Eventos Anais de eventos
ENCIT 2022
19th Brazilian Congress of Thermal Sciences and Engineering
A feedback linearization controller using a hybrid control with wavelet and perceptron neural networks applied to a hydraulic actuator
Submission Author:
Fabio Borges , RS
Co-Authors:
Fabio Borges, Thomaz Da Silva Junior, Vitor Mauro Fiori Fiori, Letieri Ávila
Presenter: Fabio Borges
doi://10.26678/ABCM.ENCIT2022.CIT22-0301
Abstract
In this work, we use a neural network as a substitute for the traditional analytic functions employed as an inversion set in feedback linearization control algorithms applied to hydraulic actuators. Although very effective and with strong stability guarantees, feedback linearization control depends on parameters that are difficult to determine, requiring large amounts of experimental effort to be identified accurately. On the other hand, neural networks require little effort regarding parameter identification the control hardware. Here, we combine these techniques to control the positioning of a hydraulic actuator, without requiring extensive identification procedures. We compare the use of wavelet and perceptron neural networks applied in the proposed schema. Simulation results are obtained, and the effectiveness of the controller is confirmed with low position errors when compared with a classical PID controller in a piston position tracking trajectory control. Advantages and weakness of the use of both perceptron and wavelet network are outlined in the final conclusions
Keywords
hydraulic actuator control, neural network-based identification, perceptron neural network, wavelet neural network
