Dual FOPID-neural network controller based on fast grey wolf optimizer: application to two-inputs two-outputs helicopter

Dual FOPID-neural network controller based on fast grey wolf optimizer: application to two-inputs two-outputs helicopter

This research introduces a novel dual Fast Grey Wolf Optimizer (FGWO) combined with Radial Basis Function Neural Networks (RBFNN) for a Fractional-Order PID (FOPID) controller applied to a helicopter simulator. The proposed FGWO improves the standard Grey Wolf Optimizer (GWO) by enhancing hunting du...

Full description

Saved in:
Bibliographic Details
Main Authors: Amar Rezoug, Jamshed Iqbal, Abdelkrim Nemra
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Systems Science & Control Engineering
Subjects:
Metaheuristic optimization
fractional-order PID controller
fast grey wolf optimizer
helicopter control
Online Access:https://www.tandfonline.com/doi/10.1080/21642583.2024.2449156
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This research introduces a novel dual Fast Grey Wolf Optimizer (FGWO) combined with Radial Basis Function Neural Networks (RBFNN) for a Fractional-Order PID (FOPID) controller applied to a helicopter simulator. The proposed FGWO improves the standard Grey Wolf Optimizer (GWO) by enhancing hunting during the exploitation phase and increases robustness in convergence to the minimum value. FGWO optimizes the FOPID parameters using a novel objective function. The RBFNN is integrated to address the nonlinearities and uncertainties, while a dual block mitigates the coupling effects. The performance of the proposed controller is characterized by two simulation scenarios. The first scenario involved nine benchmark functions across thirty trials. Results demonstrated that the FGWO offered superior performance in terms of robustness and proximity to the global minimum compared to the GWO. The second scenario involved applying the controllers to the helicopter. Results evidenced that the dual-FOPID-FGWO (DRF-FG) controller achieved a 4.3363% faster response and 1.8199% higher precision than the GWO-based controller (DRF-G). The DRF-FG showed robustness in trajectory tracking compared to the controllers based on the Ant Lion Optimizer (DRF-A) and the Whale Optimization Algorithm (DRF-W). DRF-FG improved the average regulation performance by 1.702% and trajectory tracking by 0.152% compared with DRF-G.
ISSN:2164-2583

Similar Items