Projects

Intelligent control of highly non-linear Autonomous Underwater Vehicles

Autonomous underwater vehicle (AUV) is a pilot-less, submarine-like robotic device, deployed for underwater tasks such as search and rescue operation, surveying, surveillance, inspection, repair and maintenance. The control of the AUV is a challenging task; this is primarily due to the difficult and unpredictable environmental conditions that exist in the sea. During operation, the AUV undergo complex multi-axis motion trajectories that are highly non-linear because the subsystems in the vehicle are ill-defined and are strongly coupled with each other [1]. Furthermore, the vehicle dynamics can change considerably with the changes in surrounding conditions and external disturbances such as wind velocity and sea current. These hydrodynamic coefficients are normally difficult to measure or predict accurately [2]-[4].

 

Fig. 2 PID tracking controller for marine ship [5]

Project1.

The aim of this project is to develop a simplified Fuzzy Logic Controller for controlling the autonomous underwater vehicle (AUV).

Project2. The aim of this project is to develop simplified Neuro-Fuzzy Controller for controlling the autonomous underwater vehicle (AUV).

Project3. The aim of this project is to optimize the performance of Fuzzy Logic Control using evolutionary algorithms such as Genetic, Simulated Annealing, Particle Swarm Optimization and Differential Evolution Algorithms.

Project4. The aim of this project is to optimize the performance of Neuro-Fuzzy controller using evolutionary algorithms such as Genetic, Simulated Annealing, Particle Swarm Optimization and Differential Evolution Algorithms.

Prerequisites: Basic knowledge of modeling and control; Programming in MATLAB.

Interested students would be expected to take the following postgraduate courses for attaining knowledge and skills related to the project. 1) Artificial Intelligence 2) Adaptive and Self-Tuning Control

 

Modeling and Control of Photovoltaic (PV) System

To ensure the optimal utilization of large arrays of PV modules, maximum power point tracker (MPPT) is employed in conjunction with the power converter (dc-dc converter and/or inverter). Due to the varying environmental condition such as temperature and solar insolation, the PV characteristics exhibit inconsistent maximum power point (MPP), posing a challenge in the tracking problem. The situation becomes more complicated when the array is subjected to partial shading (PS), i.e. when part or the whole module of a PV array receives non-uniform insolation. Under this condition, the PV curves are characterized by multiple peaks MPP- typically consisting of several local and one global peak (GP). If the GP is not properly tracked, significant power losses could result [6].

 

Project1.

The aim of this project is to model the PV systems under partial shading condition using Fuzzy Logic and Neural Network technique.

Project2.

The aim of this project is to model the PV systems using the evolutionary computation technique with a special focus on partial shaded PV system.

Project3.

The aim of this project is to develop a simple and efficient Neuro-Fuzzy maximum power point tracking (MPPT) controller for Photovoltaic System under partial shading conditions.

Project4.

The aim of this project is to develop a simple and efficient maximum power point tracking (MPPT) controller using Evolutionary Algorithms for Photovoltaic System under partial shading conditions.

Prerequisites: Basic knowledge of modeling and control; Programming in MATLAB.

Interested students would be expected to take the following postgraduate courses for attaining knowledge and skills related to the project. 1) Artificial Intelligence 2) Solar Photovoltaic System