projects
Current and completed MSc projects in control systems and wind energy.
I supervise student projects at the intersection of nonlinear control, data-driven methods, learning-based control, and floating offshore wind turbines. The topics below combine a clear research question with reproducible simulation or data analysis.
Current student projects
The following topics are assigned to EU-CORE MSc students. Each project starts with a focused, achievable core study and includes optional research extensions for students who make strong progress.
Data-Driven Control of a Wind Turbine Using a Linear Model
Compare modern data-driven controllers on a realistic wind-turbine benchmark.
Students: Shabir Ahmad Niazi & Sahil Nesar
Improving Adaptive Neural-Network Integral Sliding-Mode Control for Floating Wind Turbines
Improve an existing learning-based robust controller using OpenFAST data and hybrid offline-online learning.
Students: Faten Jarrar & Aria Fatemi
From Local Linearization to Koopman Models for Wind Turbines
Compare classical local linearization with DMDc and EDMD across operating conditions.
Students: Mritunjoy MOHANTA & Adrian Willian Frasson
LiDAR-Based Wind Preview and Control of Wind Turbines
Reconstruct and assess wind preview from real LiDAR data; optionally explore feedforward control.
Students: Muhammad Sohail Ashraf & Ahmed Kazmi
Blade-Effective Wind-Speed Estimation for Wind Turbines
Extend rotor-effective wind-speed estimation to the wind experienced by individual blades.
Students: Mohd Abddullah Khan & Mohammed Al-Hadi
Completed supervised projects
These projects were completed by MSc students in the EU-CORE European Master Programme at École Centrale Nantes.
Adaptive-Gain Laws for Rotor-Effective Wind-Speed Estimation
Compared adaptive-gain sliding-mode observers for rotor-effective wind-speed estimation.
Students: Adham Ahmed & Reza Azizollahi
Data-Based Power-Coefficient Approximation for Floating Wind Turbines
Learned wind-turbine power-coefficient models from simulation data using regression techniques.
Students: Akbar Zai Jalil & Alam Sameer & Adnan Nasir Isa