Yazar "Karadag, Teoman" seçeneğine göre listele
Listeleniyor 1 - 11 / 11
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Effect of outside temperature on energy consumption of electric vehicles: Real-time big data and artificial intelligence-aided seahorse optimization approach(Gazi Univ, Fac Engineering Architecture, 2025) Ekici, Yunus Emre; Karadag, Teoman; Akdag, Ozan; Aydin, Ahmet ArifIn calculating the energy consumption of electric vehicles (EVs); it is very important to optimize the consumption efficiency and driving range by considering the outdoor temperature. Studies have shown that very low and very high temperatures reduce engine efficiency and significantly increase energy consumption, while affecting regenerative energy recovery. Therefore, in the presented study, the effects of outdoor temperature on range and energy consumption were investigated using real-time big data obtained from Electric Buses (EO). The field application of the study was carried out with 22 24.7-meter EOs. The EO route was divided into 4 different regions and the energy consumption for each region and the analysis of the outdoor temperature corresponding to this consumption were obtained using regression techniques. First, the energy consumption model was created and the driving cycle was calculated for each region. Then, the driving cycle for the entire route was created and the energy consumption on the route was expressed as a mathematical model. Trilayered Neural Network (TNN) gave the best result in the calculations of the entire route. Finally, the mathematical model obtained as a result of TNN was reconsidered using the SeaHorse optimization method. Considering the analysis for the entire route (R), it was calculated that the most efficient consumption is 3.02 kWh/km and this consumption value can be achieved with a temperature of 21.5oC. This study has become a reference study for other electric vehicle manufacturers in determining the range of their vehicles in different climate conditions.Öğe Energy consumption model with real-time data for driving range extension of electric buses(Elsevier, 2025) Ekici, Yunus Emre; Aydin, Ahmet Arif; Karadag, Teoman; Akdag, Ozan; Ates, AbdullahPreventing range anxiety in electric vehicles (EVs) requires efficient energy use and an accurate estimation of the battery capacity needed for the desired range. A longer range leads to reduced consumption and extends operational activities. Thus, extended driving range can be achieved, promoting a more environmentally sustainable transportation model. This contributes significantly to reducing greenhouse gas emissions and mitigating the environmental impact of transportation. In this study, 250,000 rows of real-world data were collected from electric Trolleybus vehicles for a realistic energy consumption estimation of EVs. First, a mathematical model was obtained from these data using Gaussian Process Regression (GPR) method. To reduce the error rate of this model and increase the accuracy of consumption estimation, it was necessary to re-analyze it with an optimization technique. The accuracy of the consumption prediction model is extremely important for increasing the range of EVs and enabling uninterrupted travels. To solve range anxiety problem, the mathematical model obtained by GPR method is re-optimized by SeaHorse optimization and a new energy consumption prediction model, SHO-EBECM (Seahorse Optimized-Electric Bus Energy Consumption Model), is obtained. The trained SHO-EBECM was applied to 20 real routes of public transportation with internal combustion engine buses in a metropolitan city and the RMSE (Root Mean Square Error) value has been calculated to be between 0.1470 and 0.2920. Based on the achieved error rate, it can be inferred that SHO-EBECM offers a solution with a reduced error rate in comparison to four other optimization techniques. Furthermore, considering global warming, carbon emissions and ecological balance, it is concluded that approximately 12,060 tons/year of CO2, 372.75 tons/ year of NO and NO2 gases can be prevented from being emitted to nature by converting internal combustion engine buses on 20 different routes to electric buses (E-Bus) with the help of SHO-EBECM.Öğe Enhancing electric vehicle range through real-time failure prediction and optimization: Introduction to DHBA-FPM model with an artificial intelligence approach(Elsevier, 2025) Ekici, Yunus Emre; Karadag, Teoman; Akdag, Ozan; Aydin, Ahmet Arif; Tekin, Hueseyin OzanElectrical and mechanical failures in electric vehicles (EVs) during passenger operation cause significant operational losses and elevated energy consumption, amplifying range anxiety. To address this issue, we utilized 250,000 rows of real-time data from electric trolleybuses operating in T & uuml;rkiye to develop a robust artificial intelligence (AI)-based optimization model for failure mitigation. Initially, Tri layered Neural Network (TNN) was employed to create a predictive function for electrical and mechanical failures, followed by comparative analyses across six optimization algorithms widely adopted in failure prediction studies. Among these, the Developed Honey Badger Algorithm with AI Approach (DHBA) emerged as the most effective, achieving a predictive accuracy improvement of 15 % over the standard Honey Badger Algorithm (HBA). The DHBA incorporates a Dynamic Fitness-Distance Balance (DFDB) mechanism and a novel spiral motion feature to enhance search precision, leading to the DHBA-FPM (Developed-Honey Badger Algorithm - Failure Prediction Model). The final DHBA-FPM model was applied to the 10 highest-density bus routes in T & uuml;rkiye to predict and optimize failures. Results indicate that applying the DHBA-FPM model across these routes yielded a 3.96 % average range increase in EVs, extending the total range by approximately 79,200 km annually. It can be concluded that the model could prevent the release of 238.7 tons/year of CO2, NO, and NO2 emissions through its potential to improve both the operational efficiency and sustainability of EVs in public transit networks.Öğe Impact of Outside Temperature on Driving Range and Energy Consumption Using Real-Time Big Data for Electric Buses(Institute of Electrical and Electronics Engineers Inc., 2024) Ekici, Yunus Emre; Karadag, Teoman; Aydin, Ahmet Arif; Akdag, OzanCalculating the energy consumption of electric vehicles (EVs) is crucial to optimize efficiency and driving range, taking into account the outdoor temperature. Research shows that low temperatures significantly increase motor and battery energy consumption while inhibiting regenerative energy recovery, with optimum efficiency achieved at around 20-30 degrees Celsius. Furthermore, the use of heating and cooling systems in different seasons also affects the overall efficiency by affecting battery energy consumption. Therefore, outdoor temperature and driving conditions must be taken into account to accurately assess and optimize the energy consumption of EVs. In this study, the effects of outdoor temperature on range and energy consumption are analyzed using real-time big data from Electric Buses (EB). The field application of the study is based on the EB route currently in operation in Malatya. The EB route is divided into 4 different regions and the energy consumption and the corresponding outdoor temperature for each region are analyzed using regression analysis techniques. As a result of the calculations, it was calculated that the most efficient consumption for the entire EB route is 3,02 kWh / km and this consumption value can be achieved with a temperature of 21,5° C. © 2024 IEEE.Öğe Measurement-based assessment and optimization of electric bus energy consumption under thermal variability using long-term field data(Elsevier Sci Ltd, 2026) Ekici, Yunus Emre; Karadag, Teoman; Akdag, Ozan; Aydin, Ahmet Arif; Tekin, Huseyin OzanThis study investigates the effect of ambient temperature on the energy consumption of overhead battery-hybrid electric buses, also known as trolleybuses. The analysis uses real field data. The data were collected from 22 hybrid buses over 24 months. Each bus was monitored during daily passenger service. The onboard black-box units recorded the main operating signals at 1 Hz. This allowed second-by-second changes in speed, braking, passenger load, and energy use to be examined under real route conditions. The study is not based on standard driving cycles or simulation data. It uses measured data from daily bus operation. The dataset includes energy consumption, regenerative braking, vehicle speed, passenger load, road gradient, auxiliary power demand, and ambient temperature. Before the analysis, missing, corrupted, and inconsistent records were removed. This step was used to improve the reliability of the measurement dataset. In this study, outside temperature is not treated as a direct electric motor parameter. It is considered a factor that affects total energy use through battery behavior and heating, ventilation, and air conditioning demand. Different prediction methods were tested on the processed data. These methods include Decision Trees, Ensemble Learning, Gaussian Process Regression, Support Vector Machines, and Three-Layer Neural Networks. The Three-Layer Neural Network optimized with the Modified Tunicate Swarm Algorithm achieved the best predictive performance. According to the analysis results, the model aimed to provide a practical basis for seasonal energy forecasting and route-based fleet planning by evaluating the sensitivity of energy consumption over a wide temperature range.Öğe Modified Archimedes optimization algorithm for global optimization problems: a comparative study(Springer London Ltd, 2024) Nurmuhammed, Mustafa; Akdag, Ozan; Karadag, TeomanArchimedes Optimization Algorithm (AOA) is a recent optimization algorithm inspired by Archimedes' Principle. In this study, a Modified Archimedes Optimization Algorithm (MDAOA) is proposed. The goal of the modification is to avoid early convergence and improve balance between exploration and exploitation. Modification is implemented by a two phase mechanism: optimizing the candidate positions of objects using the dimension learning-based (DL) strategy and recalculating predetermined five parameters used in the original AOA. DL strategy along with problem specific parameters lead to improvements in the balance between exploration and exploitation. The performance of the proposed MDAOA algorithm is tested on 13 standard benchmark functions, 29 CEC 2017 benchmark functions, optimal placement of electric vehicle charging stations (EVCSs) on the IEEE-33 distribution system, and five real-life engineering problems. In addition, results of the proposed modified algorithm are compared with modern and competitive algorithms such as Honey Badger Algorithm, Sine Cosine Algorithm, Butterfly Optimization Algorithm, Particle Swarm Optimization Butterfly Optimization Algorithm, Golden Jackal Optimization, Whale Optimization Algorithm, Ant Lion Optimizer, Salp Swarm Algorithm, and Atomic Orbital Search. Experimental results suggest that MDAOA outperforms other algorithms in the majority of the cases with consistently low standard deviation values. MDAOA returned best results in all of 13 standard benchmarks, 26 of 29 CEC 2017 benchmarks (89.65%), optimal placement of EVCSs problem and all of five real-life engineering problems. Overall success rate is 45 out of 48 problems (93.75%). Results are statistically analyzed by Friedman test with Wilcoxon rank-sum as post hoc test for pairwise comparisons.Öğe Multi-factor optimization for electric bus charging stations: Integrating electrical, social, and environmental perspectives(Elsevier, 2025) Nurmuhammed, Mustafa; Akdag, Ozan; Karadag, Teoman; Kafafy, MagedIn this study, a method that provides the optimal placement of Charging Stations (CSs) for Electric Buses (EBs) on the distribution network considering electrical, social, and environmental aspects is proposed. The parameters used in the study are power loss, voltage deviation, voltage stability index, population density, traffic density, proximity to points of interest and location cost. The energy consumption of the EBs is calculated by linear modeling method using ten parameters. To test the applicability and effectiveness of the proposed method, IEEE33 and IEEE-69 bus systems are modified in accordance with EBs, and the distances between the stops are set as routes. Afterwards, CS placement is performed for different scenarios and power effects are shown. The power loss is decreased by 17.34 % in the 33-bus and 8.75 % in the 69-bus test systems. Accordingly, 106 and 25 kgs of CO2 per hour can be prevented, respectively. In summary, this study provides a method that comprehensively evaluates both electrical and social-environmental factors for the optimal placement of CSs for EBs. Additionally, the practical applications of the proposed method offer valuable data for reducing power loss and CO2 emissons, thus providing important insights for sustainable urban transportation solutions. The findings of the study can form the basis for future research on optimizing EV charging infrastructure (based on both social/environmental and electrical data) and guide policymakers and urban planners in developing more efficient and sustainable transportation networks.Öğe Optimization of Propo rtion al-In tegra l-Der ivati ve Parameters for Speed Control of Squirrel-Cage Motors with Seahorse Optimization(2024) ekici, emre; akdag, ozan; Aydin, Ahmet Arif; Karadag, TeomanThe two different motion behaviors of seahorses in nature served as inspiration for the seahorse optimization (SHO) method, which is a new metaheuristic swarm intelligence-based approach to solving fundamental engineering problems. In this study, the propo rtion al-in tegra l-der ivati ve (PID) parameters for the simplified speed control of the manipulator joint using squirrel-cage induction motors were calculated with the SHO algorithm. As a result of these calculations, Kp, Ki, and Kd values were obtained as 0.0430, 0.00474, and 0.03254, respectively. Then, the time for the squirrel-cage motor to reach 50 rpm (revolutions per minute) and 90 rpm was calculated with the help of SHO. In PID + SHO operation, the squirrel-cage electric motor reached 50 rpm in 3 seconds and 90 rpm in 8 seconds. In this study, in which the SHO optimization method was used, it was calculated that the acceleration of the squirrel-cage motor and reaching the desired value gave 50% better results compared to the particle swarm optimization algorithm.Öğe Redefining urban mobility: Real-world regenerative braking optimization via bio-inspired AI for electric buses energy efficiency(Pergamon-Elsevier Science Ltd, 2025) Ekici, Yunus Emre; Karadag, Teoman; Akdag, OzanIn the era of global decarbonization and sustainable urban mobility, optimizing energy recovery in electric public transport systems has become a strategic imperative. This study presents a comprehensive and data-driven investigation into the optimization of regenerative braking (RB) performance in hybrid electric trolleybuses operating in T & uuml;rkiye. Unlike conventional research relying on controlled driving cycles or laboratory simulations, this work employs real-world operational data totaling over 79 million records collected over five years to construct a high-fidelity predictive model. Using a novel meta-heuristic algorithm inspired by the physiological mechanism of water uptake and transport in plants (WUTP), eight critical parameters influencing RB power including vehicle speed, gradient, acceleration, passenger mass, ambient temperature, and auxiliary system loads were integrated into a robust mathematical framework. The resulting model, WUTP-EBREM, accurately predicts regenerative braking power under varying operational conditions, achieving a minimal error rate (RMSE: 0.12 %). This enables a fine-grained understanding of how instantaneous operating dynamics affect energy recovery in electric buses. Subsequently, the model was applied to 50 of the city's busiest bus routes, each with distinct topographical and operational characteristics. Route-based analyses revealed substantial variability in RB potential, highlighting that optimal energy recovery depends not only on vehicle design but also on contextual factors such as slope patterns and thermal loads. The findings offer direct implications for fleet energy planning, battery sizing, and route optimization, providing actionable insights for transit operators and electric vehicle manufacturers alike. Beyond its empirical contributions, this research introduces a scalable modeling architecture adaptable to various geographic regions and climate conditions, bridging the gap between theoretical energy models and field-level implementation. By capturing the stochastic, non-linear nature of urban electric bus operation, the study sets a precedent for integrating artificial intelligence into real-time transport energy optimization. The WUTP-EBREM model stands as a unique decision-support tool for smart transportation planning, offering both academic value and immediate practical utility. This work is poised to inform future studies in energy-aware vehicle control systems, sustainable transit infrastructure, and intelligent fleet management strategies in electrified urban environments.Öğe Tailoring Energy Efficiency for Urban Electric Buses: The GTECM Model for Enhanced Range and Sustainable Operation Using Real-Time Big Data(Ieee-Inst Electrical Electronics Engineers Inc, 2025) Ekici, Yunus Emre; Karadag, Teoman; Akdag, Ozan; Aydin, Ahmet Arif; Tekin, Huseyn OzanThe increasing depletion of fossil fuels and growing environmental concerns are increasing the need for energy efficient and sustainable solutions, particularly in transport. At this point, especially in public transport, electric vehicles (EVs) offer a promising alternative; however, issues such as range anxiety and energy efficiency require comprehensive solutions. This study introduces the Gauss-based Trolleybus Energy Consumption Model (GTECM) for electric buses, harnessing real-time big data to mitigate range anxiety and enhance energy efficiency. This model employs Gaussian Process Regression to a large-scale dataset including 100,000 entries collected over six months in T & uuml;rkiye. With an overall Root Mean Square Error (RMSE) of 0.013905, GTECM substantially outperforms linear approaches across T & uuml;rkiye's primary routes, exhibiting route-specific RMSE values between 0.28117 and 0.30540. Empirical findings suggest potential energy savings of up to 50%, alongside a 10% extension in driving range, thereby mitigating an estimated 4,220 tons of CO2 and 129.88 tons of NO2 emissions annually. Moreover, the projected amortization period for diesel-to-electric bus conversion stands at 6.83 years, underscoring GTECM's pragmatic utility for sustainable urban transit optimization. The findings of the study can form the basis for future research and guide policy makers and urban planners in the development of more efficient and sustainable transport networks.Öğe V2G Uygulamalarında Elektrikli Araçların Dağıtım Şebekesine Optimum Entegrasyonunun Analizi İçin Newton Raphson Temelli Yeni Bir Model(2024) KUZU, Bünyamin; Nurmuhammed, Mustafa; akdag, ozan; Karadag, TeomanSon yıllarda, Elektrikli Araç (EA) üretimi ve kullanımı hızla artmaktadır. EA'lar, yapısı gereği enerji depolama kapasitesine sahip olduklarından, elektrik şebekesi üzerinde yedek güç kaynağı ve yardımcı hizmetler sağlama gibi işlevleri yerine getirebilecekleri fikirleri ortaya çıkmıştır. Bu fikirlerden biri, araçtan şebekeye enerji transferi olan Vehicle-to-Grid (V2G) konseptidir. Bu çalışmada, EA'lara ait şarj istasyonlarının şebekeye optimum şekilde entegrasyonu ve EA'ların V2G konsepti ile şebekeye elektrik enerjisi aktarımının incelenmesi için Newton Raphson temelli yeni bir model önerilmektedir. Önerilen çalışmanın etkinliğinin incelenmesi için öncelikle IEEE 33 bara sistemi DigSilent yazılımı ile modellemiştir. Sonrasında bu çalışmada sunulan yeni model ile güç sisteminde EA şarj istasyonlarının optimum entegrasyonu sağlatılmıştır. Çalışma kapsamında, EA'ların şarj/deşarj durumları simüle edilerek V2G konsepti analiz edilmiştir. Böylece, bu çalışma ile EA'ların hem mevcut şebeke üzerindeki etkileri hem de çevresel etkileri detaylı olarak incelenmiştir. Analiz sonucunda, 156 EA radyal dağıtım şebekesine (optimum) entegre edilmiş ve 10 saatte toplam 4464 kWh elektrik enerjisi şebekeye aktarılarak yaklaşık 1519 kg CO2 salınımı azaltılmıştır. Bu çalışma, V2G konsepti ile elektrik şebekesine pik talep saatlerinde destek olmak, yük dengelenmesi, araçlarda depolanan yenilenebilir enerjinin kullanılabilmesi, sistemdeki darboğazların ve karbon salınımının azaltılması için EA'ların şebeke entegrasyonunu teşvik etmektedir.
