Yazar "Guney, Ezgi" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    A Comparative Velocity Control Study of Permanent Magnet Tubular Linear DC Motor by Using PID and Fuzzy-PID Controllers
    (Ieee, 2017) Guney, Ezgi; Demir, Memnun
    This paper presents, PID and Fuzzy-PID (FPID) controller to control frequency of Permanent Magnet Tubular Linear Direct Current Motor (PMTLDCM). In the study firstly, is released by motor frequency can be controlled using PID and FPID controller. There are 27 fuzzy rules for FPID of each parameter of PID controller. FPID controller has two inputs as error and change of error and has output signal. After all, the control program is loaded to LPC1768FBD100 ARM microcontroller, the rotor frequency regulation system PID controller and FPID controller is applied and experimental results have been transferred to PC by MATLAB. Consequently, PID and FPID control based simulation and experimental results examine and the simulation demonstrate that the FPID controller has a better behavior of the PMTLDCM motor, an excellent frequency tracking with minimum overshoot and minimum steady state error and give better performance compared to conventional PID controller.
  • [ X ]
    Öğe
    An Eco-Friendly Gas Insulated Transformer Design
    (Mdpi, 2021) Guney, Ezgi; Ozgonenel, Okan
    Electricity companies around the world are constantly seeking ways to provide electricity more safely and efficiently while reducing the negative impact on the environment. Mineral oils have been the most popular transformer insulation, having excellent electrical insulating properties, but have many problems such as high flammability, significant cleaning problems, and are toxic to fish and wildlife. This paper presents an alternative approach to mineral oil: a transformer design that is clean and provides better performance and environmental benefits. A 50 kVA, 34.5/0.4 kV gas insulated distribution transformer was designed and evaluated using the COMSOL Multiphysics environment. R410A was used as insulation material. R410A is a near-azeotropic mixture of difluoromethane (CH2F2, called R-32) and pentafluoro ethane (C2HF5, called R-125), which is used as a refrigerant in air conditioning applications. It has excellent properties including environmentally friendly, no-ozone depletion, low greenhouse effect, non-explosive and non-flammable, First, the breakdown voltage of the selected gas was determined. The electrostatic and thermal properties of the R410A gas insulated transformer were investigated in the COMSOL environment. The simulation results for the performance of oil and SF6 gas insulated transformers using the same model were compared. The gas-insulated transformer is believed to have equivalent performance and is an environmentally friendly alternative to current oil-based transformers.
  • [ X ]
    Öğe
    Artificial Neural Network Based Real Time Speed Control of a Linear Tubular Permanent Magnet Direct Current Motor
    (Ieee, 2017) Guney, Ezgi; Dursun, Mahir; Demir, Memnun
    This paper presents a real-time speed control for a linear tubular permanent magnet direct current motor (LTPMDCM) by using artificial neural network (ANN). Firstly, a novel form of LTPMDCM prototype has been developed for linear motions. Then, a low cost motor drive has designed for expected rapid response and precise position control. Software developed in MATLAB environment is used for speed control. Through this software, real-time speed control of the motor with ANN has been performed. The effectiveness of the proposed control system is verified by experimental results and presented.
  • [ X ]
    Öğe
    Time-Aware Machine Learning for Biomass Power Output Estimation Using SCADA Data
    (Springer Heidelberg, 2026) Guney, Ezgi; Demir, Memnun
    Accurate short-term estimation of electrical power output in biomass power plants remains challenging due to the nonlinear and dynamically coupled nature of thermochemical conversion processes, fuel heterogeneity, and pronounced thermal inertia. Conventional physics-based models, while effective for steady-state analysis, often fail to capture the high-frequency dynamics required for real-time monitoring and decision-support applications. This study proposes a data-driven framework for short-term power output estimation using high-resolution Supervisory Control and Data Acquisition (SCADA) data collected from an operational industrial biomass power plant. A large-scale SCADA dataset comprising several hundred thousand time-stamped records is used to model the relationship between seven key thermodynamic and operational variables and net electrical power output. Multi-layer perceptron (MLP), random forest (RF), gradient boosting regressor (GBR), and support vector regression (SVR) are evaluated under two distinct validation strategies: (i) a conventional random train-test split and (ii) a temporally blocked cross-validation scheme preserving causal order. Under random sampling, RF attains the highest apparent accuracy (R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{2}$$\end{document} = 0.9687), whereas MLP exhibits lower performance (R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{2}$$\end{document} = 0.8492), highlighting sensitivity to instantaneous regression assumptions. When temporal continuity is enforced, predictive performance improves consistently across all models. In the blocked validation stage, GBR and RF achieve R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{2}$$\end{document} values of 0.9983 and 0.9973, respectively, while MLP demonstrates a substantial performance increase (R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{2}$$\end{document} = 0.9865). Time-domain analysis further reveals that ensemble-based models provide smoother tracking of short-term fluctuations, whereas temporally aligned evaluation significantly improves the physical consistency of neural network predictions. These results demonstrate that temporally consistent validation is essential for reliable SCADA-based modeling of biomass power generation and provide a practical foundation for real-time monitoring and decision-support applications in industrial biomass power plants.