SDG 7 · Erişilebilir ve Temiz Enerji · SDG · Erzincan Binali Yıldırım Üniversitesi

Yazarlar

Yayınlar

Yeniden eskiye Eskiden yeniye

ArticleYalnız künye2023/r/ebyu/12914
Implementation of hybrid wind speed prediction model based on different data mining and signal processing approaches
Katipoğlu, Okan Mert
Accurate estimation of wind speed (WS) data, which greatly influences meteorological parameters, plays a vital role in the safe operation and optimization of the power system and water resource management. The study’s main aim is to combine artificial intelligence and signal decomposition techniques to improve WS prediction accuracy. Feed-forward back propagation neural network (FFBNN), support vector machine (SVM) and Gaussian processes regression (GPR) models, discrete wavelet transform (DWT), and empirical mode decomposition (EMD) were used to forecast the WS values 1 month ahead in Burdur meteorology station. Statistical criteria such as Willmott’s index of agreement, mean bias error, mean squared error, determination coefficient, Taylor diagram and regression analysis, and graphical indicators were used to evaluate the prediction success of the models. As a result of the study, it was determined that both wavelet transform and EMD signal processing increased the WS prediction performance of the stand-alone ML model. The best performance was obtained with the hybrid EMD-Matern 5/2 kernel GPR with test (R2:0.802) and validation (R2:0.606). The most successful model structure was obtained using input variables with a delay of up to 3 months. The study’s results contribute to wind energy-related institutions in terms of practical use, planning, and management of wind energy.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2023/r/ebyu/12904
A Common Capacitor Hybrid Buck-Boost Converter
Can, Erol
DC-DC converters are electronic circuit elements that are frequently used to change the direct current (DC) level. This paper presents a hybrid buck-boost converter-with constant modulation index-that can change a DC voltage at two directions compared to the conventional buck-boost DC-DC converters. First, the circuit structure and operation are given. Then, the performance of the proposed converter is tested on resistive and inductive loads, and compared with that of conventional buck-boost converters. The obtained results demonstrate the effectiveness of the proposed converter. They unveil that the proposed converter-compared to the conventional buck-boost converters – produces a higher and flexible rate of conversion without changing the operating ratio of the switches. Moreover, the proposed converter is able to change the voltage on double way on load for a constant operating ratio, while the traditional converters provide a one-way conversion.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2023/r/ebyu/12690
Fully soft-switched half-bridge DC–DC converter for hybrid electric vehicle battery charge applications
Yesilyurt, Huseyin; Sahin, Yakup; Ting, Naim Suleyman
This paper proposes a soft-switching (SS) active snubber cell for half-bridge (HB) DC–DC converters, which are utilized in hybrid vehicle battery charge applications. The proposed converter has an advantage over conventional HB DC–DC converters, which suffer from transformer leakage inductance issues. The new snubber cell performs SS operation using the energy stored in the leakage inductance. Thus, the leakage inductance, which creates troubles for HS DC–DC converters, is beneficial to the proposed converter. The proposed SS HB DC–DC converter is compared with the conventional HB DC–DC converter under 100 kHz and 110 W output power operating conditions. The efficiency of the proposed converter is 7.3% and 4.8% higher than the conventional HB converter at light and heavy loads, respectively. The proposed active snubber cell provides complete SS for the main and auxiliary semiconductor switches. The new snubber cell has a basic structure, low-cost, ease of application, and simple control features.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2023/r/ebyu/12535
Hydrothermal synthesis of MnCO3 thin film and its conversion to Mn-oxides by annealing in different atmospheres
Astam, Aykut; İnanç, Cemal Turgay
Transition metal carbonates are of great interest, not only as alternative electrode materials in Li/Zn/Na/K-ion batteries or supercapacitors, but also as solid precursors for the synthesis of transition metal oxides via thermal decomposition. In this work, thin films of MnCO3 were deposited on quartz substrates via a mild one-pot hydrothermal process without using any catalysts or templates and the conversion of these films to manganese oxides through post-deposition thermal annealing for 1 h in air and nitrogen atmospheres was investigated. The films were analyzed by X-ray diffraction, scanning electron microscopy, energy dispersive X-ray analysis, X-ray photoelectron spectroscopy, Raman spectroscopy, Fourier transform infrared spectroscopy, and optical absorption measurements before and after annealing. The obtained results showed that as deposited films composed of MnCO3 with an impurity phase of Mn3O4 and annealing in air atmosphere caused the conversion of the films to Mn2O3, whereas nitrogen atmosphere led to the conversion to MnO with a secondary phase of Mn3O4. After annealing in both atmospheres, the size and shape of the microcubic structure were mainly retained, except for porosity caused by the release of CO2 and O2 gases. From the analysis of the room temperature optical absorption measurements, direct optical band gaps of the as deposited and air annealed films were determined as 3.27 eV and 2.30 eV, respectively, whereas the nitrogen annealed film was found to have two band gaps of 2.50 eV and 2.71 eV.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2023/r/ebyu/12470
Daily global solar radiation time series prediction using variational mode decomposition combined with multi-functional recurrent fuzzy neural network and quantile regression forests algorithm
Abdallah, Mohammed; Mohammadi, Babak; Nasiri, Hamid; Katipoğlu, Okan Mert; Abdalla, Modawy Adam Ali; Ebadzadeh, Mohammad Mehdi
Global solar radiation (GSR) prediction capability with a reliable model and high accuracy is crucial for comprehending hydrological and meteorological systems. It is vital for the production of renewable and clean energy. This research aims to evaluate the performance of combined variational mode decomposition (VMD) with a multi-functional recurrent fuzzy neural network (MFRFNN) and quantile regression forests (QRF) models for GSR prediction in daily scales. The hybrid VMD-MFRFNN and QRF models were compared with standalone MFRFNN, random forest (RF), extreme gradient boosting (XGB), and M5 tree (M5T) models across the Lund and Växjö meteorological stations in Sweden. The meteorological data from 2008 to 2017 were used to train the models, while the prediction accuracy was verified by using the data from 2018 to 2021 under five different input combinations. The various meteorological-based scenarios (including the input are air temperatures (Tmin, Tmax, T), wind speed (WS), relative humidity (RH), sunshine duration (SSH), and maximum possible sunshine duration (N)) were considered as input of predictor models. The current study resulted that the M5T model exhibited higher accuracy than RF and XGB models, while the QRF model showed equivalent performance with the M5T model at both study sites. The MFRFNN model outperformed QRF and M5T models across all input combinations at both study sites. The hybrid VMD-MFRFNN model showed the best performance when fewer input variables (Tmin, Tmax, T, WS at Lund station and Tmin, Tmax, T, WS, SSH, RH at Växjö station) were used for GSR prediction. We conclude that the MFRFNN model best predicts average daily GSR when combining all meteorological variables (Tmin, Tmax, T, WS, SSH, RH, N).
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2023/r/ebyu/12415
Renewable Energy Consumption Convergence in G-7 Countries
Helmi, Mohamad Husam; Çatık, Abdurrahman Nazif; Coşkun, Nuran; Ballı, Esra; Sigeze, Çiler
This study examines the convergence of renewable energy consumption in G-7 countries. We employ LM unit root and RALS version of LM unit root tests with endogenously determined with structural one or two breaks. Despite the increase in renewable energy consumption in G-7 countries, it is important to identify whether renewable energy consumption converges across these countries to formulate appropriate policies to support sustainable energy consumption and reduce CO2 emissions. Our analysis indicated that Germany, Italy, and Canada exhibit evidence of convergence. However, after employing both the LM and RALS versions of the LM unit root tests, which consider level shifts with one or two breaks or trend shifts with one or two breaks, we found that there is no evidence of convergence for France, Japan, and the United Kingdom. Overall, our results highlight the importance of formulating country-specific policies to support renewable energy consumption and reduce CO2 emissions. Policymakers need to identify the drivers of renewable energy consumption and adopt appropriate measures to ensure that the countries can meet their climate goals while also ensuring energy security.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2023/r/ebyu/12348
Rational design of MXene/Boron Carbon Nitride nanotube composite electrode for supercapacitors with improved electrochemical properties
Tuzluca Yesilbag, Fatma Nur; Yesilbag, Yasar Ozkan; Huseyin, Ahmad; Salih, Ahmed Jalal Salih; Ertugrul, Mehmet
3D structures obtained using 1D and 2D materials are promising materials in energy storage. Optimizing the interlayer spacing of 2D MXene through flexible conductive materials is an important step in synthesizing 3D composite electrodes. In this study, flexible and conductive MXene/BCN nanotube composite film electrodes were prepared by vacuum filtration using BCN nanotubes in different weight ratios (10 %, 20 %, and 30 %) in mixed and sandwiched structures. The mixed MXene/BCN10 (m-MX/BCN10) composite film electrode structure attained a specific capacitance of 678 F g−1, the highest of all tested electrodes, and exhibited remarkable cycle stability by retaining 95 % of its capacitance even after 10,000 charge/discharge cycles. In the symmetric supercapacitor (SSC), the cell exhibited a specific capacitance of 97 % after 10,000 charge/discharge cycles. Moreover, SSC showed an energy density of 32 Wh kg−1 and a power density of 11.5 kW kg−1. The composite electrodes made of 2D Ti3C2Tx MXene and 1D BCN nanotube materials open up a new avenue for synthesizing promising materials for energy storage in transition metal carbides and 1D nanotubes or nanowires.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2022/r/ebyu/20596
Evaluation of Irreversibility Analysis for Different Coal Types of a Thermal Power Plant
Uzun, Sinem
In this study, first law (energy conservation) and second law (exergy) analyzes of thermodynamics were performed for a thermal power plant. It is very important to perform energy and exergy analyzes in industrial plants. These analyzes can provide guidance on improving energy efficiency and recycling waste energy. In this study, energy and exergy analyzes were made for coals with different chemical contents in nine different countries. According to the results of the analysis, the highest first-law efficiency was found in Serbian coal (second type), as 53.61%. The second highest law efficiency was determined as 46.67% in Bangladesh coal (sixth type). Environmental Destruction Index (EDI) and Sustainability Index (SI) values were determined for all coal types. According to the results of the analysis, the highest EDI value was obtained as 4.00 at the temperature of 305 K for the 2nd coal type, and the highest SI value was obtained as 1.91 at the temperature of 293 K for the 6th coal type, according to the changing reference temperature values. According to this study, the highest second law efficiency was obtained from Bangladesh coal with a carbon (C) content of 77.84%.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2022/r/ebyu/20364
Energy and Exergy Analysis of a Shell and Tube Heat Exchangers Having Smooth and Corrugated Inner Tubes
Celen, Ali
Shell and tube heat exchangers are one of the most used heat exchanger types in applications and it is important to predict heat transfer capacity and pressure loss in both design stage. Heat transfer capacity of a heat exchanger can be enhanced by using tubes having enhanced surfaces instead of smooth ones. In this study, the usage of corrugated tubes in a shell and tube heat exchanger is investigated by using ε-NTU method, energy/exergy analysis. The impact of the usage of corrugated tubes on hot and cold fluid outlet temperatures, energy/exergy efficiencies, entropy generation and total exergy destruction are researched for various operation conditions. The results revealed that the difference between fluid outlet temperatures can be decreased by using tubes having corrugated surfaces instead of smooth ones because of fluid mixing and secondary flows obtained by means of the corrugations. Overall heat transfer coefficient of heat exchanger is enhanced up to 8% with the usage of corrugated tube in considered operation conditions. It is exhibited that the energy and exergy efficiencies of heat exchanger can be improved up to 18% and 16% with the usage of corrugated tubes instead of one having smooth tubes. Moreover, the entropy generation because of heat transfer and pressure loss and total exergy destruction of considered heat exchangers are determined to reveal the impact of corrugated tubes.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2022/r/ebyu/20110
Türkiye'de Ankara ili için düz plaka kollektör güneş sıcak su sisteminin TRNSYS yazılımı ile incelenmesi
Uzun, Sinem; Seyhan, Aslıhan Kurnuç; Coşkun, Salih
Düz plaka kollektör kullanan bir güneş enerjili su ısıtma sistemi, Türkiye'deki Ankara ili için, bir konut biriminin kullanım sıcak suyu ihtiyacı için modellenmiştir. Gerekli tasarım parametreleri belirlenmiş ve analizler TRNSYS simülasyon programı kullanılarak gerçekleştirilmiştir. Modellenen sistemde kullanım suyu sıcaklığı 55 °C olarak belirlenmiş ve kullanım yoğunluğuna göre gün içerisinde farklı debilerde su çekimleri gerçekleştirilmiştir. Su çekim hızları 07.00-09.00 saatleri arasında 80 kg/saat, 12.00-13.00 saatleri arasında 100 kg/saat ve 17.00-22.00 saatleri arasında 50 kg/saat olarak belirlenmiştir. Elde edilen sonuçlara göre tasarlanan sistem, yardımcı ısıtıcılar vasıtasıyla güneş enerjisi kullanılarak yaz ve kış aylarındaki sıcak su ihtiyacını karşılayabilmiştir. Kolektör verimi Eylül ayında %40 ile en yüksek değerine ulaşırken, Aralık ayında %8 ile en düşük verim değerine ulaşmıştır.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2022/r/ebyu/18318
Energy and Exergy Analysis of Solar Collectors Having Different Tilt Angles: Case Study of Erzincan City
Kaba, Muhammet Yasin; Kurnuc Seyhan, Aslihan; Celen, Pinar; Celen, Ali
Solar collectors are frequently used in domestic water heating applications. In the design stage, the positioning of solar collector with suitable title angle is important in order to utilize from sun energy efficiently. In this study, the effect of tilt angle of a solar collector located to Erzincan city on monthly/daily average radiation values, water outlet temperature, energy and exergy efficiencies are theoretically investigated. It is seen that the maximum and minimum values of optimum tilt angles are 63 degrees ve 0 degrees for December and June, respectively. Tilt angles which are suggested for Erzincan (27.14 degrees) and calculated are compared for daily average hourly radiation values and it is seen that the maximum variation is 26% for January. In addition, energy and exergy efficiencies of solar collector are estimated and the maximum efficiencies are determined as 74.2% ve 9.7% for optimum tilt angles.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2022/r/ebyu/18206
The inverter with reverse connected double converter driving unbalanced loads
Can, Erol
Inverter circuits play an important role in providing energy to multiple loads or energy lines. In cases where power lines or loads are unbalanced, it is important to balance and regulate the power it carries. Therefore, in this study, an inverter structure with an inverted connecting double dc-dc converter is used to drive unbalanced loads. While load balancing is performed by changing the widths of the pulse width modulation that make up the voltage in load balancing methods in other inverter studies, the maximum point of the generated voltage is changed by affecting the operating times of the converters in this study. First, the circuit structure and the working order of the circuit are given. Then three-phase balanced and unbalanced loads are driven. The unbalanced loads driven are finally balanced with the proposed circuit structure. Distortions of load currents are decreased as %3, 51. This distortion value is lower than 4% reported by the international IEEE, while the obtained load currents maintain a smooth sinusoidal structure.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2022/r/ebyu/18144
A new multi-level inverter with reverse connected dual dc to dc converter at simulation
Can, Erol
It is very important to drive loads and control the electrical devices with changing electrical energy levels and change a voltage form. While DC-DC converters are used to change the value level of direct current (DC) electrical energy, inverters are used to change its form such as alternating voltage. Unlike these studies in the literature, for the first time, dc-dc converters are used to a new device structure to convert dc electrical energy into alternating current (AC) electrical energy and they can also change an amplitude of the multi-level voltage. So, the paper presents a multi-level inverter with reverse connected dual dc to dc converter. Firstly, the circuit structure and the signals that control the circuit are given and the operating logic is explained. Then, the proposed circuit is gradually modeling in MATLAB Simulink. After that, the circuit is operated in MATLAB Simulink and its performance is measured. According to the results obtained, the new circuit structure gives highly successful results.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2022/r/ebyu/14052
Prediction of experimental thermal performance of new designed cold plate for electric vehicles’ Li-ion pouch-type battery with artificial neural network
Kalkan, Orhan; Colak, Andac Batur; Celen, Ali; Bakirci, Kadir; Dalkilic, Ahmet Selim
Since liquid-based thermal management systems are usually preferred methods for battery electric vehicles and cold plates are generally preferred to circulate the coolant, studies on their design are becoming increasingly essential. Besides, it seems useful to work artificial intelligence approaches to evaluate different battery thermal management systems, as it is known that the use of artificial intelligence is increasing in many applications today. The aim of this paper is to build up an artificial neural network model due to predict average battery temperature and maximum temperature difference on the battery surface which are also the artificial neural network outputs. The model inputs are depth of discharge, coolant flow rate (0.1, 0.6 and 1.1 l/min), discharge rate (1C- 5C), coolant inlet temperature (15, 25 and 35 °C). It is developed for a serpentine tubed cold plate, and mini channeled one which has novel design. To shorten the training time, after the optimization of the data set, a total of 270 data sets were utilized for training, validation, and test phases. In addition, the developed model predicts successfully average battery temperature and maximum temperature difference on the battery surface in the 10% error band range. Finally, the maximum margin of deviation and R values are 7.3% and 0.997%, respectively.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2022/r/ebyu/13987
Investigating the potential of renewable energy in establishing global peace: Fresh evidence from top energy consumer countries
Destek, Mehmet Akif; Manga, Müge; Cengiz, Orhan; Destek, Gamze
Although the socio-economic determinants of terrorism are conducted by many researchers using different samples and time spans, the impact of renewable energy consumption on terrorism has been ignored for a long time. To bridge the gap, this paper aims to investigate the impact of renewable energy consumption on terrorism regarding economic growth, non-renewable energy consumption, and income inequality over the period straddling 1990 and 2019 for a panel of the USA, China, India, Iran, Germany, and Russia. We employ the CUP-FM and CUP-BC estimators to reveal the long-run relationship between variables. The empirical findings suggest that renewable energy consumption has a negative impact on terrorism. A 1% increase in renewable energy consumption decreases terrorism by 0.315% and 0.631%, according to the CUP-FM and CUP-BC estimators, respectively. Economic growth also has a negative impact on terrorism, whereas non-renewable energy consumption and income inequality positively affect terrorism. Our empirical findings highlighted that renewable energy consumption and economic growth are crucial for combating terrorism in these countries. Therefore, these countries need to improve comprehensive policies in terms of renewable energy consumption and simultaneously decrease non-renewable energy consumption and income inequality.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2022/r/ebyu/13927
A Comparative Analysis of Exhaust Gas Temperature Based on Machine Learning Models for Aviation Applications
Atasoy, Vehbi Emrah; Suzer, Ahmet Esat; Ekici, Selcuk
The main objective of this study is to investigate elaborately the relationship between exhaust gas temperature (EGT) and various operational parameters specific to aero-engine for the cruise phase. EGT prediction is performed based on different models, including deep learning (DL) and support vector machine (SVM), using a set of historical flight data, more than 1300. In order to achieve this goal, the EGT is taken as the output parameter while the most key variables for the EGT prediction are taken as the input parameters to the models. Several statistical goodness tests, namely root-mean-square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2), are conducted to make a fair comparison between the efficiency and performance of each model that is developed based on Matrix Laboratory (matlab) and R code. The relative importance for the altitude (ALT) parameter of 11.89% has the highest value while the lowest relatively importance parameter is vibration (VIB) of 5.00%. EGT variation for the actual data is in the range of 459.05 and 607.32 °C. It is observed that the EGT variation of DL and SVM ranges from 457.09 to 604.52 and from 454.64 to 603.23 °C, respectively. Furthermore, the prediction error for DL and SVM fluctuates between a minimum of -21.61 to a maximum of 22.50 °C and a minimum of -13.34 to a maximum of 12.44 °C, respectively. In the light of the statistical test results, it is concluded that the DL model with RMSE of 4.3922, MAE of 3.3981, and R2 of 0.9834 shows more excellent ability in predicting EGT than the SVM model with RMSE of 5.5212, MAE of 4.0527, and R2 of 0.9712. This study may effectively be applied to different aircraft types as a useful roadmap for academic and industrial researchers in this sort of application and it shed the light on optimizing performance for a specific aircraft by thermodynamic methods.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2022/r/ebyu/13917
Thermal–hydraulic performance of the circular-slice-shaped-winglet for tube bank heat exchanger
Tepe, Ahmet Ümit; Yilmaz, Harun
In this study, heat transfer performance of circular-slice-shaped-winglet (CSSW) for tube bank heat exchanger (TBHE) was numerically investigated. Circular-slice angle (α = 5°, 10° and 20°), layer gap (h/d = 0.08, 0.14, and 0.20) and winglet diameter (D/d = 1.60, 1.76 and 1.92) were analyzed as geometric parameters to obtain optimal design. Comprehensive numerical simulations were conducted under both laminar and turbulent flow (1100 ≤ Re ≤ 8500) conditions. Navier Stokes Equations were solved by using RNG k-ε turbulence model (with enhanced wall treatment). Colburn-j factor (j), friction factor (f), modified London area goodness factor (j/f1/3) and performance evaluation criterion (PEC) were investigated quantitatively. Flow characteristics were also analyzed to elucidate the underlying physics of the effects of CSSW on thermal-hydraulic performance for TBHE. Results were compared with the data related to bare tube heat exchanger, and showed that the highest modified London area goodness factor is 26.34% with α = 10°, h/d = 0.20 and D/d = 1.92 CSSW winglet design. Additionally, numerical calculations revealed that PEC increased to 1.356 with these CSSW design parameters, which corresponds to reduction of the required total heat transfer area by 36.60% compared to the bare tube heat exchanger for the same heat duty at a fixed pumping power.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2022/r/ebyu/13897
EXERGY ANALYSIS AND DETERMINATION OF IRREVERSIBILTY OF A THERMAL POWER PLANT
Ata, İsmail; Tanürün, H. Erdi; Uzun, Sinem; Bayrak, Sebile; Acır, Adem
The exergy analysis and determination of irreversibility İ of a thermal power plant with 210 MW are presented in this study. The first- (ηI) and second-law (ηII) efficiencies, losses, and İ are computed for each component in the plant. The highest energy loss (43.538%) occurs with heat transfer to cooling water of the condenser, whereas the second loss (14.138%) occurs in the boiler. The highest İ value in the cycle (86.87%) occurs in the boiler followed by the turbine (5.95%). The ηI and ηII efficiencies of the whole plant are 38.64% and 31.68%, respectively. In addition, effects of the efficiencies in the temperature range from 5°C to 30°C are investigated. The ηI efficiency of the whole plant does not change, whereas the ηII efficiency decreases with increasing reference temperatures. In addition, the ηII efficiency is associated with environmental impact and sustainability.
RDL Kalıcı Kaydıİncele
ArticleYalnız künye2022/r/ebyu/13815
The hierarchical synthesis of tungsten disulfide coated vertically aligned boron carbon nitride nanotubes composite electrodes for supercapacitors
Yesilbag, Yasar Ozkan; Tuzluca Yesilbag, Fatma Nur; Huseyin, Ahmad; Ertugrul, Mehmet
This study investigated the specific capacitance, energy density and cyclic stability parameters of a WS2 coated vertically aligned BCN nanotubes (VA-BCN-NTs) composite electrode structure. The specific capacitance of VA-BCN-NTs was found to be 364 F g−1 at a current density of 0.5 A g−1. This electrode had 97% of their initial specific capacitance after 10,000 cycles at a current density of 20 A g−1, exhibiting excellent cyclic stability. In the three-electrode cell, the specific capacitance of the VA-BCN-NT@WS2 electrode at a current density of 0.5 A g−1 was calculated to be 690 F g−1. After 5000 cycles at a current density of 20 A g−1, the electrode structure had a capacitance value of 74%, showing good stability. In the two-electrode cell, the specific capacitance of the VA-BCN-NT@WS2 symmetrical supercapacitor at a current density of 1 A g−1 was found to be 170 F g−1. It was observed to have retained 85% of its capacitance after 10,000 cycles over a 1 V potential range. While the energy density of this structure was 23.6 Wh kg−1, the power density was 4250 W kg−1.
RDL Kalıcı Kaydıİncele
ArticleAçık Erişim2022/r/ebyu/13782
Machine Learning-Based Estimation of Output Current Ripple in PFC-IBC Used in Battery Charger of Electrical Vehicles: A Comparison of LR, RF and ANN Techniques
Aslay, Fulya; Ting, Naim Suleyman
In this study, an artificial neural network (ANN) model is developed for the purpose of estimating the output current ripple of a power factor correction (PFC) AC/DC interleaved boost converter (IBC) used in battery charger of electrical vehicles (EVs) based on the inductance current ripple, switching frequency and load changes. Besides, the improved ANN model is compared with some different machine learning (ML) techniques like linear regression (LR), random forest (RF). The PFC-IBC is simulated with the PSIM simulation program to estimate the output current ripple. As a result, 336 output current ripple values are obtained based on inductance current ripple, different switching frequency and load changes. Then, the value of output current ripple is estimated by training the input parameters with LR, RF and ANN machine learning techniques (MLTs) for controlling the current harmonics drawn from the grid and for reliable charging of batteries. It is seen that the estimation value obtained with MLTs is quite compatible with the actual value obtained with the simulation. In addition, in the study carried out with the simulation, it takes a period of several days to obtain the estimation results; whereas, the operation of estimation with MLTs can be completed in a short period such as a few minutes. This clearly reveals the advantage of the MLTs. Therefore, this value is estimated through the MLTs with a high accuracy before the design of the charging device in order to maintain at a secure level the output current ripple posing considerable importance in electrical vehicle battery charge. Also, in this estimation process, LR, RF and developed ANN techniques are examined and compared separately in the WEKA program and it is observed that the developed ANN model proposes better results than other techniques.
RDL Kalıcı Kaydıİncele