Yazar "Luy, Murat" seçeneğine göre listele
Listeleniyor 1 - 15 / 15
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Backpropagation Neural Network Applications for a Welding Process Control Problem(Springer-Verlag Berlin, 2012) Aktepe, Adnan; Ersoz, Suleyman; Luy, MuratThe aim of this study is to develop predictive Artificial Neural Network (ANN) models for welding process control of a strategic product (155 mm. artillery ammunition) in armed forces' inventories. The critical process about the production of product is the welding process. In this process, a rotating band is welded to the body of ammunition. This is a multi-input, multi-output process. In order to tackle problems in the welding process 2 different ANN models have been developed in this study. Model 1 is a Backpropagation Neural Network (BPNN) application used for classification of defective and defect-free products. Model 2 is a reverse BPNN application used for predicting input parameters given output values. In addition, with the help of models developed mean values of best values of some input parameters are found for a defect-free weld operation.Öğe Control of Pitch Angle of Wind Turbine by Fuzzy Pid Controller(Taylor & Francis Inc, 2016) Civelek, Zafer; Luy, Murat; Cam, Ertugrul; Barisci, NecaattinThis article presents a study on set of PID parameters of blade pitch angle controller of wind turbine with fuzzy logic algorithm. Three individual control methods were used to control the wind turbine pitch angle. These control methods are conventional PI, fuzzy and fuzzy PID. With the use of these control methods, the system was protected from possible harms in high wind speed region and maintained changing of nominal output power. It was aimed to the control the wind turbine blade pitch angle in different wind speeds and to hold the output power stable in the set point by simulation of controllers with Matlab/Simulink Software. By evaluating the steady state time of output power received from the simulation results and steady state errors, the performances of the control systems have been measured and compared with one another. As a result of these simulation comparisons, it is clear that fuzzy PID controller performed better than PI and Fuzzy Controller.Öğe The Effect of Crack Geometry on the Nondestructive Fault Detection in a Composite Beam(Int Inst Acoustics & Vibration, 2016) Orhan, Sadettin; Luy, Murat; Dirikolu, M. Husnu; Zorlu, Gazi MustafaDefects in structures may be inherited from materials and manufacturing or they develop during service. Defects may cause catastrophic failure, which is why their detection and classification are important issues. Many aspects of defects have already been dealt with, but with wider applications of non-destructive testing methods to composite materials. However, the effect of arbitrary and random defect geometry on the applicability of these methods has been overlooked. In order to investigate this issue, this study carries out a free vibration analysis of a specially orthotropic cracked cantilever beam that was manufactured by Pultrusion. A new crack model, unlike the widely known V-shaped crack, is introduced and the effect of crack depth on the natural frequency is investigated, both experimentally and numerically. The results obtained from both the new- and the V-shaped models are compared with each other, and it is revealed that the results are not sensitive to the geometry change.Öğe Individual pitch control on wind turbines with permanent magnet synchronous generator for reduction of mechanical load and stability of output power(Pamukkale Univ, 2017) Luy, Murat; Civelek, Zafer; Cam, ErtugrulIn this article, increasing output power quality of wind turbines and decreasing mechanical loads on turbines was studied. By adjusting the blade pitch angle on nominal wind speed, output power of wind turbine kept on nominal value. Beside, by individual pitch angle control, mechanic al loads on wind turbine vas decreased, Wind turbine in which permanent magnet synchronous generator is used, modeled in matlah/simulink. Simulation results show that by individual pitch angle control both output power quality of wind turbine assured and balanced periodical loads on wind turbine reduced,Öğe Initial Results of Testing a Multilayer Laser Scanner in a Collision Avoidance System for Light Rail Vehicles(Mdpi, 2018) Luy, Murat; Cam, Ertugrul; Ulamis, Faruk; Uzun, Ibrahim; Akin, Salih IbrahimThis paper presents an application to detect and track obstacles using a multilayer laser scanner. The goal of the detection system is to develop collision avoidance for the Light Rail Vehicle (LRV). The laser scanner, which is mounted in front of the tram, collects information in a four-scan plane. The object recognition and tracking module, which is composed of a three sub-modules segmentation, classification, and Kalman Filter tracking, was carried out on the raw data. Thus, data were provided for collision avoidance module. The proposed system was applied to a tram named "Silkworm" which is manufactured by Durmazlar Machine Inc. (Bursa, Turkey) and initial experimental tests have been conducted at the facilities of Durmazlar Machine Inc. in the city of Bursa, Turkey. This study aims to illustrate parts of the possible tests that can be carried out and to share with the scientific community an important application of multilayer laser scanners, although in the initial implementation phase, in urban rail transportation.Öğe Investigation of the effect of hectoliter and thousand grain weight on variety identification in wheat using deep learning method(Pergamon-Elsevier Science Ltd, 2023) Luy, Murat; Turk, Fuat; Argun, Mustafa Samil; Polat, TurgayAccurate identification of wheat varieties in the seed and flour industry is extremely important. The success rate of correctly identifying wheat varieties using artificial intelligence methods compared to traditional methods is quite high. Whether hectoliter weight (HLW) and thousand grain weight (TGW) represent the variety in iden-tification studies is a subject to debate. The reason of this debate is these parameters are heavily affected by environmental factors such as soil nutrient levels, amount of rainfall, and number of sunny days. In other words, it is assumed that these parameters are not specific to the variety. In this study, the feature map obtained using the GLCM method was compared with the feature map obtained by adding the HLW and TGW parameters. As a result of the comparison, the accuracy rate was calculated as 78% in the first feature map. However, when standard features were added to the HLW and TGW parameters, the accuracy rate was calculated as 82%. The results show that the HLW and TGW parameters contribute to the identification of the wheat variety when used correctly with artificial intelligence.Öğe Kidney and Renal Tumor Segmentation Using a Hybrid V-Net-Based Model(MDPI, 2020) Turk, Fuat; Luy, Murat; Barisci, NecaattinKidney tumors represent a type of cancer that people of advanced age are more likely to develop. For this reason, it is important to exercise caution and provide diagnostic tests in the later stages of life. Medical imaging and deep learning methods are becoming increasingly attractive in this sense. Developing deep learning models to help physicians identify tumors with successful segmentation is of great importance. However, not many successful systems exist for soft tissue organs, such as the kidneys and the prostate, of which segmentation is relatively difficult. In such cases where segmentation is difficult, V-Net-based models are mostly used. This paper proposes a new hybrid model using the superior features of existing V-Net models. The model represents a more successful system with improvements in the encoder and decoder phases not previously applied. We believe that this new hybrid V-Net model could help the majority of physicians, particularly those focused on kidney and kidney tumor segmentation. The proposed model showed better performance in segmentation than existing imaging models and can be easily integrated into all systems due to its flexible structure and applicability. The hybrid V-Net model exhibited average Dice coefficients of 97.7% and 86.5% for kidney and tumor segmentation, respectively, and, therefore, could be used as a reliable method for soft tissue organ segmentation.Öğe Kidney Tumor Segmentation Using Two-Stage Bottleneck Block Architecture(Tech Science Press, 2022) Turk, Fuat; Luy, Murat; Barisci, Necaattin; Yalcinkaya, FikretCases of kidney cancer have shown a rapid increase in recent years. Advanced technology has allowed bettering the existing treatment methods. Research on the subject is still continuing. Medical segmentation is also of increasing importance. In particular, deep learning-based studies are of great importance for accurate segmentation. Tumor detection is a relatively difficult procedure for soft tissue organs such as kidneys and the prostate. Kidney tumors, specifically, are a type of cancer with a higher incidence in older people. As age progresses, the importance of having diagnostic tests increases. In some cases, patients with kidney tumors may not show any serious symptoms until the last stage. Therefore, early diagnosis of the tumor is important. This study aimed to develop support systems that could help physicians in the segmentation of kidney tumors. In the study, improvements were made on the encoder and decoder phases of the V-Net model. With the double-stage bottleneck block structure, the architecture was transformed into a unique one, which achieved an 86.9% kidney tumor Dice similarity coefficient. The results show that the model gives applicable and accurate results for kidney tumor segmentation.Öğe Mobile Device Supported Online Examination System Appropriate To Distance Learning(Int Organization Center Acad Research, 2016) Bursalioglu, Ozgun; Luy, Murat; Ates, Volkan; Erguzen, AtillaIn modern life information technology has entered into almost every area of people's daily lives and become an important and undeniable part of business, educational and personal life. Thus, technological innovations that became widespread in political, economic, institutional and cultural fields are also being widespread in the educational field. Until recently the existing technical shortcomings, the problems of real-time operation of systems, the difficulty and expensiveness of providing the necessary system were making it almost impossible to apply these technological innovations to education and examination systems. At the present day, studying in various schools and courses in order to fulfill the needs of life, improve ourselves and our lives is essential for us. Eventually exams are administered in various ways to measure people's level of education, practical and theoretical knowledge and abilities. In traditional education system, trainers and learners should adapt to each other in terms of time and venue and they have to fit in the same place at the same time. This particularly leaves learners in the lurch in their personal life and force them education priority scheduling. Despite this situation, it makes impossible to receive training for working people and people with disabilities and also makes it difficult for learners to develop themselves. Web-based learning and online examination systems are able to deliver the required web content to user on all devices with web browsers such as desktop computers, tablet computers and even some televisions. Because of high sales and maintenance fees, deficiency of existing properties on fulfilling the needs of the institution, inability of adding new features of commercial systems make it disadvantageous to use them. In the open source systems, obligation for institution to pay to developer company for eliminating the problems that may occur in using process, insufficiency of technical documentation and difficulties on developing a software for these reasons, these systems are also not preferred. The goal of our work is to develop an institution-specific, user-friendly web-based online examination system that minimizes operating costs, allows institution to add new features easily by expert teams, meets the needs of the institution, integrates the current learning management system. We have developed our application in accordance with the requirements of the Distance Learning Center of Kirikkale University using the contemporary software (Asp. NET MVC5, Angular JS, Bootstrap, Microsoft SQL Server 2014) techniques.Öğe A new fuzzy logic proportional controller approach applied to individual pitch angle for wind turbine load mitigation(Pergamon-Elsevier Science Ltd, 2017) Civelek, Zafer; Luy, Murat; Cam, Ertugrul; Mamur, HayatiIn the world, efforts to increase the resource diversity in electric generation have accelerated lately. So, the great improvements have been achieved in wind turbines (WTs). The dimensions of WTs have grown for more electric generation and their energy productions have increased. Depending on these developments, it has become more important to reduce the WT load mitigation. Thus, a tendency to pass an individual pitch angle system control rather than a collective pitch angle system control employed to stable the output power of WTs over nominal wind speeds has whetted in recent studies. However, in literature, a controller proposal relating to how to incorporate the blade moments used for providing the individual pitch angle system into the output power control system has not yet been offered. Therefore, in this study, a new fuzzy logic proportional control (FL-P-C) approach has been recommended to mitigate the moment load on blades and tower to a minimum possible value while keeping the output power of WTs at a constant value. The offered FL-P-C has also been verified by MATLAB/Simulink. Through the first application of the FL-P-C on a WT, a significant improvement of 33-83% has been managed for the blade and tower moment loads. Furthermore, the grid fluctuations have been reduced because of the stabilisation of the output power of the WT. Ultimately, by the offered FL-P-C, not only the WT load mitigations and maintenance costs of WTs could be reduced, but also electric costs could be decreased owing to increasing lifetimes of WTs. (C) 2017 Elsevier Ltd. All rights reserved.Öğe Optimization of indoor thermal comfort values with fuzzy logic and genetic algorithm(Ios Press, 2023) Balci, Sonay Gorgulu; Ersoz, Suleyman; Luy, Murat; Turker, Ahmet Kursad; Barisci, NecaattinIt is known that in crowded environments such as educational institutions and workplaces, keeping indoor air quality and climate within certain limits contributes to success and production. For this purpose, a system has been developed to ensure air quality well-being in working environments. In our study, the Arduino processor managed by the fuzzy logic control system (FLC) starts to work with the trigger of the motion sensor HC-SR501. The inputs of the FLC system are defined as LM-35 sensor for temperature, DHT-11 for humidity, MQ-135 for air quality, MQ-9 sensor for CO and explosive gas. The designed system evaluates the instantaneous data obtained from the fuzzy logic system rule base and decides which of the output air filter, heater and alarm systems will operate at what speed. In order to increase system efficiency, fuzzy logic input membership values are optimized by genetic algorithm.Öğe Prediction of coronary angiography requirement of patients with Fuzzy Logic and Learning Vector Quantization(Ieee, 2013) Akbulut, Harun; Barisci, Necaattin; Arinc, Huseyin; Topal, Taner; Luy, MuratIn this study, prediction of coronary angiography (CA) requirement of patients is presented using Fuzzy Logic (FL) and Learning Vector Quantization (LVQ). Data sets of patients are received from 200 patients, half of whom undergo CA, the other half doesn't undergo CA, the numbers of both men and women patients are selected equal. Input data sets and output data sets are determined and tested for FL. The correct classification rate of FL is measured 86% for prediction of CA requirement of patients. Training data sets and testing data sets are determined and tested for LVQ. The correct classification rate of LVQ is measured 88% for prediction of CA requirement of patients. These results show that LVQ is more effective than FL at prediction of CA requirement of patients.Öğe Proportional-integral-derivative parameter optimisation of blade pitch controller in wind turbines by a new intelligent genetic algorithm(Inst Engineering Technology-Iet, 2016) Civelek, Zafer; Cam, Ertugrul; Luy, Murat; Mamur, HayatiOutput powers of wind turbines (WTs) with variable blade pitch over nominal wind speeds are controlled by means of blade pitch adjustment. While tuning the blade pitch, conventional proportional-integral-derivative (PID) controllers and some intelligent genetic algorithms (IGAs) are widely used in hot systems. Since IGAs are community-based optimisation methods, they have an ability to look for multi-point solutions. However, the PID parameter setting optimisation of the IGA controllers is important and quite difficult a step in WTs. To solve this problem, while the optimisation is carried out by regulating mutation rates in some IGA controllers, the optimisation is conducted by altering crossover point numbers in others. In this study, a new IGA algorithm approach has been suggested for the PID parameter setting optimisation of the blade pitch controller. The algorithm rearranging both the mutation rate and the crossover point number together according to the algorithm progress has been firstly used. The new IGA approach has also been tested and validated by using MATLAB/Simulink software. Then, its superiority has been proved by comparing the other genetic algorithm (GAs). Consequently, the new IGA approach has more successfully adjusted the blade pitch of a WT running at higher wind speeds than other GA methods.Öğe Welding Process Optimization With Artificial Neural Network Applications(Acad Sciences Czech Republic, Inst Computer Science, 2014) Aktepe, Adnan; Ersoz, Suleyman; Luy, MuratCorrect detection of input and output parameters of a welding process is significant for successful development of an automated welding operation. In welding process literature, we observe that output parameters are predicted according to given input parameters. As a new approach to previous efforts, this paper presents a new modeling approach on prediction and classification of welding parameters. 3 different models are developed on a critical welding process based on Artificial Neural Networks (ANNs) which are (0 Output parameter prediction, (ii) Input parameter prediction (reverse application of output prediction model) and (iii) Classification of products. In this study, firstly we use Pareto Analysis for determining uncontrollable input parameters of the welding process based on expert views. With the help of these analysis, 9 uncontrollable parameters are determined among 22 potential parameters. Then, the welding process of ammunition is modeled as a multi-input multi-output process with 9 input and 3 output parameters. 1st model predicts the values of output parameters according to given input values. 2nd model predicts the values of correct input parameter combination for a defect-free weld operation and 3rd model is used to classify the products whether defected or defect-free. 3rd model is also used for validation of results obtained by 1st and 2nd models. A high level of performance is attained by all the methods tested in this study. In addition, the product is a strategic ammunition in the armed forces inventory which is manufactured in a limited number of countries in the world. Before application of this study, the welding process of the product could not be carried out in a systematic way. The process was conducted by trial-and-error approach by changing input parameter values at each operation. This caused a lot of costs. With the help of this study, best parameter combination is found, tested, validated with ANNs and operation costs are minimized by 30%.Öğe Wind speed estimation for missing wind data with three different backpropagation algorithms(Sila Science, 2012) Luy, Murat; Saray, UmutIn this study, wind data acquired from Tokat province located in the Central Black Sea section of the Black Sea region of Turkey were used to estimate wind speed by using artificial neural networks (ANN). A 3-layer feedback network was designed for wind speed modeling with MATLAB Neural Network Toolbox. Data used were acquired from State Meteorological station taken from a height of 10 meters. By using daily average wind speed data of Tokat province in 2010, ANN feedback network algorithms were used in order to recover any missing wind speed data. ANN feedback model Levenberg - Marquardt (LM) learning algorithm, the gradient - Descent (GD) learning algorithm and Resilient (RPROP) learning algorithm were used for randomly selected three data for each month and root mean square error (RMSE) and mean square error (MSE) values were calculated.
