Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/C18B2F4B-D6E0-400C-9BE8-84A5FC9E8BAE | ||
| Year | 2020 | ||
| Type of Item | Diploma Work | ||
| License |
|
||
| Bibliographic Citation | Thomas Kyriakakis, "Programming neurofuzzy controller and its connection to intelligent mechanical systems", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2020 https://doi.org/10.26233/heallink.tuc.86071 | ||
| Appears in Collections |
The techniques presented in this paper are suitable for solving both linear and nonlinear systems and can be applied to a number of different applications, such as anti-seismic construction testing, vehicle engineering, robotics, financial applications, etc.The aim of this paper is to develop a reliable neuro fuzzy control system (ANFIS) and to link it to mechanical systems using the finite element method.To achieve this goal, two different implementations are used. The first, concerns the Matlab code (MyANFIS), which works independently of the Fuzzy Toolbox. After all, as we know, the operation of ANFIS through Matlab's obscure toolkit, which is the second implementation, is not quite configurable, but it does work in a way like a "black" box in which the user cannot intervene immediately and change various variables.To control the operation and compare these two implementations, two types of intelligent mechanical systems with piezoelectric materials were studied. A beam construction and a plate construction. The identification was done using the finite element method and the completion of the motion equations was done using the Houbolt numerical method.
Copyright © DIAS 2013
