Determination of Minimum Vehicle Operating Voltage in a Metro Line with 1500 V DC Supply Based on Performance Data

Abstract

In DC railways, the traction power supply voltage provided by the electrification system gives the power it needs. Energy is aimed to be of high quality while providing this power. The vehicle’s performance is influenced when the voltage supplied for the vehicle performance is in certain limits. This value is affected by voltage drop on the line. In this study, the determination of the minimum vehicle voltage in a railway line with 1500 V DC supply in relation to the vehicle performance data was investigated. .The artificial intelligence methods adaptive neuro-fuzzy inference system (ANFIS) and support vector machines (SVM) were applied. The performance data of Sultangazi-Arnavutkoy metro line were used in the study. Ideal results were obtained with the calculations.

Keywords

• ANFIS,electrification,metro,SVM,traction

1500 V DC Beslemeli Bir Metro Hattında Minimum Araç İşletme Geriliminin Performans Verilerine Bağlı Olarak Belirlenmesi

Abstract

DC beslemeli metro hatlarında elektrifikasyon sistemi tarafından sağlanan cer gücü besleme gerilimi vasıtasıyla aracın ihtiyacı olan güç sağlanmaktadır. Güç temini sağlanırken enerjinin kaliteli olması hedeflenir. Hat için sağlanan gerilimin belirli sınırlar dahilinde olması aracın performansını etkilemektedir. Hatta oluşan gerilim düşümüne bağlı olarak bu değer etkilenmektedir. Bu çalışmada 1500 V DC beslemeli bir metro hattında minimum araç geriliminin araç performans verilerine bağlı olarak belirlenmesi incelenmiştir. Çalışma için yapay zeka tekniklerinden olan Uyarlamalı Sinirsel Bulanık Çıkarım Sistemi (ANFIS) ve Destek Vektör Makinaları (SVM) yöntemleri tercih edilmiştir.  Çalışma için Sultangazi-Arnavutköy hattına ait bir grup performans verisi kullanılmıştır. Yapılan hesaplamalarla ideal sonuçlar elde edilmiştir.

Keywords

• ANFIS,cer,elektrifikasyon,metro,SVM

References

1. Ghassemi A, Fazel SS, Maghsoud I, Farshad S. (2014). Comprehensive study on the power rating of a railway power conditioner using thyristor switched capacitor. IET Electrical Systems in Transportation, 4, 97-106.
2. Raimondo G, Ladoux P, Lowinsky A, Caron H, Marino P. (2012). Reactive power compensation in railways based on AC boost choppers. IET Electrical Systems in Transportation, 2, 169-177.
3. Aodsup K, Kulworawanichpong T. (2012). Effect of train headway on voltage collapses in high-speed AC railways. In: APPEEC 2012 Power and Energy Engineering Conference; 27-29 March, Shanghai, China, New York, USA, IEEE, 1-4.
4. Abrahamsson L, Kjellqvist T, Ostlund S. (2012). High-voltage DC-feeder solution for electric railways. IET Power Electronics, 5, 1776 - 1784.
5. Goodman CJ, Chymera M. (2013). Modelling and simulation. In: REIS Railway Electrification Infrastructure and Systems Conference; 3-6 June, London, England. New York, USA: IEEE, 16-25.
6. Ladoux P, Raimondo G, Caron H, Marino P. (2013). Chopper-Controlled steinmetz circuit for voltage balancing in railway substations. IEEE Transactions on Power Electronics, 28, 5813-5822.
7. Shin HS, Cho SM, Huh JS, Kim, JC, Kweon, DJ. (2012). Application on of SFCL in automatic power changeover switch system of electric railways. IEEE Transactions on Applied Superconductivity, 22, 5600704.
8. Ozkan IA, Saritas I, Herdem S. (2007). Modeling of magnetic filtering with ANFIS. In: 12. National Conference on Electrical Electronic Computer Biomedical Engineering; 14-18 November, Eskisehir, Turkey. Ankara, Turkey: CEE, 415-418.

9. Sit S, Ozcalik HR, Kilic E, Dogmus O, Altun M. (2016). Investigation of performance based on online adaptive neuro-fuzzy ınference system (ANFIS) for speed control of ınduction motors. Cukurova University Journal of the Faculty of Engineering and Architecture, 31, 33-42.
10. Jang, JSR. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics ,23, 665–685.
11. Ayhan, S., Erdogmus, S. (2014). Kernel function selection for the solution of classification problems via support vector machines, Eskisehir Osmangazi University Journal Of IIBF, 9, 175-198.
12. Yakut, E., Elmas, B., Yavuz, S. (2014). Predictıng stock-exchange index using methods of neural networks and support vector machines, Suleyman Demirel University The Journal Of Faculty Of Economics And Administrative Sciences, 19, 139-157.
13. Kavzaoglu, T., Colkesen, I. (2010). Investigation of the effects of kernel functions in satellite image classification using support vector machines, Gebze High Technology Institute The Journal of Map, 144, 73-82.
14. Guran, A., Uysal, M., Dogrusoz, O. (2014). Effects of support vector machines parameter optimization on sentiment analysis, DEU Engineering Faculty The Journal Of Engineering Sciences, 16, 86-93.