![Ιδρυματικό Αποθετήριο [SANDBOX]](images/dias.logo.png "Ιδρυματικό Αποθετήριο [SANDBOX]"){kind=logo}
Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/4F2A75D0-4C35-4F0E-B1A3-80B14786D4BD | ||
| Έτος | 2019 | ||
| Τύπος | Κεφάλαιο σε Βιβλίο | ||
| Άδεια Χρήσης |
|
||
| Βιβλιογραφική Αναφορά | G.K. Tairidis and G.E. Stavroulakis, "Fuzzy and neuro-fuzzy control for smart structures," in Computational Intelligence and Optimization Methods for Control Engineering, vol. 150, Springer Optimization and Its Applications, M. Blondin, P. Pardalos, J. Sanchis Sáez, Eds., Cham, Switzerland: Springer Nature, 2019, pp. 75-103. doi: 10.1007/978-3-030-25446-9_4 https://doi.org/10.1007/978-3-030-25446-9_4 | ||
| Εμφανίζεται στις Συλλογές |
Classical control tools often encounter a number of limitations on the investigation of smart composite structures due to nonlinearities and/or other uncertainties. Especially in smart structures, which is the case here, a significant degree of uncertainty is involved due to several imperfections and/or errors of both the controller and the structure itself. For example, in structures with multiple layers, several failures may appear, such as delamination, debonding, fatigue, etc. The use of intelligent fuzzy and adaptive control which is based on neuro-fuzzy techniques can be very helpful in this direction. One may also consider using global optimization algorithms for the fine-tuning of the characteristics of the controllers to maximize their applicability, their efficiency, and their robustness. In other words, the controllers can be designed based on intuition and basic engineering principles, and then they can be subjected to optimization, e.g., to training/learning using artificial neural networks, in order to achieve certain properties.
Copyright © DIAS 2013
