Page 164 - IJOCTA-15-4

An International Journal of Optimization and Control: Theories & Applications
ISSN: 2146-0957 eISSN: 2146-5703
Vol.15, No.4, pp.706-727 (2025)
https://doi.org/10.36922//IJOCTA025080032

RESEARCH ARTICLE

African vultures optimization-based hybrid neural
network–proportional-integral-derivative controller for improved
robot manipulator tracking

1*
1
Bashra Kadhim Oleiwi , Mohamed Jasim Mohamed , Ahmad Taher Azar 2,3 , Saim Ahmed 2,3* ,
Ahmed Redha Mahlous 2,3 , and Walid El-Shafai 2,3,4
1
Mechatronics and Robotics Engineering Department, College of Control and Systems Engineering,
University of Technology, Baghdad, Iraq
2
College of Computer and Information Sciences, Prince Sultan University, Riyadh, Saudi Arabia
3
Automated Systems and Computing Lab (ASCL), Prince Sultan University, Riyadh, Saudi Arabia
4
Department of Electronics and Electrical Communication Engineering, Faculty of Electronic Engineering,
Menoufia University, Menouf, Monufia, Egypt
bushra.k.oleiwi@uotechnology.edu.iq, 60098@uotechnology.edu.iq, aazar@psu.edu.sa, sahmed@psu.edu.sa,
arMahlous@psu.edu.sa, eng.waled.elshafai@gmail.com

ARTICLE INFO ABSTRACT
Article History: Rigid robotic manipulators encounter several challenges in trajectory tracking
Received: February 20, 2025 control, including low accuracy and poor stability, resulting from uncertain-
1st revised: February 26, 2025 ties, external disturbances, and parameter variations. To address these is-
2nd revised: April 22, 2025 sues, this study proposes two hybrid controllers that integrate the strengths of
3rd revised: May 6, 2025 proportional-integral-derivative (PID) control with neural network (NN) meth-
4th revised: June 29, 2025 ods for a three-link rigid robotic manipulator. These hybrid structures are the
Accepted: July 2, 2025 NN–PID controller and the self-tuning NN with PID (STNN–PID) controller.
Published Online: September 4, 2025 Their performance is compared against that of a conventional PID controller.
Keywords: To optimize control performance metrics, such as the integral time square er-
3-Link rigid robotic manipulator ror (ITSE), the parameters of the proposed controllers were tuned using the
African vultures optimization African vultures optimization algorithm. MATLAB was used to evaluate the
algorithm effectiveness. Robustness tests were performed by varying the initial condi-
Neural network tions, introducing external disturbances, and modifying system parameters.
Proportional-integral-derivative The NN–PID controller achieved ITSE values of 0.28919 × 10 −4 , 0.064321,
controller and 0.001164, respectively, while the STNN–PID controller yielded values of
Self-tuning proportional-integral 3.54549×10 −4 , 3.526199, and 0.883710, respectively. Moreover, when all these
-derivative controller conditions were applied simultaneously, the NN–PID controller achieved an
Trajectory tracking ITSE of 0.073968, compared to 2.672754 for the STNN–PID controller. These
results demonstrate that the NN–PID controller outperforms the other con-
trollers across all testing conditions. These findings confirm that the NN–PID
controller is the most effective controller in terms of tracking accuracy, stabil-
ity, and robustness across all test scenarios.

1. Introduction various fields, including spray painting, auto-
mated assembly lines, the handling of hazardous
radioactive materials, fabrication, freight loading
2
The use of robotic manipulators in industrial ap- and unloading, and military operations. A robust
plications has grown significantly in recent years. 1 and efficient robotic manipulator must be capable
These manipulators primarily serve as handling of regulating both its motion and the forces ex-
and positioning tools. Their applications span erted on its environment. However, due to their
*Corresponding Authors
706