Fabio Augusto Pires Borges

Dr. Fabio Augusto Pires Borges


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 April 2021 in Journal of the Brazilian Society of Mechanical Sciences and Engineering
Verified
Journal Article
Closed access
PDF file
FBFabio Augusto Pires Borges
Fabio Augusto Pires Borges
EPEduardo Perondi
Eduardo Perondi
MCMauro André Barbosa Cunha
Mauro André Barbosa Cunha
MSMario Roland Sobczyk
Mario Roland Sobczyk

26 October 2016
Verified
Conference Paper
Closed access
PDF file
FBFabio Augusto Pires Borges
Fabio Augusto Pires Borges
EPEduardo Perondi
Eduardo Perondi
MCMauro A. B. Cunha
Mauro A. B. Cunha
MSMario R. Sobczyk
Mario R. Sobczyk
This paper report a research investigation that proposes to replace the inversion set present in the traditional feedback linearization approach by an artificial neural network resulting in a hybrid composition approach with a neural network and an analytical term. The method is applied into a hydraulic actuator position system together with a friction compensation approach also built using neural networks. The control strategy used is based on a cascade methodology that consists of interpreting the hydraulic positioning system model as two interconnected subsystems: a mechanical subsystem driven by a hydraulic one. As experimental results have indicated a significant system behavior dependence on the oil temperature, its effects are also studied and the proposed method was improved by the inclusion of the oil temperature information as an input for the neural network functions. Experimental results show the effectiveness of the proposed controller and their advantages when compared with the traditional analytical schemes with feedback linearization approaches.

1 August 2023 in IEEE Latin America Transactions
Verified
Journal Article
Closed access
RIRafael Crespo Izquierdo
Rafael Crespo Izquierdo
FBFabio Augusto Pires Borges
Fabio Augusto Pires Borges
ACAnselmo Rafael Cukla
Anselmo Rafael Cukla
FLFlávio José Lorini
Flávio José Lorini
EPEduardo Perondi
Eduardo Perondi
This work evaluates the influence of the reference trajectory on the tracking error in a servo-positioner control system. Thus, the objective is to improve the ideal tuning of the gains of a controller applied to the tracking of the positional trajectory of a hydraulic actuator through the physical characteristics of the plant and the trajectory. The applied controller uses a cascade strategy and consists of dividing the mathematical model into two interconnected subsystems, one hydraulic and the other mechanical, applying specific control strategies to each subsystem. The proposed methodology is implemented using the Firefly Metaheuristic Algorithm (FMA). The first stage consists of generating the 5th order optimal trajectories by means of b-splines functions, in which they must minimize the acceleration along the actuator's path, considering speed and flow restrictions related to the hydraulic servo-position. The second step consists in determining the effective value of the error during the execution of the trajectory and the respective gains applied to the model. The results show that this strategy proved to be useful for obtaining adequate trajectories and gains in plants with significant non-linearities, because the trajectory error was 27% lower than the empirical adjustment method of gains compared in this study.

27 March 2023
Verified
Conference Paper
Open access
TJThomaz Pereira Da Silva Junior
Thomaz Pereira Da Silva Junior
EFEverson da Silva Flores
Everson da Silva Flores
VRVagner Santos da Rosa
Vagner Santos da Rosa
FBFabio Augusto Pires Borges
Fabio Augusto Pires Borges
This paper presents a comparison of two different types of neural networks when used in the control of a hydraulic actuator. The advantages of using hydraulic actuators are pondered when facing the nonlinearities present in their model, which difficult their control difficult. The state of the art seeks several solutions, mostly in the use of neural networks. In this way, this paper addressed a study regarding the replacement of traditional sigmoidal networks by the use of wavelet networks in the representation of friction on the walls of hydraulic cylinders and reverse valve dynamics. Different architectures are tested and trained using the quickpropagation algorithm. Finally, the efficiency of the networks is compared regarding generalization for friction and reverse dynamics of the valve, as well as their use in a cascade neural control.