Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651
Browse
59 results
Search Results
Article Machine Learning-Based Efficiency Prediction of Francis Type Hydraulic Turbines Through Comprehensive Performance Testing(Sage Publications Ltd, 2025) Besni, Ferdi; Buyuksolak, Fevzi; Ayli, Ece; Celebioglu, Kutay; Aradag, Selin; Tascioglu, YigitIn this study, the rehabilitation works carried out for the KEPEZ HPP, which has been in operation for over 50 years in Antalya, Turkey, is discussed. Within this scope, the existing turbine components are optimized using the CFD method, and a design that provides higher performance at the required flow rate and head is obtained. Analyses are performed using numerical methods to examine the behavior of the new turbine at different flow rates and heads, and a hill chart is created. In the second stage, model tests are carried out at the TOBB ETU HYDRO Water Turbine Design and Test Center in accordance with IEC60193 standards. Different ML methods are examined for their ability to predict turbine performance, following the development of the hydrid CFD-Experimental methodology. According to the authors knowledge, there is no study in the literature that combines experimental, numerical, and ML methods for turbines, and ML methods have not been applied before for Francis-type turbine performance prediction. The outcomes of the study contribute to the advancement of turbine design and optimization processes, offering valuable insights for the successful implementation of rehabilitation projects in the hydropower sector.Article Citation - WoS: 1Citation - Scopus: 1Performance Analysis of Dielectric Application Methods in Electrical Discharge Machining(Sage Publications Ltd, 2025) Cogun, Can; Tosun, NihatA lack of comprehensive research exists on the machining performance of the reciprocating electrode method (REM) compared to other dielectric application methods (DAMs), particularly the commonly used side flushing method (SFM) in electric discharge machining. This study aims to investigate the performance outputs of the two methods under varying machining parameters through experimental and statistical analysis to fill the gap in the field. The impact of each machining parameter and DAM on the critical performance outputs was also determined using the analysis of variance (ANOVA). The study employed signal-to-noise ratio analysis to ascertain the optimal machining parameter settings. It has been demonstrated that the REM has several advantages over the SFM, including a 2-25% reduction in average surface roughness, a 5-70% decrease in electrode wear rate, a smoother workpiece surface, and sharper edges. However, the SFM exhibits a higher workpiece removal rate and less relative wear (RW) than the REM. The ANOVA revealed that the primary factor influencing the RW was the pulse time, followed by the discharge current and the DAM. Similarly, the discharge current was the primary factor affecting the average roughness and mean spacing between successive profile peaks, followed by the pulse time.Article Citation - WoS: 1Citation - Scopus: 3Improving the Performance of a Mems-Imu System Based on a False State-Space Model by Using a Fading Factor Adaptive Kalman Filter(Sage Publications Ltd, 2024) Akbas, Eren Mehmet; Cifdaloz, Oguzhan; Ucuncu, MuratIn this study, we introduce a novel algorithm, the low error rate adaptive fading Kalman filter (LERAFKF), designed to predict system states in the presence of uncertainty in both the system matrix and the model. The purpose of developing the LERAFKF is to address challenges arising from measurement difficulties, system parameter uncertainties, and state-space model inaccuracies. Several studies have utilized the Kalman filter (KF) and extended Kalman filter (EKF) algorithms to handle uncertainties in system parameters, corrupted measurements with unknown covariances, and incorrectly defined system modeling. Our work distinguishes itself by proposing a new approach that achieves lower error and deviation rates by combining the current Kalman estimation algorithm and the fading factor adaptive filter. To achieve this goal, we transformed the KF into an adaptive KF by introducing a forgetting factor, and the algorithm was subsequently reconfigured to calculate an optimized forgetting factor. In this study, we conducted simulations and measurements using both linear and nonlinear systems. The linear system represents the motion of an object, and the simulation involved measurements from the inertial navigation system (INS) sensor, specifically the Pololu IMU01b three-axis inertial measurement unit (IMU) sensor. We employed the SDI33 system with 9 degrees of freedom (DoF) mounted on a three-axis rotary table for the nonlinear system. This system simulates a missile as a 4th-order nonlinear system. Our findings demonstrate that the proposed LERAFKF filter outperforms KF and EKF in estimating system states, particularly in measurement-related error scenarios. Mean square error analysis further confirmed that LERAFKF exhibited the lowest error values, showcasing superior performance over KF and EKF in linear and nonlinear systems.Article Citation - WoS: 4Citation - Scopus: 3On Generalized Asymmetric Harmonic Oscillator With Quadratic Nonlinearity Within Fractional Variational Principles(Sage Publications Ltd, 2024) Baleanu, Dumitru; Jajarmi, Amin; Defterli, Ozlem; Mohammad, Noorhan F. AlShaikh; Asad, Jihad; AlShaikh Mohammad, Noorhan FThis work studies the nonlinear fractional dynamics of asymmetric harmonic oscillators. The classical description of the physical system is generalized using the principles of fractional variational analysis. As a system of two-coupled fractional differential equations with a quadratic nonlinear component, the fractional Euler-Lagrange equations of the motion of the corresponding system are obtained. The Adams-Bashforth predictor-corrector numerical approach is used to approximate the system's outcomes, which are then simulated comparatively with respect to various model parameter values, including mass, linear and quadratic nonlinear stiffness, and the order of the fractional derivative. The simulations provided the possibility of investigating various dynamical behaviours within the same physical model that is generalized by the use of fractional operators.Article Enhancing Efficiency of an Old Hydropower Plant Turbine Through a Mutual Runner Design and Component Optimization(Sage Publications Ltd, 2025) Seydim, Sila; Yildirim, Gozde; Ulucak, Oguzhan; Buyuksolak, Fevzi; Ejder, Beril; Kantar, Ece Nil; Celebioglu, KutayThis paper presents a systematic approach to the rehabilitation process of Sar & imath;yar HEPP, a hydroelectric power plant that has been operational for more than 50 years. Units 1 and 2 (U1-U2) were originally designed with a head of 93 m and a turbine power of 48.5 MW, while Units 3 and 4 (U3-U4) were designed with a lower head of 76.5 m but the same turbine power of 48.5 MW. A methodology combining reverse engineering and CFD analysis is developed to identify and evaluate the critical parameters that have an impact on the existing turbine performance. A hybrid design is proposed to replace the existing two different types of turbines, which reduces manufacturing costs and design time. The performance of the new hybrid design is evaluated in detail with CFD analysis. For both existing and hybrid design, steady and unsteady analyses are performed. For all of the situations hill charts are obtained and the comparison of the old and new hybrid design is discussed in detail. The results show that the new design has improved the efficiency of the turbine and the power plant, resulting in a 14.2% efficiency increase in U1-U2 and a 21% system efficiency improvement in U3-U4. This study provides a guide to designers and practitioners for the rehabilitation of hydroelectric power plants.Article Prediction of Noise Generated by Rod-Airfoil Configuration: an Investigation Based on Experiments and Machine Learning(Sage Publications Ltd, 2024) Kocak, Eyup; Ayli, EceThis study investigated the effects of various parameters on the SPL (Sound Pressure Level) levels of rod-airfoil configurations. An experimental study was performed to investigate the effects of the rod parameters, such as the configuration of the rod, the distance between the rod and the airfoil, the diameter effect of the rod, and the geometry of the rod, on the performance of the rod-airfoil configuration. An Artificial Neural Network (ANN) model was then developed and applied to accurately predict the SPL of rod-airfoil configurations. The results of the study revealed that the Levenberg-Marquardt (LM) algorithm with 2 hidden neurons produced the best performance in predicting the SPL level, with a training R-squared value of 0.9998 and a testing R-squared value of 0.998715. The findings also indicated that increasing rod diameter increases sound pressure level while reducing gap width increases SPL levels and decreases frequency values. This method offers a more precise and effective technique to forecast the SPL levels of rod-airfoil designs, allowing designers to enhance their creations and lower noise levels. The findings of this study can also be utilized to direct future research in this area and offer important information for a better understanding of the mechanism of rod-airfoil noise creation. To the best of the authors' knowledge, this is the first study to look into rod-airfoil design predictions made using machine learning approaches.Article Citation - WoS: 2Citation - Scopus: 1Exploring the Potential of Artificial Intelligence Tools in Enhancing the Performance of an Inline Pipe Turbine(Sage Publications Ltd, 2024) Celebioglu, Kutay; Ayli, Ece; Cetinturk, Huseyin; Tascioglu, Yigit; Aradag, SelinIn this study, investigations were conducted using computational fluid dynamics (CFD) to assess the applicability of a Francis-type water turbine within a pipe. The objective of the study is to determine the feasibility of implementing a turbine within a pipe and enhance its performance values within the operating range. The turbine within the pipe occupies significantly less space in hydroelectric power plants since a spiral casing is not used to distribute the flow to stationary vanes. Consequently, production and assembly costs can be reduced. Hence, there is a broad scope for application, particularly in small and medium-scale hydroelectric power plants. According to the results, the efficiency value increases on average by approximately 1.5% compared to conventional design, and it operates with higher efficiencies over a wider flow rate range. In the second part of the study, machine learning was employed for the efficiency prediction of an inline-type turbine. An appropriate Artificial Neural Network (ANN) architecture was initially obtained, with the Bayesian Regularization training algorithm proving to be the best approach for this type of problem. When the suitable ANN architecture was utilized, the prediction was found to be in good agreement with CFD, with an root mean squared error value of 0.194. An R2 value of 0.99631 was achieved with the appropriate ANN architecture.Article Citation - WoS: 10Citation - Scopus: 11Analysis of Heat Transfer Enhancement of Passive Methods in Tubes With Machine Learning(Sage Publications Ltd, 2024) Ayli, Ece; Turkoglu, Hasmet; Yapici, Ekin Ozgirgin; Özgirgin Yapıcı, EkinThis study investigates the efficacy of machine learning techniques and correlation methods for predicting heat transfer performance in a dimpled tube under varying flow conditions, including the presence of nanoparticles. A comprehensive numerical analysis involving 120 cases was conducted to obtain Nusselt numbers and friction factors, considering different dimple depths and velocities for both pure water and water-Al2O3 nanofluid at 1%, 2%, and 3% volume concentrations. Utilizing the data acquired from the numerical simulations, a correlation equation, SVM ANN architectures were developed. The predictive capabilities of the statistical approach, ANN, and SVM models for Nusselt number distribution and friction factor were meticulously assessed through mean average percentage error (MAPE) and correlation coefficients (R2). The research findings reveal that machine learning techniques offer a highly effective approach for accurately predicting heat transfer performance in a dimpled tube, with results closely aligned with Computational Fluid Dynamics (CFD) simulations. Particularly noteworthy is the superior performance of the ANN model, demonstrating the most precise predictions with an error rate of 2.54% and an impressive R2 value of 0.9978 for Nusselt number prediction. In comparison, the regression model achieved an average error rate of 6.14% with an R2 value of 0.8623, and the SVM model yielded an RMSE value of 2.984% with an R2 value of 0.9154 for Nusselt number prediction. These outcomes underscore the ANN model's ability to effectively capture complex patterns within the data, resulting in highly accurate predictions. In conclusion, this research showcases the promising potential of machine learning techniques in accurately forecasting heat transfer performance in dimpled tubes. The developed ANN model exhibits notable superiority in predicting Nusselt numbers, making it a valuable tool for enhancing thermal system analyses and engineering design optimization.Article Citation - WoS: 7Citation - Scopus: 8On the New Hadamard Fractional Optimal Control Problems(Sage Publications Ltd, 2023) Tajani, Asmae; Jajarmi, Amin; Baleanu, Dumitru; Zguaid, KhalidThe main goal of this manuscript is to investigate a fractional optimal control problem subject to a dynamical system involving Hadamard fractional derivatives. Necessary conditions for the optimality of the considered problem are derived in terms of the corresponding Euler-Lagrange equations. An iterative method is also proposed to numerically solve the obtained equations from the necessary optimality conditions. Two illustrative examples are considered and simulated in order to show the applicability and efficiency of the proposed method. Numerical simulations show that the used method presents some satisfying results regarding the absolute error values.Article Citation - WoS: 4Citation - Scopus: 4Window Length Insensitive Real-Time Emg Hand Gesture Classification Using Entropy Calculated From Globally Parsed Histograms(Sage Publications Ltd, 2023) Alguner, Ayber Eray; Ergezer, HalitElectromyography (EMG) signal classification is vital to diagnose musculoskeletal abnormalities and control devices by motion intention detection. Machine learning assists both areas by classifying conditions or motion intentions. This paper proposes a novel window length insensitive EMG classification method utilizing the Entropy feature. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. Additionally, the entropy feature can classify feature vectors of different sliding window lengths without including them in the training data. Many kinds of entropy feature succeeded in electroencephalography (EEG) and electrocardiography (ECG) classification research. However, to the best of our knowledge, the Entropy Feature proposed by Shannon stays untested for EMG classification to this day. All the machine learning models are tested on datasets NinaPro DB5 and the newly collected SingleMyo. As an initial analysis to test the entropy feature, classic Machine Learning (ML) models are trained on the NinaPro DB5 dataset. This stage showed that except for the K Nearest Neighbor (kNN) with high inference time, Support Vector Machines (SVM) gave the best validation accuracy. Later, SVM models trained with feature vectors created by 1 s (200 samples) sliding windows are tested on feature vectors created by 250 ms (50 samples) to 1500 ms (300 samples) sliding windows. This experiment resulted in slight accuracy differences through changing window length, indicating that the Entropy feature is insensitive to this parameter. Lastly, Locally Parsed Histogram (LPH), typical in standard entropy functions, makes learning hard for ML methods. Globally Parsed Histogram (GPH) was proposed, and classification accuracy increased from 60.35% to 89.06% while window length insensitivity is preserved. This study shows that Shannon's entropy is a compelling feature with low window length sensitivity for EMG hand gesture classification. The effect of the GPH approach against an easy-to-make mistake LPH is shown. A real-time classification algorithm for the entropy features is tested on the newly created SingleMyo dataset.