MS, Engineering Sciences (Research in Control System), GIK Institute, Pakistan
BS, Engineering Sciences (Specialization in Modeling and Simulation), GIK Institute, Pakistan
Research interests include Control System: neuro-adaptive control, Intelligent control, Data-Driven Control. Machine Learning: Lyapunov Neural Networks. Modeling and Simulation
Published: Engineering Applications of Artificial Intelligence (IF 7.5)
Muhammad Sadiq, Muhammad Shafiq, Naveed R. Butt, A recurrent Lyapunov neural network for fast tracking of unknown Single-Input Single-Output nonlinear systems, Engineering Applications of Artificial Intelligence, Volume 143, 2025
Experience:
Lecturer (Faculty of Engineering of Sciences) September 2023– Ongoing
Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi, Pakistan
Key Responsibilities:
Graduate Assistant (Faculty Development Program) September 2021– June 2023
Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi, Pakistan
Key Responsibilities:
Electronic Engineer August 2018 – September 2021
Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi, Pakistan
Key Responsibilities:
Continuing Professional Development (CPD) Program
MS Thesis
Lyapunov Neural Network-based Adaptive Inverse Control for Tracking of Unknown MIMO Nonlinear Systems
The thesis proposes a direct model-free neuro-adaptive tracking controller using a novel fast gradient-free Lyapunov stable machine learning recurrent neural network (LSMRN) algorithm applicable to invertible input-output stable dynamic systems. This controller processes the plant input and output signals data for synthesizing the adaptive tracking control effort without using the model structure and the system parameters.
The key contributions are twofold: reducing computational complexity by replacing the traditional neural network estimator (NNE) and controller (NNC) with a single recurrent neural network, and significantly improving tracking performance. The LSMRN relies solely on input/output data, eliminating the need for explicit system models and control signal estimators in the closed loop. Lyapunov stability analysis ensures closed-loop stability and error convergence. Simulations on the Lorenz Chaotic and 3D Chaotic Satellite systems demonstrate the controller’s superior tracking accuracy with reduced control effort, highlighting its robustness and efficiency compared to conventional methods.