Elektrik Elektronik Mühendisliği Bölümü Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/11468/10518

Listeleniyor 1 - 20 / 65

A new control algorithm for increasing efficiency of PEM fuel cells – Based boost converter using PI controller with PSO method
(Elsevier Ltd, 2024) Yakut, Yurdagül Benteşen; 0000-0003-3236-213X
The single-stack fuel cell system is utilized extensively in several industries. Unfortunately, the main problems are its low efficiency and durability, and unsatisfied reliability, especially in the high-power situation. Due to its significant performance, which includes high output power, durability, and reliability, multi-stack fuel cell systems (MFCS) are becoming more and more attractive. In this study, it is aimed to develope a control algorithm in parallel structure in the Matlab/Simulink software for the efficient use of hydrogen fuel consumption of PEM fuel cells – based boost converter using PI controller with PSO method. Models of both single and parallel connected PEM fuel cells were created in Matlab using mathematical equations in this paper. The analysis made in the study were applied for both models. PEMFCs were connected in parallel and only one DC-DC converter was used for the entire system. According to the load change, the required number of cells are activated due to control algorithm to provide the required power. As a result, the proposed method reduces hydrogen consumption by approximately 5 times under the same load, while optimized parameters reduce output voltage oscillation.
An atom search optimization approach for IIR system identification
(Taylor & Francis Inc, 2023) Ekinci, Serdar; Budak, Cafer; Izci, Davut; Gider, Veysel
Filtering, or digital signal processing, is a significant and fundamental requirement in fields such as signal systems and computers. The process of designing optimal digital filters is difficult, which has led researchers to design filters using emerging evolutionary computations. Metaheuristics have emerged as the most promising tool for solving optimization problems, with excellent development and improvement. However, it has not been clear how to select the best performing metaheuristic to design an optimal digital filter. In this paper, a digital infinite impulse response (IIR) filter is constructed using the atom search optimization (ASO) algorithm impressed by the physical motion of atoms in nature based on molecular dynamics. The simulation results obtained are extensively compared with the results of other optimization algorithms such as moth flame optimization, gravitational search algorithm and artificial bee colony optimization. ASO was found to have the highest percentage of improvement. Furthermore, eight cases are analyzed across four numerical filter instances with the same degree and four with reduced degree, and the results are validated by outperforming several different algorithm-based approaches in the literature. The stability analysis on the basis of pole zero diagrams further cements the efficacy of the ASO for IIR system identification problem.
An effective torque-based method for automatic turn fault detection and turn fault severity classification in permanent magnet synchronous motor
(Springer, 2023) Lale, Timur; Gümüş, Bilal
This article presents a novel approach based on the electromechanical torque signal for the inter-turn short-circuit fault (ISCF) detection and the ISCF severity estimation in permanent magnet synchronous motors (PMSMs). The electromechanical torque data have been obtained experimentally in the healthy condition and in three various states of the ISCF at various load rates and at various operating speeds. To extract the features to be used in the ISCF diagnosis, the fast Fourier transform (FFT) implemented to the torque signal. The torque's second and fourth harmonics were found to be new turn fault features that could be used for ISCF diagnosis. These features were used to train and test the classification algorithms. Four classification algorithms were used to detect ISCF and determine the severity of ISCF: decision trees (DT), artificial neural networks (ANN), K-nearest neighbor (KNN) and support vector machines (SVM). Classification accuracies of 100%, 99.30%, 97.91% and 95.48% were achieved by the ANN, SVM, KNN and DT classifiers, respectively. High accuracy ISCF detection and high accuracy ISCF severity estimation were performed using the developed diagnostic method based on the torque signal.
Wireless power transmission on martian surface for zero-energy devices
(Institute of Electrical and Electronics Engineers Inc., 2022) Tekbıyık, Kürşat; Altınel, Doğay; Cansız, Mustafa; Kurt, Güneş Karabulut
Exploration of the Red Planet is essential on the way through both human colonization and establishing a habitat on the planet. Due to the high costs of space missions, the use of distributed sensor networks has been investigated to make in situ explorations affordable. Along with this, the devices with ultralow-power receivers, which are called zero-energy (ZE) devices, can pave the way to further discoveries for the environment of Mars. This article focuses on wireless power transmission to provide the power required by ZE devices on the Martian surface. The main motivation of this study is to investigate whether conventional harvesters and communication units can supply the required power for a long distance. The numerical results show that it is possible to deliver power to ZE devices without utilizing any sophisticated hardware. In addition, the effects of pointing error and dust storms on harvesting performance are investigated. Comprehensive simulation results reveal that harvester selection and design should be done by considering propagation channel and transmitter characteristics.
Optimization of Proportional–Integral (PI) and Fractional-Order Proportional–Integral (FOPI) parameters using Particle Swarm Optimization/Genetic Algorithm (PSO/GA) in a DC/DC converter for Improving the performance of proton-exchange membrane fuel cells
(Multidisciplinary Digital Publishing Institute (MDPI), 2024) Yakut, Yurdagül Benteşen
In this article, the control of a DC/DC converter was carried out using the proposed methods of conventional PI, PSO-based PI, PSO-based FOPI, GA-based PI, and GA-based FOPI controllers in order to improve the performance of PEMFCs. Simulink models of a PEMFC model with two inputs—hydrogen consumption and oxygen air flow—and with controllers were developed. Then, the outputs of a system based on conventional PI were compared with the proposed methods. IAE, ISTE, and ITAE were employed as fitness functions in optimization algorithms such as PSO and GA. Fitness function value, maximum overshoot, and rising time were utilized as metrics to compare the performance of the methods. PI and FOPI parameters were optimized with the proposed methods and the results were compared with traditional PI in which the optimum parameters were determined by an empirical approach. This research study indicates that the proposed methods perform better than the conventional PI method. However, it becomes apparent that the GA-FOPI approach outperforms the others. The simulation result also shows that the PEMFC model with conventional PI and FOPI controllers in which the controller parameters are tuned using PSO and GA has an acceptable control performance.
Neuro-fuzzy approach on core resistance estimation at loss minimization control of permanent magnet synchronous motor
(Kauno Technologijos Universitetas, 2016) Erdoğan, Hüseyin; Özdemir, Mehmet
Iron losses are among the most significant losses occurring on the Permanent Magnet Synchronous Motor (PMSM). These losses consume active power and cause heat in the iron core. Due to this behavior, they can be represented by an equivalent resistance to make the computations simple. Determining the equivalent core resistance is also a major problem. Computing these lost power is very difficult especially in dynamic applications because these lost power varies by partial differential equations. This study aims to estimate the dynamic core resistance depended on inconstant operating conditions online, and compare the performance of the motor with dynamic versus fixed core resistance at the designed loss minimization algorithm. In order to obtain this estimation, firstly the finite element calculations have been made for many different operating speeds and lost power values were gathered for each speed. Then corresponding core resistance for each power value has been calculated with the dynamic model of a PMSM. Finally, a Neuro-Fuzzy estimator has been designed by computations on the gathered resistance values to estimate the core resistance for different operating conditions. At the end the obtained results are discussed with respect to feasibility of the system.
Soil moisture estimation over vegetated agricultural areas: Tigris Basin, Turkey from Radarsat-2 data by polarimetric decomposition models and a generalized regression neural network
(MDPI, 2017) Özerdem, Mehmet Siraç; Acar, Emrullah; Ekinci, Remzi
Determining the soil moisture in agricultural fields is a significant parameter to use irrigation systems efficiently. In contrast to standard soil moisture measurements, good results might be acquired in a shorter time over large areas by remote sensing tools. In order to estimate the soil moisture over vegetated agricultural areas, a relationship between Radarsat-2 data and measured ground soil moistures was established by polarimetric decomposition models and a generalized regression neural network (GRNN). The experiments were executed over two agricultural sites on the Tigris Basin, Turkey. The study consists of four phases. In the first stage, Radarsat-2 data were acquired on different dates and in situ measurements were implemented simultaneously. In the second phase, the Radarsat-2 data were pre-processed and the GPS coordinates of the soil sample points were imported to this data. Then the standard sigma backscattering coefficients with the Freeman–Durden and H/A/α polarimetric decomposition models were employed for feature extraction and a feature vector with four sigma backscattering coefficients (σhh, σhv, σvh, and σvv) and six polarimetric decomposition parameters (entropy, anisotropy, alpha angle, volume scattering, odd bounce, and double bounce) were generated for each pattern. In the last stage, GRNN was used to estimate the regional soil moisture with the aid of feature vectors. The results indicated that radar is a strong remote sensing tool for soil moisture estimation, with mean absolute errors around 2.31 vol %, 2.11 vol %, and 2.10 vol % for Datasets 1–3, respectively; and 2.46 vol %, 2.70 vol %, 7.09 vol %, and 5.70 vol % on Datasets 1 & 2, 2 & 3, 1 & 3, and 1 & 2 & 3, respectively.
Neural network approach on loss minimization control of a PMSM with core resistance estimation
(Turkiye Klinikleri Journal of Medical Sciences, 2017) Erdoǧan, Hüseyin; Özdemir, Mehmet
Permanent magnet synchronous motors (PMSMs) are often used in industry for high-performance applications. Their key features are high power density, linear torque control capability, high efficiency, and fast dynamic response. Today, PMSMs are prevalent especially for their use in hybrid electric vehicles. Since operating the motor at high efficiency values is critically important for electric vehicles, as for all other applications, minimum loss control appears to be an inevitable requirement in PMSMs. In this study, a neural network-based intelligent minimum loss control technique is applied to a PMSM. It is shown by means of the results obtained that the total machine losses can be controlled in a way that keeps them at a minimum level. It is worth noting here that this improvement is achieved compared to the case with I d set to zero, where no minimum loss control technique is used. Within this context, hysteresis and eddy current losses are primarily obtained under certain conditions by means of a PMSM Finite element model, initially developed by CEDRAT as an educational demo. A comprehensive loss model with a dynamic core resistor estimator is developed using this information. A neural network controller is then applied to this model and comparisons are made with analytical methods such as field weakening and maximum torque per ampere control techniques. Finally, the obtained results are discussed.
Practical tuning algorithm of PDµ controller for processes with time delay
(Elsevier B.V., 2017) Özyetkin, Mine Münevver; Tan, Nusret
In this paper, a practical tuning algorithm of fractional order PD controller for processes with time delay using the weighted geometrical center (WGC) method is presented. This method is based on calculating of the stabilizing PDµ controller parameters region which is plotted using the stability boundary locus in the (kd,kp) plane and computing the weighted geometrical center of stability region. The important advantages of the proposed method are both calculating of controller parameters without using complex graphical methods and ensuring the stability of closed loop system. From the examples, it can be easily seen that this simple tuning method can perform quite reliable results in that unit step response.
Smith predictor with sliding mode control for processes with large dead times
(De Gruyter Open Ltd, 2017) Mehta, Utkal; Kaya, İbrahim
The paper discusses the Smith Predictor scheme with Sliding Mode Controller (SP-SMC) for processes with large dead times. This technique gives improved load-disturbance rejection with optimum input control signal variations. A power rate reaching law is incorporated in the sporadic part of sliding mode control such that the overall performance recovers meaningfully. The proposed scheme obtains parameter values by satisfying a new performance index which is based on biobjective constraint. In simulation study, the efficiency of the method is evaluated for robustness and transient performance over reported techniques.
A new approach based on electromechanical torque for detection of inter-turn fault in permanent magnet synchronous motor
(Taylor and Francis Ltd., 2022) Lale, Timur; Gümüş, Bilal
Fault detection is an important issue for permanent magnet synchronous motors (PMSMs). In the initial stage, it is very crucial to detect stator winding inter-turn short-circuit failure, which is one of the most common types of faults. In this paper, a new approach based on electromechanical torque has been proposed to detect the stator inter-turn short circuit fault (ISCF) that occurs in surface-mounted permanent magnet synchronous motors (PMSMs). New fault signatures based on the torque signal that can be used in stator winding ISCF detection are tried to be found in the torque frequency distribution. Fast Fourier Transform (FFT) was used to extract the torque frequency components associated with the stator ISCF. It was found that the amplitudes of the 2nd and 4th harmonic components of the torque signal are distinctive features that can be used for stator winding ISCF detection in PMSM. With the proposed components of the 2nd and 4th harmonic of torque, an inter-turn fault can be easily detected at the initial stage. Both experimental results and simulation results for healthy and three different faulty states (2%, 12.5%, and 25% ISCF) at different load levels and different speeds are presented in this paper.
Instruction of molecular structure similarity and scaffolds of drugs under investigation in ebola virus treatment by atom-pair and graph network: A combination of favipiravir and molnupiravir
(Elsevier Ltd, 2022) Gider, Veysel; Budak, Cafer
The virus that causes Ebola is fatal. Although many researchers have attempted to contain this deadly infection, the fatality rate remains high. The atom-pair fingerprint technique was used to compare drugs suggested for the treatment of Ebola or those that are currently being tested in clinical settings. Subsequently, using scaffold network graph (SNG) methods, the molecular and structural scaffolds of the drugs chosen based on these similar results were created, and the drug structures were examined. Public databases (PubChem and DrugBank) and literature regarding Ebola treatment were used in the analysis. Graphical representations of the molecular architecture and core structures of the drugs with the highest similarity to Food and Drug Administration (FDA)-approved drugs were produced using the SNG method. The combination of molnupiravir, the first licensed oral medication candidate for COVID-19, and favipiravir, employed in other viral outbreaks, should be further researched for treating Ebola, as observed in our study. We also believe that chemists will benefit from understanding the core structure(s) of medication molecules effective against the Ebola virus, their inhibitors, and the chemical structure similarities of existing pharmaceuticals utilized to build alternative drugs or drug combinations.
Maximum sensitivity (Ms)-based I-PD controller design for the control of integrating processes with time delay
(Taylor and Francis Ltd., 2023) Peker, Fuat; Kaya, İbrahim
Integrating processes, whose one or more poles are located at the origin, are common in the process industry. This paper focuses on maximum sensitivity (Ms)-based control of these types of processes. Integral–proportional derivative (I-PD) controllers are designed by exploiting the direct synthesis method for different forms of integrating processes. The suggested design approach is based on comparing the characteristic equation of the closed-loop system, which comprises the integrating system and I-PD controller with a lead/lag filter, with the desired characteristic equation. Simple and analytical adjusting rules are followed to determine the parameters of the I-PD controller and the lead/lag filter according to desired robustness specified by maximum sensitivity (Ms). The formulas provided contain process transfer function parameters and a tuning parameter that is used for setting the desired Ms. The benefits of the proposed technique are demonstrated by simulation examples and a real-time application of cart position control on an experimental set-up. Comparisons with some reported proportional–integral–derivative (PID) and I-PD design techniques are presented to demonstrate the advantages of the proposed design method more evidently.
Mobile robot application with hierarchical start position DQN
(Hindawi Limited, 2022) Erkan, Emre; Arseri̇m, Muhammet Ali
Advances in deep learning significantly affect reinforcement learning, which results in the emergence of Deep RL (DRL). DRL does not need a data set and has the potential beyond the performance of human experts, resulting in significant developments in the field of artificial intelligence. However, because a DRL agent has to interact with the environment a lot while it is trained, it is difficult to be trained directly in the real environment due to the long training time, high cost, and possible material damage. Therefore, most or all of the training of DRL agents for real-world applications is conducted in virtual environments. This study focused on the difficulty in a mobile robot to reach its target by making a path plan in a real-world environment. The Minimalistic Gridworld virtual environment has been used for training the DRL agent, and to our knowledge, we have implemented the first real-world implementation for this environment. A DRL algorithm with higher performance than the classical Deep Q-network algorithm was created with the expanded environment. A mobile robot was designed for use in a real-world application. To match the virtual environment with the real environment, algorithms that can detect the position of the mobile robot and the target, as well as the rotation of the mobile robot, were created. As a result, a DRL-based mobile robot was developed that uses only the top view of the environment and can reach its target regardless of its initial position and rotation.
Multiband RF energy harvesting for zero-energy devices
(Springer Science and Business Media Deutschland GmbH, 2023) Cansız, Mustafa; Altınel, Doğay
Radio frequency (RF) energy harvesting system scavenges energy from electromagnetic waves and supplies power wirelessly enabling the usage of zero-energy sensors or devices. Frequency band of the electromagnetic wave is an important parameter for energy harvesting systems. In this study, simultaneous multiband RF energy harvesting systems are analyzed both theoretically and experimentally for zero-energy devices. An advanced measurement system, which consists of an RF energy harvesting circuit, universal software radio peripherals (USRPs), and other equipment, is established to obtain received power and charging time samples for Industrial, scientific, and medical (ISM) and Global system for mobile communications (GSM) radio bands. The effects of each band and their different combinations on the charging time as well as the conversion parameter are thoroughly investigated for RF energy harvesting. According to a real-life communication scenario, the outage probabilities of wireless zero-energy sensors are presented. It is demonstrated in this study that the use of multiband frequencies in energy harvesting, in addition to the low-power requirement, increases the feasibility of zero-energy devices.
Towards environment-aware fall risk assessment: Classifying walking surface conditions using IMU-Based Gait Data and deep learning
(Multidisciplinary Digital Publishing Institute (MDPI), 2023) Yıldız, Abdulnasır
Fall risk assessment (FRA) helps clinicians make decisions about the best preventative measures to lower the risk of falls by identifying the different risks that are specific to an individual. With the development of wearable technologies such as inertial measurement units (IMUs), several free-living FRA methods based on fall predictors derived from IMU-based data have been introduced. The performance of such methods could be improved by increasing awareness of the individuals’ walking environment. This study aims to introduce and analyze a 25-layer convolutional neural network model for classifying nine walking surface conditions using IMU-based gait data, providing a basis for environment-aware FRAs. A database containing data collected from thirty participants who wore six IMU sensors while walking on nine surface conditions was employed. A systematic analysis was conducted to determine the effects of gait signals (acceleration, magnetic field, and rate of turn), sensor placement, and signal segment size on the method’s performance. Accuracies of 0.935 and 0.969 were achieved using a single and dual sensor, respectively, reaching an accuracy of 0.971 in the best-case scenario with optimal settings. The findings and analysis can help to develop more reliable and interpretable fall predictors, eventually leading to environment-aware FRA methods.
Optimal PI–PD controller design for pure integrating processes with time delay
(Springer, 2021) Kaya, İbrahim
Though Proportional-Integral-Derivative (PID) controllers are commonly being used for process control applications, it has been proven that they may give unacceptable closed loop responses for open loop unstable processes including integrating ones. Hence, this paper addresses to tuning of PI–PD controllers which is an extension of PID controllers and uses PD part in an inner feedback loop to convert the open loop unstable processes to a stable one so that PI controller in the forward path can be used to achieve a better closed loop response. PI–PD tuning parameters are determined from simple analytical rules which were obtained from minimization of the control system error based on IST3E criterion which is an integral performance index and has been proven to be resulting in very satisfactory closed loop responses. Derived tuning rules are in terms of the assumed process transfer function parameters, namely the gain and time delay. Effectiveness and superiority of obtained tuning rules have been shown by simulation examples.
Multi-task learning for arousal and sleep stage detection using fully convolutional networks
(IOP Publishing, 2023) Zan, Hasan; Yıldız, Abdulnasır
Objective.Sleep is a critical physiological process that plays a vital role in maintaining physical and mental health. Accurate detection of arousals and sleep stages is essential for the diagnosis of sleep disorders, as frequent and excessive occurrences of arousals disrupt sleep stage patterns and lead to poor sleep quality, negatively impacting physical and mental health. Polysomnography is a traditional method for arousal and sleep stage detection that is time-consuming and prone to high variability among experts.Approach. In this paper, we propose a novel multi-task learning approach for arousal and sleep stage detection using fully convolutional neural networks. Our model, FullSleepNet, accepts a full-night single-channel EEG signal as input and produces segmentation masks for arousal and sleep stage labels. FullSleepNet comprises four modules: a convolutional module to extract local features, a recurrent module to capture long-range dependencies, an attention mechanism to focus on relevant parts of the input, and a segmentation module to output final predictions.Main results.By unifying the two interrelated tasks as segmentation problems and employing a multi-task learning approach, FullSleepNet achieves state-of-the-art performance for arousal detection with an area under the precision-recall curve of 0.70 on Sleep Heart Health Study and Multi-Ethnic Study of Atherosclerosis datasets. For sleep stage classification, FullSleepNet obtains comparable performance on both datasets, achieving an accuracy of 0.88 and an F1-score of 0.80 on the former and an accuracy of 0.83 and an F1-score of 0.76 on the latter.Significance. Our results demonstrate that FullSleepNet offers improved practicality, efficiency, and accuracy for the detection of arousal and classification of sleep stages using raw EEG signals as input.
Deep insights into MCI diagnosis: A comparative deep learning analysis of EEG time series
(Elsevier, Mart 2024) Şeker, Mesut; Özerdem, Mehmet Siraç
Background Individuals in the early stages of Alzheimer’s Disease (AD) are typically diagnosed with Mild Cognitive Impairment (MCI). MCI represents a transitional phase between normal cognitive function and AD. Electroencephalography (EEG) records carry valuable insights into cerebral cortex brain activities to analyze neuronal degeneration. To enhance the precision of dementia diagnosis, automatic and intelligent methods are required for the analysis and processing of EEG signals. New methods This paper aims to address the challenges associated with MCI diagnosis by leveraging EEG signals and deep learning techniques. The analysis in this study focuses on processing the information embedded within the sequence of raw EEG time series data. EEG recordings are collected from 10 Healthy Controls (HC) and 10 MCI participants using 19 electrodes during a 30 min eyes-closed session. EEG time series are transformed into 2 separate formats of input tensors and applied to deep neural network architectures. Convolutional Neural Network (CNN) and ResNet from scratch are performed with 2D time series with different segment lengths. Furthermore, EEGNet and DeepConvNet architectures are utilized for 1D time series. Results ResNet demonstrates superior effectiveness in detecting MCI when compared to CNN architecture. Complete discrimination is achieved using EEGNet and DeepConvNet for noisy segments. Comparison with existing methods ResNet has yielded a 3 % higher accuracy rate compared to CNN. None of the architectures in the literature have achieved 100 % accuracy except proposed EEGNet and DeepConvnet. Conclusion Deep learning architectures hold great promise in enhancing the accuracy of early MCI detection.
Complexity of EEG dynamics for early diagnosis of alzheimer's disease using permutation entropy neuromarker
(Elsevier, 2021) Şeker, Mesut; Özbek, Yağmur; Yener, Görsev; Özerdem, Mehmet Siraç
Background and objective Electroencephalogram (EEG) is one of the most demanded screening tools that investigates the effects of Alzheimer's Disease (AD) on human brain. Identification of AD in early stage gives rise to efficient treatment in dementia. Mild Cognitive Impairment (MCI) is considered as a conversion stage. Reducing EEG complexity can be used as a marker to detect AD. The aim of this study is to develop a 3-way diagnostic classification using EEG complexity in the detection of MCI/AD in clinical practice. This study also investigates the effects of different eyes states, i.e. eyes-open, eyes-closed on classification performance. Methods EEG recordings from 85 AD, 85 MCI subjects, and 85 Healthy Controls with eyes-open and eyes- closed are analyzed. Permutation Entropy (PE) values are computed from frontal, central, parietal, temporal, and occipital regions for each EEG epoch. Distribution of PE values are visualized to observe discrimination of MCI/AD with HC. Visual investigations are combined with statistical analysis using ANOVA to determine whether groups are significant or not. Multinomial Logistic Regression model is applied to feature sets in order to classify participants individually. Results Distribution of measured PE shows that EEG complexity is lower in AD and higher in HC group. MCI group is observed as an intermediate form due to heterogeneous values. Results from 3-way classification indicate that F1-scores and rates of sensitivity and specificity achieve the highest overall discrimination rates reaching up to 100% for at TP8 for eyes-closed condition; and C3, C4, T8, O2 electrodes for eyes-open condition. Classification of HC from both patient groups is achieved best. Eyes-open state increases discrimination of MCI and AD. Conclusions This nonlinear EEG methodology study contributes to literature with high discrimination rates for identification of AD. PE is recommended as a practical diagnostic neuro-marker for AD studies. Resting state EEG at eyes-open condition can be more advantageous over eyes-closed EEG recordings for diagnosis of AD.

Güncel Gönderiler