DSpace Arşivi :: by Yazar "Aksu, Inayet Ozge" değerine göre listeleniyor

Yazar "Aksu, Inayet Ozge" seçeneğine göre listele

Listeleniyor 1 - 18 / 18

A comprehensive study on dry type transformer design with swarm-based metaheuristic optimization methods for industrial applications
(Taylor & Francis Inc, 2018) Aksu, Inayet Ozge; Demirdelen, Tugce
By the development of technology, clean, reliable, and continuous energy has increased its importance. Transformers, one of the indispensable parts of this, have a role in the production, transmission, distribution, and consumption of electrical energy. Dry type transformers are more widely applied for industrial application because of its properties such as safety, incombustible structure, and eco-friendly. However, these transformers have some drawbacks related to dimension and cost depending on it. Therefore, the researchers have begun to study for reduction of dimension. Thus, the manufacturers will be supplied lower material cost. The idea of using new optimization methods is emerged to minimize the dimension of dry type transformer design This article presents the Invasive Weed Optimization (IWO) and the Firefly Algorithm (FA) which are newly introduced in the literature applied first time in the industry. First of all, the mathematical model of the three-phase dry-type transformer is described in detail. Secondly, the transformer is re-designed with the FA and the IWO by adjusting the current density (s) and the iron section compatibility factor (C). In addition, these optimization methods are compared with the performance with Particle Swarm Optimization (PSO), one of the most preferred optimization methods in the literature, in detail. The main contribution of this article is to optimize the weight and its related to cost of dry type transformer A 100 kVA three-phase dry-type transformer is used. The obtained results showed that the optimization of the weight and cost of the transformer are efficient. This article aims at providing a broad perspective on the status of optimum design for transformer fo the researchers and the application engineers dealing with these issues.
A novel hybrid metaheuristic optimization method to estimate medium-term output power for horizontal axis wind turbine
(Sage Publications Ltd, 2019) Ekinci, Firat; Demirdelen, Tugce; Aksu, Inayet Ozge; Aygul, Kemal; Esenboga, Burak; Bilgili, Mehmet
The increasing damage caused by fossil fuels has made it a necessity for new and clean energy sources. In recent years, the use of wind energy from renewable energy sources has increased, which is a new and clean energy source. Wind energy is everywhere in nature. The wind speed changes depending on time. Thus, the wind power is unstable. In order to keep this disadvantage at a minimum level, future power estimation studies have been carried out. In these studies, different methods and algorithms are applied to estimate short and medium term in wind power. In this study, artificial neural network, particle swarm optimization and firefly algorithm (FA) as a new method are used for the first time in predicting wind power. As input data, temperature, wind speed and rotor speed the data recorded in the SCADA in wind turbines are used to predict medium-term wind speed and also wind power. Each method is compared in detail and their performances are revealed.
Identification of Disk Drive Systems using the Multifeedback-Layer Neural Network and the Particle Swarm Optimization Algorithm
(IEEE, 2013) Aksu, Inayet Ozge; Coban, Ramazan
In this study, the closed loop identification of the reader head position of a disk drive system is proposed by using the Multifeedback-Layer Neural Network. To identify the system, the connection weights of the Multifeedback-Layer Neural Network (MFLNN) are trained by the Particle Swarm Optimization (PSO) algorithm. Simulation results show the effectiveness of the proposed method.
Identification of disk drive systems using the Multifeedback-Layer Neural Network and the Particle Swarm Optimization algorithm
(2013) Aksu, Inayet Ozge; Coban, Ramazan
In this study, the closed loop identification of the reader head position of a disk drive system is proposed by using the Multifeedback-Layer Neural Network. To identify the system, the connection weights of the Multifeedback-Layer Neural Network (MFLNN) are trained by the Particle Swarm Optimization (PSO) algorithm. Simulation results show the effectiveness of the proposed method. © 2013 IEEE.
Modeling and experimental validation of dry-type transformers with multiobjective swarm intelligence-based optimization algorithms for industrial application
(Springer London Ltd, 2022) Demirdelen, Tugce; Esenboga, Burak; Aksu, Inayet Ozge; Ozdogan, Alican; Yavuzdeger, Abdurrahman; Ekinci, Firat; Tumay, Mehmet
In recent years, the optimum and efficient design of the transformer core and conductive materials is the most significant issues to overcome the high-temperature problems. The temperature increases on the transformer materials are directly related to the energy efficiency of it. The overheating of the core and coils of the transformer reduces the amount of energy to be obtained from the transformer. However, copper, core, eddy current and other losses can be minimized by obtaining an optimum design of the transformer for maximum efficiency. Thus, the transformer life and the energy efficiency to be obtained from the transformer are maximized. The temperature rise and temperature distribution of the windings can be monitored by computer technology and the transformer can be safely overloaded and the production cost can be minimized. Also, the operating life of the transformers can be further increased by specifying hot spot temperatures on the transformer coils and core. In this study, 3 kVA and 5 kVA Dyn 11 connected 380/220-V dry-type transformers are optimized by multiobjective swarm intelligence-based optimization methods. The main contribution of this study is to prevent the overheating of the transformers by reducing the losses in the transformer core and coils and to reduce the costs of the transformer. The thermal and electromagnetic analyses of the transformers are realized by ANSYS/Maxwell software program which utilizes the industry-leading ANSYS/Fluent computational fluid dynamics and finite element method solvers. Finally, the experimental analyses are realized under the loaded conditions for the transformers. The experimental results are verified with the simulation results. The optimization, modeling, thermal/electromagnetic analysis and experimental processes are carried out step by step in this study. The transformer manufacturers will realize the optimum cost, efficiency and thermal analysis before transformers are manufactured.
Neuro-Controller Design by Using the Multifeedback Layer Neural Network and the Particle Swarm Optimization
(Univ Osijek, Tech Fac, 2018) Coban, Ramazan; Aksu, Inayet Ozge
In the present study, a novel neuro-controller is suggested for hard disk drive (HDD) systems in addition to nonlinear dynamic systems using the Multifeedback-Layer Neural Network (MFLNN) proposed in recent years. In neuro-controller design problems, since the derivative based train methods such as the back-propagation and Levenberg-Marquart (LM) methods necessitate the reference values of the neural network's output or Jacobian of the dynamic system for the duration of the train, the connection weights of the MFLNN employed in the present work are updated using the Particle Swarm Optimization (PSO) algorithm that does not need such information. The PSO method is improved by some alterations to augment the performance of the standard PSO. First of all, this MFLNN-PSO controller is applied to different nonlinear dynamical systems. Afterwards, the proposed method is applied to a HDD as a real system. Simulation results demonstrate the effectiveness of the proposed controller on the control of dynamic and HDD systems.
Next-Month Prediction of Hourly Solar Irradiance based on Long Short-Term Memory Network
(2023) Aksu, Inayet Ozge
Today, in parallel with the population growth and the advancement of technology, development concerns have started to arise in terms of country administrators. Therefore, alternative solutions to classical energy sources are sought. Renewable energy sources are one of the preferred energy sources today. The popularity of renewable energy sources, including solar energy, is increasing day by day. Solar energy has the potential and accessibility to spread faster than other renewable energy sources. Since Türkiye is located in a region with a high potential in terms of solar energy, which is generally called the sun belt, it is a right decision to prefer solar energy as an energy source in our region. In this study, time series prediction using Long Short-Term Memory (LSTM) Network method is used for short-term solar irradiance estimation. In order to demonstrate the success of the results, a comparison was made with the Artificial Neural Network (ANN) method. Finally, prediction results of solar irradiance were compared with statistical tests and error analyzes were given in numerically.
Prediction of an Electromechanical System Parameters using the Particle Swarm Optimization Algorithm
(IEEE, 2016) Aksu, Inayet Ozge; Coban, Ramazan
In this study, the effect of the mechanical parts consisting of Tachometer/Gearbox, Digital Encoder, Input and Output Potentiometers, a brake disc, transmission belt, and some couplings which are directly connected to the shaft of a DC servo motor is investigated. The appropriate model of the DC servo motor can be achieved by modeling the effect of the mechanical parts correctly. The contribution of these mechanical parts is added to the mathematical model of the DC servo motor as new parameters. These parameters are estimated by using the Particle Swarm Optimization (PSO) algorithm since the convergence speed of the PSO is high. The result of the PSO algorithm is confirmed with experimental results. According to the experimental results, the obtained mathematical model including the effect of mechanical parts represents the real system more accurate.
Prediction of an electromechanical system parameters using the Particle Swarm Optimization algorithm
(Institute of Electrical and Electronics Engineers Inc., 2016) Aksu, Inayet Ozge; Coban, Ramazan
In this study, the effect of the mechanical parts consisting of Tachometer/Gearbox, Digital Encoder, Input and Output Potentiometers, a brake disc, transmission belt, and some couplings which are directly connected to the shaft of a DC servo motor is investigated. The appropriate model of the DC servo motor can be achieved by modeling the effect of the mechanical parts correctly. The contribution of these mechanical parts is added to the mathematical model of the DC servo motor as new parameters. These parameters are estimated by using the Particle Swarm Optimization (PSO) algorithm since the convergence speed of the PSO is high. The result of the PSO algorithm is confirmed with experimental results. According to the experimental results, the obtained mathematical model including the effect of mechanical parts represents the real system more accurate. © 2016 IEEE.
Second Order Sliding Mode Control of MIMO Nonlinear Coupled Tank System
(IEEE, 2018) Aksu, Inayet Ozge; Coban, Ramazan
The aim of present work is to control the coupled tank system with Multi Input Multi Output (MIMO) structure by using the Sliding Mode Control (SMC) method. The most important disadvantage of the conventional SMC is chattering problem. The purpose of the presented study is to decrease the chattering effect. Two different controllers are proposed: Firstly, conventional SMC is designed. In the second step; to decrease the chattering problem in the conventional SMC, the same system is controlled by the second order SMC (SOSMC). The designed controllers have been applied to the coupled tank system, which has an important place in the industry. At the end of the study, by comparing the experimental results, it has been observed that the chattering in the control signal is significantly decreased.
Second order sliding mode control of MIMO nonlinear coupled tank system
(Institute of Electrical and Electronics Engineers Inc., 2018) Aksu, Inayet Ozge; Coban, Ramazan
The aim of present work is to control the coupled tank system with Multi Input Multi Output (MIMO) structure by using the Sliding Mode Control (SMC) method. The most important disadvantage of the conventional SMC is chattering problem. The purpose of the presented study is to decrease the chattering effect. Two different controllers are proposed: Firstly, conventional SMC is designed. In the second step; to decrease the chattering problem in the conventional SMC, the same system is controlled by the second order SMC (SOSMC). The designed controllers have been applied to the coupled tank system, which has an important place in the industry. At the end of the study, by comparing the experimental results, it has been observed that the chattering in the control signal is significantly decreased. © 2018 IEEE.
Sliding mode PI control with backstepping approach for MIMO nonlinear cross-coupled tank systems
(Wiley, 2019) Aksu, Inayet Ozge; Coban, Ramazan
The control of tank systems in industrial applications is an important issue for monitoring the chemical processes involved in the manufacture and delivery of product. The most important reason to control the tank systems is to keep the liquid level in the tanks constant and at the desired level for a specified period of time. In this study, the sliding mode control (SMC) with a repetitive approach called backstepping that is insensitive to uncertainties in system parameters and input disturbances is proposed and experimentally applied to a quadruple, cross-coupled, uncertain, nonlinear, and multiple-input/multiple-output tank system. A proportional-integral (PI) control is used to reduce the steady-state error caused by the parameter variations and external noises. The traditional way of introducing PI usually leads to sliding surfaces. In this paper, the PI action is introduced to the control signal. The proposed backstepping sliding mode PI control (BSMPIC) is applied to such a complex tank system for the first time. The experimental results are compared with those of the SMC, sliding mode PI control, and backstepping sliding mode control to see the effect of the proposed BSMPIC on the system. As a result of the comparison, it is observed that less overshoot and tracking error, better tracking performance, and faster rise time in the transient regime is obtained by the BSMPIC.
Sliding mode PI control with backstepping approach for MIMO nonlinear cross-coupled tank systems (vol 29, pg 1854, 2019)
(Wiley, 2019) Aksu, Inayet Ozge; Coban, Ramazan
[Abstract Not Available]
Sustainable Textile Manufacturing with Revolutionizing Textile Dyeing: Deep Learning-Based, for Energy Efficiency and Environmental-Impact Reduction, Pioneering Green Practices for a Sustainable Future
(Mdpi, 2024) Yilmaz, Kubra; Aksu, Inayet Ozge; Gocken, Mustafa; Demirdelen, Tugce
The textile industry, a substantial component of the global economy, holds significant importance due to its environmental impacts. Particularly, the use of water and chemicals during dyeing processes raises concerns in the context of climate change and environmental sustainability. Hence, it is crucial from both environmental and economic standpoints for textile factories to adopt green industry standards, particularly in their dyeing operations. Adapting to the green industry aims to reduce water and energy consumption in textile dyeing processes, minimize waste, and decrease the carbon footprint. This approach has become crucial in achieving sustainability in textiles following the signing of the Paris Climate Agreement. Important elements of this transformation include the reuse of washing waters used in the dyeing process, the recycling of wastewater, and the enhancement of energy efficiency through necessary methodological and equipment changes. This study analyzes the energy, labor, production, and consumption data since 2011 for a textile factories with four branches located in the Adana Organized Industrial Zone. Among these factories, the one designated as UT1, which has the highest average energy and water consumption compared to the other three branches, is selected. In recent years, the use of artificial intelligence and machine learning technologies in predicting industrial processes has been increasingly observed. The data are analyzed using LSTM (Long Short-Term Memory) and ANN (Artificial Neural Networks) forecasting methods. Particularly, the LSTM algorithms, which provided the most accurate results, have enabled advanced forecasting of electricity consumption in dyeing processes for future years. In 2020, electricity consumption was recorded as 3,717,224 kWh and this consumption was reflected in the total energy cost as TRY 1,916,032. Electricity consumption accounts for 22.34% of total energy consumption, while the share of this energy type in the cost is 43.25%. In the light of these data, the MAPE value for energy consumption forecasts using the LSTM model was 0.45%, which shows that the model is able to forecast with high accuracy. As a result, a solar power plant was installed to optimize energy consumption, and in 2023 60% energy savings were achieved in summer and 25% in winter. The electricity consumption forecasting results have been an essential guide in planning strategic initiatives to enhance factory efficiency. Following improvement efforts aimed at reducing energy consumption and lowering the carbon footprint, significant optimizations in processes and layouts have been made at specific bottleneck points within the facility. These improvements have led to savings in labor, time, and space, and have reduced unit production costs.
The New Prediction Methodology for CO2 Emission to Ensure Energy Sustainability with the Hybrid Artificial Neural Network Approach
(Mdpi, 2022) Aksu, Inayet Ozge; Demirdelen, Tugce
Energy is one of the most fundamental elements of today's economy. It is becoming more important day by day with technological developments. In order to plan the energy policies of the countries and to prevent the climate change crisis, CO2 emissions must be under control. For this reason, the estimation of CO2 emissions has become an important factor for researchers and scientists. In this study, a new hybrid method was developed using optimization methods. The Shuffled Frog-Leaping Algorithm (SFLA) algorithm has recently become the preferred method for solving many optimization problems. SFLA, a swarm-based heuristic method, was developed in this study using the Levy flight method. Thus, the speed of reaching the optimum result of the algorithm has been improved. This method, which was developed later, was used in a hybrid structure of the Firefly Algorithm (FA). In the next step, a new Artificial Neural Network (ANN)-based estimation method is proposed using the hybrid optimization method. The method was used to estimate the amount of CO2 emissions in Turkiye. The proposed hybrid model had the RMSE error 5.1107 and the R2 0.9904 for a testing dataset, respectively. In the last stage, Turkiye's future CO2 emission estimation is examined in three different scenarios. The obtained results show that the proposed estimation method can be successfully applied in areas requiring future estimation.
The Prediction Model of Characteristics for Wind Turbines Based on Meteorological Properties Using Neural Network Swarm Intelligence
(Mdpi, 2019) Demirdelen, Tugce; Tekin, Piril; Aksu, Inayet Ozge; Ekinci, Firat
In order to produce more efficient, sustainable-clean energy, accurate prediction of wind turbine design parameters provide to work the system efficiency at the maximum level. For this purpose, this paper appears with the aim of obtaining the optimum prediction of the turbine parameter efficiently. Firstly, the motivation to achieve an accurate wind turbine design is presented with the analysis of three different models based on artificial neural networks comparatively given for maximum energy production. It is followed by the implementation of wind turbine model and hybrid models developed by using both neural network and optimization models. In this study, the ANN-FA hybrid structure model is firstly used and also ANN coefficients are trained by FA to give a new approach in literature for wind turbine parameters' estimation. The main contribution of this paper is that seven important wind turbine parameters are predicted. Aiming to fill the mentioned research gap, this paper outlines combined forecasting turbine design approaches and presents wind turbine performance in detail. Furthermore, the present study also points out the possible further research directions of combined techniques so as to help researchers in the field develop more effective wind turbine design according to geographical conditions.
TRAINING THE MULTIFEEDBACK-LAYER NEURAL NETWORK USING THE PARTICLE SWARM OPTIMIZATION ALGORITHM
(IEEE, 2013) Aksu, Inayet Ozge; Coban, Ramazan
In this study, the Multifeedback-Layer Neural Network (MFLNN) weights are trained by the Particle Swarm Optimization (PSO). This method (MFLNN-PSO) is applied to two different problems to prove accomplishment of the study. Firstly, a chaotic time series prediction problem is used to test the MFLNN-PSO. Also, the method is used for identification of a non-linear dynamic system. This study shows that the MFLNN-PSO can be used for dynamic system identification as well as controller design.
Training the multifeedback-layer neural network using the Particle Swarm Optimization algorithm
(IEEE Computer Society, 2013) Aksu, Inayet Ozge; Coban, Ramazan
In this study, the Multifeedback-Layer Neural Network (MFLNN) weights are trained by the Particle Swarm Optimization (PSO). This method (MFLNN-PSO) is applied to two different problems to prove accomplishment of the study. Firstly, a chaotic time series prediction problem is used to test the MFLNN-PSO. Also, the method is used for identification of a non-linear dynamic system. This study shows that the MFLNN-PSO can be used for dynamic system identification as well as controller design. © 2013 IEEE.

Yazar "Aksu, Inayet Ozge" seçeneğine göre listele

Sayfa Başına Sonuç

Sıralama seçenekleri