Department of Electrical Engineering
Permanent URI for this communityhttps://repository.cuilahore.edu.pk/handle/123456789/18
Browse
3 results
Search Results
Item Estimation of Wake Effect in Wind Farms using Machine Learning Algorithms(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Muhammad Usama Riaz; SP22-REE-001; Dr. Aamer Bilal Asghar; LHR TP 9501The need for renewable energy is always growing, making wind farm efficiency opti mization a vital area of study. Wind turbines that are dispersed throughout the landscape on wind farms use the kinetic energy of the wind to generate electricity. The idea that a wind turbine running in the wake of another turbine lowers wind speed after the rotor and reduces power generation is introduced by these massive wind farms with several turbines. The flow field in the wake of first row turbines is characterized by strong wind velocity deficit and high turbulent intensity as well. For this reason, a further downstream turbine in a wind farm can capture lesser wind energy than the first row turbine. Most importantly wake effect modeling is done in this study since it is important in determining the real en ergy production of a wind farm enhanced by this feature. In this study, machine learning algorithms are used to determine the wake effect of a wind turbine in a wind farm. Although the wind turbines appear simple in their working principle, their control is actually complex and difficult to maintain operational and structural integrity and performance. Each turbine produces a ‘wake’ when it takes wind energy; this is a major factor in the overall dynamics of the turbines. These wakes, which are areas of turbulent flow and decreased wind speed behind the turbines, are a major barrier to efficient wind energy harvesting. Moreover, the extension of the mechanical life of the turbines in not only increase efficiency but also sus tain turbulence in the wake. The present research work, specifically focuses on estimating wake effects in wind farms for machine learning algorithms. The data used for this aim is archival data of wind farm recordings, but in this case, the data is computationally syn thesized. The goal is to improve accuracy and efficacy while reducing wake estimating loss compared to traditional methods. Utilizing machine learning models such as Artificial Neural Networks (ANN), Random Forest Regression, Decision Tree Regression, Support Vector Machines (SVM)andtheadaptive neuro-fuzzy inference system (ANFIS) which are used to capture complex architecture and forecast accuracy. The outcomes of this research have the potential to revolutionize wind farm optimization by providing a more adaptive and faster wake estimation process. Among the models tested, the Random Forest Model performed the best with an outstanding R2 score of 0.99, demonstrating its effectiveness in accurately estimating wake effects. In comparison, the Decision Tree Regression also showed strong performance with R2 score of 0.97, although it exhibited a slightly higher MSEandRMSEItem A Data-Driven Approach for Design and Development of Batch Process Automation System of a Plant(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Muhammad Subiyyal Fayyaz; SP20-REE-001; Dr. Aamer Bilal Asghar; LHR TP 8070Industrial automation processes make use of control systems to operate and observe machines as well as processes. Automation in industrial workplace gives advantages of enhancing quality and productivity whereas minimizing errors, improving safety, and adding flexibility to manufacturing process. The aim of this work is to implement the simulation-based data driven control automation in which I have to design, develop and automate the complete plant through Programmable Logic controllers (PLC). Keeping this in view, I have designed the redundant controller architecture by using Device Level Ring (DLR) topology; a cost-effective control solution in which the single point of failure on networking and SCADA/HMI layer will be minimized. V-Cycle process model will be followed during detail design and development phase of the project till complete simulation. Control Logix soft computing technique used for logic development. I have developed complete simulated data driven control project in which I have utilized different soft computing techniques and software’s for industrial automation including RS-Logix5000/Studio 5000 for logic development, RSLinx for communication between PLC controllers and SCADA/HMI layer are used. Factory talk View Studio will be used for graphics development. Also, I have used the soft computing techniques for reporting purpose. SQL Database management console utility have utilized for reporting DB. For simulation activity, I have used RS-Simulator. Simulated data driven automated SCADA/HMI system are ensure to meet the performance parameters i.e. increase productivity, increase efficiency, reduce variability and ensure safety. Major parameters are showed in form of Bar-Trends. Health Statuses of control hardware and communication diagnostics are very helpful for system health checks and monitoring in diagnostic HMI.Item Diagnosis of Doubly Fed Induction Generator Inter-Turn Faults (ITF) in Wind Energy Conversion System(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Anisa Sharif; SP20-REE-014; LHR TP 8686The most often utilized wind turbine generators right now are Doubly Fed Induction Generators (DFIG). When compared to other generators, it offers significant benefits such as low mechanical stress, excellent system efficiency, and a variable speed constant frequency mechanism. Mechanical and electrical faults are the two categories into which DFIG faults exist. The stator inter-turn fault is one of the stator problems that are not detectable by traditional protective devices. This study focuses on the identification of stator inter-turn short circuit (ITSC) Faults in DFIG since it accounts for more than one-third of all DFIG faults. Because the DFIG system is nonlinear, estimating its states without linearizing the system is challenging. Many approaches, including adaptive extended Kalman filtering, Wavelet Transform, Hilbert-Hang Transform, and Neural Networks can be utilized to identify stator inter turn faults and produce reasonable results. These approaches are less precise and efficient because some of these techniques linearize the DFIG nonlinear model for fault identification. The Unscented Kalman Filter (UKF) is really a derivative-free strategy for nonlinear systems that outperform linearization-based Kalman filter algorithms in fault detection approaches. Because the UKF is a nonlinear estimate approach that solves directly without linearization, it produces more accurate results than the Extended Kalman Filter (EKF). In this contribution, the UKF is implemented to detect stator inter-turn faults in the DFIG. By creating and examining the electrical currents residual from the stator, the fault is detected. The outcomes of the simulation demonstrated how well the suggested technique performs in both the diagnosis of a high and a low value of the ITSC fault in the generator stator windings. Firstly, by applying the state space model equations we created both healthy and defective DFIG-based wind turbine models in Matlab/Simulink, and then we used the UKF to identify inter-turn faults and describe the UKF estimation response. Simulation results of the UKF and EKF are compared for performance Analysis. For the implementation of the proposed scheme, the state space model of DFIG in the dq-reference framework is used and the simulations are carried out in the MATLAB/Simulink environment. Although, the trade-off between accuracy and speed of estimation response has played an important role in deciding the most effective technique.