis via the Functional Principal Component Analysis, and then the model is used for Model Predictive Control (MPC). This procedure is systematic, and eventually leads to feasible low-cost microcontroller-based implementations, which has become a generic need in the era of IoT. In order to validate the results, two experimental setups have been controlled using these principles. The first of these, a mechanical pendulum, presents nonlinear dynamics that suggests the use of linear discrete models at specific operating points. In the second, a pilot plant implementing an industrial process with a chemical reactor and a heat exchanger, presents nonlinear multivariate dynamics that are successfully handled with the Fuzzy MPC Controller. © 2019, Taiwan Fuzzy Systems Association. |
| Keywords |
Controllers; Feedback control; Fuzzy inference; Fuzzy logic; Pilot plants; Predictive control systems; Principal component analysis; Complexity reduction; Functional principal component analysis; Fuzz |
| Universidad Loyola members |
|
Manage cookies