Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Robotics and Control Systems
Cortes, Hugo Rodrıguez
Unknown Affiliation
Control & Systems Engineering Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Altitude Controller Based on Artificial Neural Network Genetic Algorithm for a Quadcopter MAV Ibarra, José Ramón Meza; Ulloa, Joaquın Martınez; Pacheco, Luis Alfonso Moreno; Cortes, Hugo Rodrıguez
International Journal of Robotics and Control Systems Vol 4, No 4 (2024)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v4i4.1582

Abstract

Mechanical systems with high dynamic complexity often face challenges due to unmodeled uncertainties and external perturbations, making effective control difficult. Therefore, new advanced, robust, intelligent control theories have been developed through the sudden advance of computational power in recent years. In this research work, these new theories of automatic control are used, mainly based on what is currently called Artificial Intelligence (AI) algorithms, to develop a novel altitude controller based on the theory of Genetic Algorithms (GA) and Artificial Neural Networks (ANN).Theperformance of the designed controller is evaluated by employing the numerical simulation model in MATLAB SIMULINK, which was created for the commercial MAV Mambo Parrot. The developed intelligent ANN-GA controller uses the Levenberg-Marquardt optimization method and a Genetic Algorithm (GA) to improve Artificial Neural Network performance. The initial PID gains are obtained according to the GA, generating optimal values that initialize the neural network and contribute to optimal performance of the ANN training through evaluation of (Mean Square Error) MSE and (Integral Time Absolute Error) ITAE; the ANN takes then, the adequate output and signals as data from input to calculate the required combination of gains as output for MAV altitude controller. Simulation results demonstrate that the self-tunable controller improves the settling time, decreasing by 31.6% compared to the original PID controller. The certainty of the implemented controller opens new routes for automatic control strategies based on artificial intelligence algorithms for the complex nonlinear dynamics of unmanned aircraft.
Co-Authors Ibarra, José Ramón Meza Pacheco, Luis Alfonso Moreno Ulloa, Joaquın Martınez