Browsing by Author "Atan, Ozkan"

Now showing 1 - 14 of 14

Classification of Distributed Bearing Faults Using a Novel Sensory Board and Deep Learning Networks With Hybrid Inputs
(Ieee-inst Electrical Electronics Engineers inc, 2024) Rajabioun, Ramin; Afshar, Mojtaba; Atan, Ozkan; Mete, Mutlu; Akin, Bilal
Distributed bearing faults are the most common ones in industry and create random vibration patterns, which make their detection difficult. They are caused by lubrication issues, contamination issues, electrical erosion, bearing roughness, or the spread of a local fault. This research mainly focuses on the distrusted bearing faults diagnosis using a multi-sensory kit. For this purpose, a novel deep-learning framework is proposed to detect these faults using 3 axis vibrations and one stray magnetic flux signal. The data is collected at 50 operating points, i.e., 10 speed and 5 torque levels. The proposed architecture benefits from a multi-input pipeline consisting of time-frame signals and extracted features. A feature-rich architecture is proposed combining convolutional and high-level information. Although a deep learning structure coherently learns from the features through convolutional and LSTM layers, 20 predefined features sampled from each instance are also fed into the network to improve accuracy. The robustness of the overall system is validated with train/test split data. Deep learning results are compared with two more classification algorithms, SVM and XGBoost. The high accuracy of the proposed model demonstrates the superiority of the deep learning architecture for distributed bearing fault detection.
Effects of Variable-Order Passive Circuit Element in Chua Circuit
(Springer Birkhauser, 2020) Atan, Ozkan
In this paper, the behaviour of a variable-order passive circuit element which is used in Chua chaotic circuit is analysed. Firstly, the behaviour of a circuit with a variable-order memristor is presented. In the generalized Ohm's law for a memory element, the order of a passive circuit element is defined as a kind of the element, so the circuit shows unusual behaviour. Finally, the chaotic circuit is designed with a variable-order memristor, and the effect of the variable-order element is shown in the Chua circuit. The chaotic circuit model with the novel memristor shows limit-cycle behaviour.
Fractional Order Pid and Application of Its Circuit Model
(Chinese inst Engineers, 2016) Atan, Ozkan; Chen, Diyi; Turk, Mustafa
In this paper, the circuit design of a fractional order proportional-integrated derivation (FO-PID) controller for synchronization between different FO chaotic systems has been described. Chaotic synchronization and control are used in different applications in nonlinear physical systems such as performance tests for controllers and chaotic communication systems. FO chaotic systems have been created, and the synchronization control of these two systems has been carried out using an FO-PID controller. The total square error should be minimized in order to determine the parameters and orders of the designed FO controller circuit. The results obtained using the FO controller are better than those obtained using classical control systems. Using an FO-PID controller, the time to reach synchronization decreased significantly.
Fractional Order Sliding Mode Control System Design for Nonlinear Mimo Systems With Time-Varying Delay
(Springer international Publishing Ag, 2018) Atan, Ozkan
This paper has aimed to design fractional-order sliding mode controller (FO-SM) for time delayed MIMO system. The proposed controller has many uncertain parameters so we used adaptive particle swarm optimization method to determine the parameters. The controller provides faster tracking and more stable structure than the integer order. The selection of the controller parameters is important for control performance so intelligent optimization can provide optimal control parameters. Simulation results show that FO-SM controller has robust control performance through change of time delay.
Fuzzy Logic Controller Aided Expert Relaying Mechanism System
(Pergamon-elsevier Science Ltd, 2021) Samonto, Soumyadeep; Kar, Samarjit; Pal, Sagarika; Atan, Ozkan; Sekh, Arif Ahmed
Protection and reliability enactment of electrical systems are important and emerging in power system research. Nowadays, it is very evident that the implementation of an intelligent algorithm is found in the field of substation equipment protection and relaying purposes. Majority of the researches are based on single load connected to a single feeder line and validated using simulation. A hardware based implementation and validation system will be an additional aspects. In this paper, we have discussed an expert system based intelligent relaying scheme by incorporating fuzzy algorithm in microcontroller. Purpose is to control the moving contacts of the breaker part for controlling multiple loads connected to a single feeder line. This paper reports the entire performance of intelligent relaying mechanism only considering stage - I with respect to non-fuzzy based relaying scheme and successfully achieved fastest coordination time after validating it under IEEE 13 Bus system. We have also validated the cascaded fuzzy based system and a non-fuzzy based system using ATMEL microcontroller. (c) 2021 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.
Implementation and Simulation of Fractional Order Chaotic Circuits With Time-Delay
(Springer, 2018) Atan, Ozkan
The potential application of nonlinear systems and time delay, has a resulted in increasing attention to such systems. In this paper, we designed numerical and circuit models for synchronisation of fractional-order chaotic systems with time delay. Also two fractional order Sprott chaotic systems with time delay is used systems, and, the control circuit is designed for synchronization of the chaotic systems. To provide time delay, all pass filter circuit model has been used. Global stability for the synchronisation is defined according to Lyapunov stability criteria and according to the stability method, the input range is determined to make the system stable. The paper is presented numerical solution of fractional order systems with time delay and designed the circuit model of the system. For different time delay values, the changes in the errors of synchronisation were examined. Finally the results of numerical simulations were compared with the results of circuit analysis to verify the theoretical analysis.
Intuitionistic Fuzzy Adaptive Sliding Mode Control of Nonlinear Systems
(Springer, 2020) Kutlu, Fatih; Atan, Ozkan; Silahtar, Onur
In this paper, Takagi-Sugeno intuitionistic fuzzy adaptive sliding mode control system (TS-IFASMC) is designed for nonlinear systems. We propose an intuitionistic fuzzy method to determine the parameters of the adaptive sliding mode control method which is used to control nonlinear systems. Intuitionistic fuzzy systems are considered as a skilled tool to model uncertainty in systems so they can transfer expert knowledge to control schemes better than the other classical methods, and real-world problems can be handled more effectively with this control method. In the proposed system, control parameters are defined by the intuitionistic fuzzy membership, non-membership, hesitation degrees and an integral sliding mode surface for a robust control performance. The novelty of this study is the use of Takagi-Sugeno type intuitionistic fuzzy system in adaptive sliding mode control method and comparison of performance of this new system with other classical methods. Thus, adaptive sliding mode controller based on the Takagi-Sugeno intuitionistic fuzzy system is obtained to provide robust control performance. Finally, the results support the effectiveness of the presented control scheme.
Intuitionistic Fuzzy Control of Twin Rotor Multiple Input Multiple Output Systems
(Ios Press, 2020) Castillo, Oscar; Kutlu, Fatih; Atan, Ozkan
This paper proposes an intuitionistic fuzzy control method for twin rotor multi-input and multi-output (twin rotor MIMO) systems. Twin rotor MIMO systems are often used to measure the performance of control systems as they are extremely sensitive to environmental factors. The use of the intuitionistic fuzzy control method for modeling these uncertainties offers an effective way to increase the robustness of the control system to uncertainties in the structure of twin rotor MIMO systems. In this study, two intuitionistic fuzzy controllers are designed, namely for the main and tail rotors separately and then combine the outputs of these rotors. Also, this method is compared with the classical optimal PID method in terms of stability and performance by various simulations and experiments.
Intuitionistic Fuzzy Sliding Controller for Uncertain Hyperchaotic Synchronization
(Springer Heidelberg, 2020) Atan, Ozkan; Kutlu, Fatih; Castillo, Oscar
In this study, the design of an intuitionistic fuzzy controller for synchronization of two non-identical hyperchaotic systems is proposed. Since hyperchaotic systems has high sensitivity to the initial condition, disturbance and parameter variability. Synchronization of hyperchaotic systems is used to test the controller performance. On the other hand, using of fuzzy logic-based controller has an increasing tendency. As known, fuzzy logic control (FLC), only membership functions are used to obtain a realistic model of the systems. But the intuitionistic fuzzy logic control (IFLC) allows us to obtain a more realistic model than FLC because it also takes into account the degree of non-membership and the degree of uncertainty beside of degree of membership to model examined system. Fuzzy logic-based controllers are hybridized with robust control methods such as sliding mode controller to improve the performance of controller. To take advantages of SMC with fuzzy logic-based IFLC, the IFSMC controller obtained by hybridizing these two methods was designed for hyperchaotic systems. To demonstrate the performance of IFSMC, the results obtained from the synchronization of hyperchaotic systems with FSMC (fuzzy sliding mode controller) and IFSMC were compared. The stability of IFSMC is proved by Lyapunov stability condition. The numerical results and analysis show the efficiency of the IFSMC with regards to synchronization control of uncertain chaotic systems having challenging external disturbances in terms of robustness, minimum tracking error.
On the Qualitative Analysis of Volterra Iddes With Infinite Delay
(Prairie View A & M Univ, dept Mathematics, 2020) Tunc, Osman; Korkmaz, Erdal; Atan, Ozkan
This investigation deals with a nonlinear Volterra integro-differential equation with infinite retardation (IDDE). We will prove three new results on the stability, uniformly stability (US) and square integrability (SI) of solutions of that IDDE. The proofs of theorems rely on the use of an appropriate Lyapunov-Krasovskii functional (LKF). By the outcomes of this paper, we generalize and obtain some former results in mathematical literature under weaker conditions.
Optimal Source Selection for Distributed Bearing Fault Classification Using Wavelet Transform and Machine Learning Algorithms
(MDPI, 2025) Rajabioun, Ramin; Atan, Ozkan
Early and accurate detection of distributed bearing faults is essential to prevent equipment failures and reduce downtime in industrial environments. This study explores the optimal selection of input signal sources for high-accuracy distributed fault classification, employing wavelet transform and machine learning algorithms. The primary contribution of this work is to demonstrate that robust distributed bearing fault diagnosis can be achieved through optimal sensor fusion and wavelet-based feature engineering, without the need for deep learning or high-dimensional inputs. This approach provides interpretable, computationally efficient, and generalizable fault classification, setting it apart from most existing studies that rely on larger models or more extensive data. All experiments were conducted in a controlled laboratory environment across multiple loads and speeds. A comprehensive dataset, including three-axis vibration, stray magnetic flux, and two-phase current signals, was used to diagnose six distinct bearing fault conditions. The wavelet transform is applied to extract frequency-domain features, capturing intricate fault signatures. To identify the most effective input signal combinations, we systematically evaluated Random Forest, XGBoost, and Support Vector Machine (SVM) models. The analysis reveals that specific signal pairs significantly enhance classification accuracy. Notably, combining vibration signals with stray magnetic flux consistently achieved the highest performance across models, with Random Forest reaching perfect test accuracy (100%) and SVM showing robust results. These findings underscore the importance of optimal source selection and wavelet-transformed features for improving machine learning model performance in bearing fault classification tasks. While the results are promising, validation in real-world industrial settings is needed to fully assess the method's practical reliability and impact on predictive maintenance systems.
Qualitative Analyses of Integro-Fractional Differential Equations With Caputo Derivatives and Retardations Via the Lyapunov-Razumikhin Method
(Mdpi, 2021) Tunc, Osman; Atan, Ozkan; Tunc, Cemil; Yao, Jen-Chih
The purpose of this paper is to investigate some qualitative properties of solutions of nonlinear fractional retarded Volterra integro-differential equations (FrRIDEs) with Caputo fractional derivatives. These properties include uniform stability, asymptotic stability, Mittag-Leffer stability and boundedness. The presented results are proved by defining an appropriate Lyapunov function and applying the Lyapunov-Razumikhin method (LRM). Hence, some results that are available in the literature are improved for the FrRIDEs and obtained under weaker conditions via the advantage of the LRM. In order to illustrate the results, two examples are provided.
Retracted: Evaluation of Carcinogenic Effects of Electromagnetic Fields (Emf) (Retracted Article. See Vol. 10, Pg. 331, 2010)
(Assoc Basic Medical Sci Federation Bosnia & Herzegovina Sarajevo, 2010) Bayazit, Vahdettin; Bayram, Banu; Pala, Zeydin; Atan, Ozkan
The purpose of this study was to investigate the carcinogenic effects of electromagnetic fields on human. There are many effects of electromagnetic fields on human such as cancer, epidemiology, acute and chronic effects. These effects vary according to the field strength and environmental conditions. There have been many instances of harmful effects of electromagnetic fields from such seemingly innocuous devices as mobile phones, computers, power lines and domestic wiring. The balance of epidemiologic evidence indicates that mobile phone use of less than 10 years does not pose any increased risk of brain tumour or acoustic neuroma. For long-term use, data are sparse, and the following conclusions are therefore uncertain and tentative.
Synchronisation and Circuit Model of Fractional-Order Chaotic Systems With Time-Delay
(Elsevier, 2016) Atan, Ozkan
The potential application of nonlinear systems and time delay, has a resulted in increasing attention to such systems. Studies on fractional-order nonlinear systems have also received attention. In this paper, we designed numerical and circuit models for synchronisation of fractional-order chaotic systems with time delay. The stability of the system's synchronisation was studied and synchronisation of the two circuits proposed. For different time delay values, the changes in the errors of synchronisation were examined. Finally the results of numerical simulations were compared with the results of circuit analysis to verify the theoretical analysis. (C) 2016, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.