Norhaliza Abdul Wahab
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Norhaliza Abdul Wahab has a total of 93 co-authors. Here are the top co-authors by number of shared publications:
Nur Sakinah Ahmad Yasmin
Universiti Teknologi Malaysia
5 shared publications- Azavitra Zainal
Instrumentation and Control Engineering Section, Malaysia Institute of Industrial Technology, Universiti Kuala Lumpur, Persiaran Sinaran Ilmu, Bandar Seri Alam, Masai 81750, Malaysia
4 shared publications - Mashitah Che Razali
Universiti Teknologi Malaysia
4 shared publications - Mohd Fua'Ad Rahmat
Universiti Teknologi Malaysia
4 shared publications - Syahira Ibrahim
Universiti Teknologi Malaysia
4 shared publications - Fatimah Sham Ismail
Universiti Teknologi Malaysia
3 shared publications
Latest Publications
- Open Access
- 18 September 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
Reinforcement Learning-based Constant Flux Control of Membrane Filtration Process
- 18 September 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
Open AccessReinforcement Learning-based Constant Flux Control of Membrane Filtration Process
- 2 May 2026
- Published by Springer Nature
- p. 126-139
A Data-driven Analysis of Backwash Interval on Ultrafiltration Membrane Performance
- 2 May 2026
- Published by Springer Nature
- p. 126-139
A Data-driven Analysis of Backwash Interval on Ultrafiltration Membrane Performance
- Open Access
- 8 April 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 124 (1) , 106
Prescribed Performance-Adaptive Sliding-Mode Control for a Morphing Quadcopter UAV
Foldable quadcopters represent a new frontier in aerial robotics technology. The ability of a foldable quadcopter to reconfigure its geometry in flight and adapt to various flight scenarios enhances agility, maneuverability, aerodynamic efficiency, and mission versatility compared to a traditional quadcopter. However, the morphing function introduces significant variations in parameters such as center of gravity, inertia, and nonlinear dynamics, in addition to inherent underactuation, coupling dynamics, and external disturbances. Thus, the folding mechanism presents significant challenges to conventional control approaches. To solve the drawbacks of the conventional control approach, nonlinear control methods have been investigated. This article proposed the development of a prescribed performance-adaptive sliding-mode control for a foldable quadcopter UAV. It models the morphing quadcopter as a rigid body system with five morphing formations (X, Y, H, O, and T). The prescribed performance sliding mode control approach systematically addresses the time-varying parameter and aerodynamic properties impact resulting from the morphing formation. Using Lyapunov theory, a sliding mode controller is designed that ensures the error evolution remains within prescribed performance bounds, maintains closed-loop stability, and tracks the trajectory under uncertainties. The effectiveness of the proposed control algorithm is evaluated and benchmarked in structured and unstructured trajectories against conventional nonlinear sliding mode control (SMC), PID, and LQR control methods. The simulation results indicate that the prescribed performance adaptive SMC achieves better performance and improved robustness compared to benchmarked control methods. The simulation results demonstrated that the adaptive control approach is a viable and effective solution for managing the complex dynamics of foldable quadcopters UAV.
- 8 April 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 124 (1) , 106
Open AccessPrescribed Performance-Adaptive Sliding-Mode Control for a Morphing Quadcopter UAV
Foldable quadcopters represent a new frontier in aerial robotics technology. The ability of a foldable quadcopter to reconfigure its geometry in flight and adapt to various flight scenarios enhances agility, maneuverability, aerodynamic efficiency, and mission versatility compared to a traditional quadcopter. However, the morphing function introduces significant variations in parameters such as center of gravity, inertia, and nonlinear dynamics, in addition to inherent underactuation, coupling dynamics, and external disturbances. Thus, the folding mechanism presents significant challenges to conventional control approaches. To solve the drawbacks of the conventional control approach, nonlinear control methods have been investigated. This article proposed the development of a prescribed performance-adaptive sliding-mode control for a foldable quadcopter UAV. It models the morphing quadcopter as a rigid body system with five morphing formations (X, Y, H, O, and T). The prescribed performance sliding mode control approach systematically addresses the time-varying parameter and aerodynamic properties impact resulting from the morphing formation. Using Lyapunov theory, a sliding mode controller is designed that ensures the error evolution remains within prescribed performance bounds, maintains closed-loop stability, and tracks the trajectory under uncertainties. The effectiveness of the proposed control algorithm is evaluated and benchmarked in structured and unstructured trajectories against conventional nonlinear sliding mode control (SMC), PID, and LQR control methods. The simulation results indicate that the prescribed performance adaptive SMC achieves better performance and improved robustness compared to benchmarked control methods. The simulation results demonstrated that the adaptive control approach is a viable and effective solution for managing the complex dynamics of foldable quadcopters UAV.
- Open Access
- 24 June 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 87 (1) , 86
Robust Backstepping Sliding Mode Control for a Morphing Quadcopter UAV
Recently, morphing quadcopters have gained an unprecedented popularity due to their nature of flexibility, self-controlled arm management and diversified application. It has been established that in morphing quadcopter control, aerial morphing generally introduces time-varying parameters into the dynamic model, thereby increasing the complexity of the control problem, in addition to the non-linearity, coupling dynamics, and external disturbances present in the model. Thus, to address those challenges, this research aimed at developing a robust backstepping sliding mode controller (BSMC) for morphing quadcopter position and orientation control. to achieve the stated aim, mathematical model of an active morphing quadcopter (a foldable drone) was presented considering five morphing formations (X, H, T, O, and Y). Following the development of the system model, the proposed control method was designed in two stages: a high-performance sliding mode controller (HSMC) for attitude control to ensure chattering-free and fast convergence of the orientation angles and a backstepping controller for position control. The robustness and effectiveness of the proposed controller were investigated and benchmarked against a backstepping control approach. The simulation results obtained show the effectiveness of the developed controller against the backstepping approach in the presence of parameter variations and external disturbances.
- 24 June 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 87 (1) , 86
Open AccessRobust Backstepping Sliding Mode Control for a Morphing Quadcopter UAV
Recently, morphing quadcopters have gained an unprecedented popularity due to their nature of flexibility, self-controlled arm management and diversified application. It has been established that in morphing quadcopter control, aerial morphing generally introduces time-varying parameters into the dynamic model, thereby increasing the complexity of the control problem, in addition to the non-linearity, coupling dynamics, and external disturbances present in the model. Thus, to address those challenges, this research aimed at developing a robust backstepping sliding mode controller (BSMC) for morphing quadcopter position and orientation control. to achieve the stated aim, mathematical model of an active morphing quadcopter (a foldable drone) was presented considering five morphing formations (X, H, T, O, and Y). Following the development of the system model, the proposed control method was designed in two stages: a high-performance sliding mode controller (HSMC) for attitude control to ensure chattering-free and fast convergence of the orientation angles and a backstepping controller for position control. The robustness and effectiveness of the proposed controller were investigated and benchmarked against a backstepping control approach. The simulation results obtained show the effectiveness of the developed controller against the backstepping approach in the presence of parameter variations and external disturbances.
- 18 April 2025
- Published by Springer Nature
- p. 102-117
Safety Control with Conflict Resolution for Multi Robots in Flexible Manufacturing System
- 18 April 2025
- Published by Springer Nature
- p. 102-117
Safety Control with Conflict Resolution for Multi Robots in Flexible Manufacturing System
- 23 August 2024
- Published by Springer Nature
- p. 191-201
Deep Learning for Ultrafiltration Membrane Prediction in Drinking Water Treatment
- 23 August 2024
- Published by Springer Nature
- p. 191-201
Deep Learning for Ultrafiltration Membrane Prediction in Drinking Water Treatment
- Open Access
- 26 March 2024
- Published by IWA Publishing in Water Science & Technology
- Vol. 89 (7) , 1701-1724
Optimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniques
Hyperparameter tuning is an important process to maximize the performance of any neural network model. This present study proposed the factorial design of experiment for screening and response surface methodology to optimize the hyperparameter of two artificial neural network algorithms. Feed-forward neural network (FFNN) and radial basis function neural network (RBFNN) are applied to predict the permeate flux of palm oil mill effluent. Permeate pump and transmembrane pressure of the submerge membrane bioreactor system are the input variables. Six hyperparameters of the FFNN model including four numerical factors (neuron numbers, learning rate, momentum, and epoch numbers) and two categorical factors (training and activation function) are used in hyperparameter optimization. RBFNN includes two numerical factors such as a number of neurons and spreads. The conventional method (one-variable-at-a-time) is compared in terms of optimization processing time and the accuracy of the model. The result indicates that the optimal hyperparameters obtained by the proposed approach produce good accuracy with a smaller generalization error. The simulation results show an improvement of more than 65% of training performance, with less repetition and processing time. This proposed methodology can be utilized for any type of neural network application to find the optimum levels of different parameters.
- 26 March 2024
- Published by IWA Publishing in Water Science & Technology
- Vol. 89 (7) , 1701-1724
Open AccessOptimizing neural network algorithms for submerged membrane bioreactor: A comparative study of OVAT and RSM hyperparameter optimization techniques
Hyperparameter tuning is an important process to maximize the performance of any neural network model. This present study proposed the factorial design of experiment for screening and response surface methodology to optimize the hyperparameter of two artificial neural network algorithms. Feed-forward neural network (FFNN) and radial basis function neural network (RBFNN) are applied to predict the permeate flux of palm oil mill effluent. Permeate pump and transmembrane pressure of the submerge membrane bioreactor system are the input variables. Six hyperparameters of the FFNN model including four numerical factors (neuron numbers, learning rate, momentum, and epoch numbers) and two categorical factors (training and activation function) are used in hyperparameter optimization. RBFNN includes two numerical factors such as a number of neurons and spreads. The conventional method (one-variable-at-a-time) is compared in terms of optimization processing time and the accuracy of the model. The result indicates that the optimal hyperparameters obtained by the proposed approach produce good accuracy with a smaller generalization error. The simulation results show an improvement of more than 65% of training performance, with less repetition and processing time. This proposed methodology can be utilized for any type of neural network application to find the optimum levels of different parameters.
- Open Access
- 23 November 2023
- Published by Akademia Baru Publishing in Journal of Advanced Research in Applied Sciences and Engineering Technology
- Vol. 34 (1) , 228-237
Crafting a Real-World Problem Project-Based Learning Based on Gantry Crane System
This paper presents the design and implementation of project-based learning for the System Modeling and Analysis course using a real-world gantry crane system problem in the first control engineering course for electrical engineering students. This project-based approach covers several topics including modeling, simulation, control and analysis. Several activities were conducted as part of the implementation of this project-based learning to achieve the intended learning outcomes of the course and the students’ expectancies values such as attainment, intrinsic, and utility values. Both individual and group assessments were performed to evaluate the abilities and knowledge, as well as to observe and provide feedback on the development of the required skills. The impact of this project-based learning implementation is evaluated by analyzing students’ feedback comments and suggestions. The findings indicate that students’ can develop their ability to solve a practical problem systematically as well as enhance their understanding and motivation towards learning. Hence, this indicates that all expectancy values considered are achieved.
- 23 November 2023
- Published by Akademia Baru Publishing in Journal of Advanced Research in Applied Sciences and Engineering Technology
- Vol. 34 (1) , 228-237
Open AccessCrafting a Real-World Problem Project-Based Learning Based on Gantry Crane System
This paper presents the design and implementation of project-based learning for the System Modeling and Analysis course using a real-world gantry crane system problem in the first control engineering course for electrical engineering students. This project-based approach covers several topics including modeling, simulation, control and analysis. Several activities were conducted as part of the implementation of this project-based learning to achieve the intended learning outcomes of the course and the students’ expectancies values such as attainment, intrinsic, and utility values. Both individual and group assessments were performed to evaluate the abilities and knowledge, as well as to observe and provide feedback on the development of the required skills. The impact of this project-based learning implementation is evaluated by analyzing students’ feedback comments and suggestions. The findings indicate that students’ can develop their ability to solve a practical problem systematically as well as enhance their understanding and motivation towards learning. Hence, this indicates that all expectancy values considered are achieved.
- 13 October 2023
- Published by Springer Nature
- p. 254-264
NARXNN Modeling of Ultrafiltration Process for Drinking Water Treatment
- 13 October 2023
- Published by Springer Nature
- p. 254-264
NARXNN Modeling of Ultrafiltration Process for Drinking Water Treatment
- 13 October 2023
- Published by Springer Nature
- p. 1-12
Identification of First Order Plus Dead Time for a pH Neutralization Process Using Open Loop Test
- 13 October 2023
- Published by Springer Nature
- p. 1-12
Identification of First Order Plus Dead Time for a pH Neutralization Process Using Open Loop Test