Yazar "Dikmen, İsmail Can" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim
    Öğe
    Efficiency Analysis of Various Batteries with Real-time Data on a Hybrid Electric Vehicle
    (2021) Ekici, Yunus Emre; Dikmen, İsmail Can; Nurmuhammed, Mustafa; Karadağ,Teoman
    Battery selection remains an up-to-date engineering problem for hybrid and electric vehicle manufacturers. Type of battery and its capacity will depend on the trip and vehicle parameters. An electric vehicle produced with the ideal bat-tery type will undoubtedly be preferred by customers. Data collected from black boxes of trolleybuses operated by Malatya Metropolitan Municipality were used in this study. The real road and driver characteristics were included in the study with the experimentally obtained data. These data are the accelerator pedal data obtained from vehicles driven by different drivers in regular and congested traf-fic hours. In this study, four different battery chemistries were run separately on a hybrid vehicle model and analyzed. Chosen battery chemistries are the most commonly used by manufacturers. These are Lead Acid, Nickel Cadmium, Nickel Metal Hydride and Lithium Iron Phosphate batteries. The results of the study are presented in detail comparatively. Among the battery chemistries, Lithium iron phosphate is observed to be the most ideal battery type for hybrid electric vehi-cles.
  • Küçük Resim Yok
    Öğe
    Efficient State of Health Estimation for LTO Batteries Using Liquid Time-Constant Neural Networks
    (Springer Science and Business Media Deutschland GmbH, 2025) Dikmen, İsmail Can; Yildiran, Nisanur; Karadağ, Teoman
    In this paper, we present a novel approach for State of Health (SoH) estimation in Lithium Titanate Oxide (LTO) batteries using Liquid Time-Constant Neural Networks (LTCNNs). The LTCNN model is designed to capture complex temporal dynamics in capacity fading. We demonstrated LTCNN’s superior accuracy with a Root Mean Squared Error (RMSE) 0.01 on both training and test datasets. This high accuracy and the model’s low computational cost position LTCNN networks as a powerful real-time battery health monitoring tool. Our study highlights the LTCNN model’s compact architecture with a computational depth of 46 operations. Additionally, with only 131 parameters and an inference time of 0.51 s, while requiring 0.12 MB of memory allocation, LTCNNs achieve an efficient performance. These characteristics enable the LTCNN algorithm to be implemented on onboard chips such as Battery Management Systems (BMS). This feature allows continuous and real-time SoH estimation without needing high-powered computational resources. The results demonstrate that LTCNN neural networks offer a scalable and cost-effective solution for enhancing BMS performance in electric vehicles and other applications where LTO batteries are used. This paper contributes to the growing body of research on neural network-based SoH estimation, providing a practical framework for implementing LTCNN models in real-world systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
  • Küçük Resim
    Öğe
    Elektrikli araçlar için akıllı batarya yönetim sisteminin tasarımı ve uygulaması
    (İnönü Üniversitesi, 2022) Dikmen, İsmail Can
    Doktora tez çalışmasında, farklı kimyalara sahip bataryaların üstün özelliklerinin bir arada kullanılarak, elektrikli araçlar için batarya kimyasını tanıyıp, uygun yönetim parametrelerini otomatik olarak uygulayabilen akıllı bir batarya yönetim sisteminin özgün donanım ve yazılım tasarımı, geliştirilmesi ayrıca prototip üretimleri yapılmıştır. Literatürde elektrikli araçlarda kullanılan pillerin kimyaları incelendiğinde; bunların nikel kadmiyum (NiCd), nikel-metal hidrit (NiMH), lityum nikel kobalt alüminyum oksit (NCA), lityum demir fosfat (LFP), lityum titanyum oksit (LTO) ve lityum sülfür (LiS) olduğu tespit edilmiştir. Bu nedenle pil kimyasını belirleme algoritması, üretilen elektronik devre kartlarının donanım parametreleri ve yazılımlar bu pil kimyaları temel alınarak geliştirilmiştir. Batarya kimyasının elektronik olarak belirlenebilmesi için, istatistiksel analiz temelli bir yaklaşım izlenerek geliştirilen algoritma sayesinde, beş farklı batarya kimyasının birkaç saniye içerisinde %100 doğrulukla belirlenmesi sağlanmıştır. Bataryanın kimyasını tespit edebilen donanım ve yazılım aynı zamanda uygun yönetim parametrelerini otomatik olarak ayarlayabilmekte; bu sayede çoklu kimyalı batarya yönetimini desteklemektedir. Farklı batarya kimyalarının üstün özelliklerinin bir arada kullanımına olanak veren bir yapıya sahip olmasının yanı sıra, bu özelliklerden en uygun anda faydalanabilmek için tasarlanan bir anahtarlama mekanizmasının etkinliği de yapılan simülasyon çalışması ile ortaya koyulmuştur. Tüm bu özellikler, geliştirilen özgün yazılımı ve donanımı sayesinde kullanıcı dostu dokunmatik bir ekran üzerinden kontrol edilebilmektedir. Çalışma üç aşamada icra edilmiştir. Birinci aşama TÜBİTAK 1512 programı çerçevesinde desteklenmiş, donanım ve yazılımın birinci sürümleri geliştirilmiştir. İkinci aşamada İnönü Üniversitesi BAP Birimi tarafından Öncelikli Alan projesi kapsamında desteklenmiş, donanım ve yazılımın ikinci sürümleri geliştirilmiştir. Üçüncü aşamada ise yine BAP Doktora Tez projesi kapsamında desteklenmiş, donanım ve yazılımın üçüncü ve son sürümleri geliştirilmiştir. Geliştirilen batarya yönetim sistemi, literatürde yer alan diğer batarya yönetim sistemleri ile fonksiyon temelli olarak karşılaştırmalı sunulmuştur.
  • Küçük Resim Yok
    Öğe
    Machine Learning Approaches for Enhancing the SoH Estimation of LTO Batteries
    (Society of Automotive Engineers Turkey, 2025) Dikmen, İsmail Can; Yıldıran, Nisanur; Karadağ, Teoman
    Lithium titanate oxide (LTO) batteries' practical application in modem technologies depends on accurately predicting their state of health (SoH). Using advanced machine learning (ML) techniques, our study examined how to estimate LTO batteries' SoH. For this purpose, we aged rechargeable LTO batteries for 3500 cycles with a battery analyzer and performed differential voltage analysis (DVA). To estimate SoH as a regression problem, we used three machine learning methods: Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Gaussian Process Regressions (GPR). As a novel approach to SoH estimation, our research uses a feedforward neural network to solve the categorization problem. In analyzing and comparing the performance of all methods, we found that this categorization-based neural network approach improved computational efficiency by 60.89% while achieving SoH estimation accuracy of 93.18%. By advancing the field of battery health monitoring, these findings contribute to more reliable and efficient battery management algorithms. In addition to improving battery management systems' accuracy and computational efficiency, the categorization approach demonstrated here could also be used to extend the life and reliability of LTO batteries, including those used in electric vehicles and renewable energy storage systems. The results of this study illustrate the importance of applying innovative machine learning applications to enhance battery SoH estimations, providing important implications for future research and practice. © 2025 Society of Automotive Engineers Turkey. All rights reserved.
  • Küçük Resim
    Öğe
    A Review on Electric Vehicle Charging Systems and Current Status in Turkey
    (2021) Karadağ, Teoman; Nurmuhammed, Mustafa; Ekici, Yunus Emre; Dikmen, İsmail Can
    The reality of global warming brings along an increase in environmental aware-ness. In recent years, this awareness has shifted public focus on electric vehicles. For a large group of people greenhouse gas emission is attributed to internal combustion engines. However, some challenges have arisen for electric vehicles. Limited range due to immature battery technologies and insufficient fast charging technologies that do not meet end user expectations are some major obstacles to overcome. Eventual-ly this situation negatively affects the sales and the wide use of electric vehicles. That is the reason why studies on wired and wireless charging systems play an important role in improving the sales performance of electric vehicles. In this study a thorough review of worldwide electric vehicle charging systems is conducted and discussed in the framework of the electric vehicles, charging stations, installations, and implemen-tation of standards in Turkey. The distribution of charging stations in Turkey are analyzed with respect to location, region, type, infrastructure requirements and future projections. The historical development of charging technologies, modes and charge levels have been studied in detail. As highlight of this study, wireless charging tech-nologies were also discussed and the historical development process was analyzed along with related standards. The current state of electric vehicle sector and charging stations in Turkey are discussed and provided with up to date information.