Ağır Vasıta Fren Sistemlerinde Kullanılan Acil Durum Valf Dinamiğinin Deneysel Olarak Araştırılması ve YSA Tabanlı Modellenmesi

Öz

Acil durum valfinin, ağır vasıta araçlarında römorkların manuel veya yarı otomatik şekilde ani frenleme yapabilmesi amacıyla kullanılan pnömatik bir fren valfi olması sebebiyle, dinamik performansı ve tepki süresi kritik öneme sahiptir. Bu çalışma kapsamında, öncelikle konu ile ilgili literatürdeki örnek çalışmalar ve kapsamlı endüstriyel uygulamalar detaylı bir şekilde incelenmiş ve frenleme süresine etki etmesi beklenen parametreler araştırılmıştır. Sistemin giriş parametreleri olarak emniyet yay katsayısı, çek valf yay katsayısı ve hortum çapı belirlenmiş, deneysel tasarım yöntemleri kullanılarak, sistem parametrelerinin frenleme tepki süresi üzerindeki etkisi incelenmiş ve tam faktöriyel bir deney tasarım oluşturulmuştur. Sistemin frenleme tepki süresini ölçmek amacıyla bir deney düzeneğini oluşturulmuş ve kapsamlı deneysel çalışmalar yürütülmüştür. Elde edilen deneysel verilerin regresyon analizi ile fren tepki süresine ait bir matematiksel model elde edilmiştir. Sistemin modelleme performansını geliştirmek amacıyla, deneysel verilerin yapay sinir ağı tabanlı modellenmesine yönelik çalışmalar yapılmıştır. Deneysel veri setinin farklı nöron sayıları, öğrenme algoritmaları ve eğitim-test-doğrulama yüzdeleri belirlenerek eğitilmesine yönelik modelleme çalışmaları gerçekleştirilmiş, daha az hata değerine sahip daha yüksek doğrulukta bir model araştırılmıştır. Elde edilen matematiksel ve yapay sinir ağı modellerinin, giriş parametrelerine bağlı olarak valf tepki süresini modelleme ve tahminleme performansları karşılaştırmalı olarak incelenmiş ve sayısal sonuçlar sunulmuştur. Yapılan deneysel ve modelleme çalışmaları, YSA modelinin matematiksel modele göre daha başarılı tahmin performansı sağlayabileceğini göstermiştir.

Anahtar Kelimeler

• Acil Durum Valfi
• Frenleme Tepki Süresi
• Havalı Fren Sistemi
• Matematiksel Modelleme
• Yapay Sinir Ağı

Experimental Investigation and ANN-Based Modelling of an Emergency Valve Dynamics Used in Heavy Vehicle Brake Systems

Abstract

Since the emergency valve is a pneumatic brake valve used in heavy vehicles to perform sudden braking of trailers manually or semi-automatically, its dynamic performance and response time are of critical importance. In this study, relevant literature and comprehensive industrial applications were thoroughly reviewed, and the parameters which are expected to affect the braking time were investigated. The safety spring coefficient, check valve spring coefficient, and hose diameter were determined as system input parameters. Using experimental design methods, the effects of system parameters on braking response time were investigated, and a full factorial experimental design was developed. An experimental setup was created to measure the braking response time of the system, and comprehensive experimental studies were conducted. A mathematical model of the braking response time was derived through regression analysis of the obtained experimental data. To improve the system's modelling performance, studies were performed on the artificial neural network-based modelling of the experimental data. Modelling studies were carried out to train the experimental data set by determining different neuron numbers, learning algorithms, and training-test-validation percentages, and a higher accuracy model with fewer error values was investigated. The performance of the obtained mathematical and artificial neural network models in predicting the valve response time depending on the input parameters was comparatively examined, and numerical results were presented. The experimental and modelling studies have shown that the ANN model can provide more successful prediction performance compared to the mathematical model.

Keywords

• Emergency Valve
• Braking Response Time
• Air Brake System
• Mathematical Modelling
• Artificial Neural Network

Kaynakça

1. [1] Bosch R. Automotive brake systems. Warrendale, PA: Society of Automotive Engineers (SAE), 1995.
2. [2] Limpert R. Brake design and safety. 3rd ed. Warrendale, PA: SAE International, 2011.
3. [3] Lindemann K, Petersen E, Schult M, Korn A. EBS and tractor trailer brake compatibility. SAE Transactions. 1997; 106: 684–692.
4. [4] Bowlin, C.L., Subramanian, S. C., Darbha, S., and Rajagopal, K.R. Pressure control scheme for air brakes in commercial vehicles. In IEE Proceedings-Intelligent Transport Systems, 2006; 153:1, 21-32.
5. [5] Ramarathnam, S., Dhar, S., Darbha, S., and Rajagopal, K.R. Development of a model for an air brake system with leaks and a scheme for the estimation of the steady-state pushrod stroke. Vehicle system Dynamics. 2011; 49(8): 1267-1282.
6. [6] Miller, J.I., Henderson, L.M. and Cebon, D. Designing and testing an advanced pneumatic braking system for heavy vehicles, Proceedings of the Institution of Mechanical Engineers, Part C: J. of Mech. Engineering science. 2013; 227(8): 1715-1729.
7. [7] Andrew, J.D., and Bryant, D. Braking of Road Vehicles, Butterworth-Heinemann is an imprint of Elsevier, Waltham, MA 02451, USA. 2014; 1-548.
8. [8] Selvaraj, M., Gaikwad, S., and Suresh, A.K. Modeling and simulation of dynamic behavior of pneumatic brake system at vehicle level, SAE, Technical Paper, 2014.

9. [9] Güleryüz, İ.C. and Başer, Ö. Computer aided calculation and experimental verification of response time of pneumatic brake system for 4x4 heavy duty vehicles, Pamukkale University Journal of Engineering Sciences. 2018; 24(8): 1409-1417.
10. [10] Özçelik, A., and Örs, İ. Four Way Safety Valve Tester Design for Heavy Vehicle Brake Systems, Int. Journal of Automotive Science and Technology. 2020; 4(3): 125-131.
11. [11] Raveendran, R., Suresh, A., Rajaram, V., and Subramanian, S. C. Artificial neural network approach for air brake pushrod stroke prediction in heavy commercial road vehicles, Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. 2019; 233(10): 2467-2478.
12. [12] Lopes, P.F. Neural network modelling of automatic brake systems for heavy haul railway vehicles, Master Thesis, Universidade Estadual De Campinas Faculdade de Engenharia Mecanica, Campinas, 2020,127-170.
13. [13] Soudagar, I.A.K., and Tota, P.D. (2022). Modelling and simulation of electro-pneumatic parking brake system for real time estimation of pressure inside parking brake chamber, (Master Thesis, Chalmers University of Technology, Sweden, 2022, 8-20.
14. [14] Gül, E. and Kalyoncu, M. Ağır Vasıta Hava Kompresörü Arıza Durumlarının Naive Bayes Sınıflandırıcısı Kullanılarak Analizi. Avrupa Bilim ve Teknoloji Dergisi. 2021; (31): 796-800.
15. [15] Çetin, İ., Ağır vasıta fren sistemlerinde kullanılan acil durum valfinin deneysel incelenmesi ve yapay sinir ağı ile modellenmesi, Yüksek Lisans Tezi, Konya Teknik Üniversitesi, Lisansüstü Eğitim Enstitüsü, Konya, 2025, 14-51.
16. [16] Vaden Co., Brake System, Park Release Emergency Valve Products, Access address:https://www.vaden.com.tr/en/products/303160006-park-release-emergency-valve-brake-system (Accessed in: 10.09.2025)
17. [17] Jankovic, A., Chaudhary, G., and Goia, F. Designing the design of experiments (DOE)–An investigation on the influence of different factorial designs on the characterization of complex systems. Energy and Buildings, 2021;250(111298):1-17.
18. [18] Öztemel, E. Yapay Sinir Ağları, 1.Baskı, Papatya yayıncılık, İstanbul, 2003.
19. [19] Jia, Z, and Lucien K. A Hybrid Approach Using Design of Experiment and Artificial Neural Network in a Camless Heavy-Duty Engine, Journal of Energy Resources Technology 2022;144(12):1-12.
20. [20] Cao, M. Applications of artificial neural networks on ground vehicle systems-modeling and diagnostics: A literature survey, ASME International Mechanical Engineering Congress and Exposition, 2008;48784:407-425.
21. [21] Katreddi, S., Sujan K., and Arvind T. A review of applications of artificial intelligence in heavy duty trucks, Energies, 2022;15(20):1-20.
22. [22] Bilgiç, H. H., and İlker M. Comparison of different techniques for estimation of incoming longwave radiation, International Journal of Environmental Science and Technology. 2021; 18(3): 601-618.
23. [23] Seidi, E., Farnaz K., and Scott F. M. Hyperparameter tuning of artificial neural network-based machine learning to optimize number of hidden layers and neurons in metal forming, Journal of Manufacturing and Materials Processing, 2025; 9(8):260.
24. [24] Öter, A. Automatic Detection of Epileptic Seizures from EEG Signals Using Artificial Intelligence Methods, Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, 2024;12(1):257-266.
25. [25] Ertürk, S., Kara, H., Akkuş, C., Genç, G. Türkiye’de Farklı İklim Kuşakları İçin Yapay Sinir Ağları Kullanılarak Güneş Işınımının Tahmini, Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, 2023;11(4):885-892.
26. [26] Uzun, S. and Arslantaş, H. Determination of Solar Radiation Value by Month Using Artificial Neural Network Model; Ankara, Sivas, Erzurum example, Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, 2024; 12(1):315-323.