An analysis method for correlation between catenary irregularities and pantograph-catenary contact force

Abstract

Pantograph-catenary contact force provides the main basis for evaluation of current quality collection; however, the pantograph-catenary contact force is largely affected by the catenary irregularities. To analyze the correlated relationship between catenary irregularities and pantograph-catenary contact force, a method based on nonlinear auto-regressive with exogenous input (NARX) neural networks was developed. First, to collect the test data of catenary irregularities and contact force, the pantograph/catenary dynamics model was established and dynamic simulation was conducted using MATLAB/Simulink. Second, catenary irregularities were used as the input to NARX neural network and the contact force was determined as output of the NARX neural network, in which the neural network was trained by an improved training mechanism based on the regularization algorithm. The simulation results show that the testing error and correlation coefficient are 0.1100 and 0.8029, respectively, and the prediction accuracy is satisfactory. And the comparisons with other algorithms indicate the validity and superiority of the proposed approach.

Keywords

catenary irregularities / pantograph-catenary contact force / NARX neural networks / correlation analysis

References

[1] FacchinettiA, BruniS. Hardware-in-the-loop hybrid simulation of pantograph-catenary interaction [J]. Journal of Sound and Vibration, 2012, 331(12): 2783-2797

[2] ZhangW-h, ShenZ-y, ZengJing. Study on dynamics of coupled systems in high-speed trains [J]. Vehicle System Dynamics, 2013, 51(7): 966-1016

[3] LeeK, ChungJ. Dynamic analysis of a hanger-supported beam with a moving oscillator [J]. Journal of Sound and Vibration, 2013, 332(13): 3177-3189

[4] ZhouN, ZhangW-h, LiR-ping. Dynamic performance of a pantograph-catenary system with the consideration of the appearance characteristics of contact surfaces [J]. Journal of Zhejiang University: Science A, 2011, 12(12): 913-920

[5] HanZ-x, WangG-liang. Unevenness analysis of overhead rigid suspension catenary [J]. Journal of Railway Engineering Society, 200761-64

[6] NagasakaS, AboshiM. Measurement and estimation of contact wire unevenness [J]. Quarterly Report of RTRI, 2004, 45(2): 86-91

[7] TakemuraT, FujiiY, ShimizuM. Characteristics of over-head rigid conductor line having T-type cross section [J]. Developments in Mass Transit Systems, 1998173-177

[8] UsudaTThe pantograph contact force measurement method in overhead catenary system [EC/OL], 2011

[9] UsudaT. Prediction of contact wire on high-speed railways [J]. Railway Technology Avalanche, 2011214

[10] UsudaT. Estimation of wear and strain of contact wire using contact force of pantograph [J]. Quarterly Report of RTRI, 2007, 48(3): 170-175

[11] BennetJ, MontesinosJ, CuarteroF, RojoT, AriasE. Advanced algorithm to calculate mechanical forces on a catenary [J]. Computers in Railways IX, 2004857-868

[12] ZhangW-h, MeiG-m, ChenL-qi. Analysis of the influence of catenary’s sag and irregularity upon the quality of current-feeding [J]. Journal of the China Railway Society, 2000, 22(60): 50-54

[13] CollinaA, LoC A, CarnevaleM. Effect of collector deformable modes in pantograph-catenary dynamic interaction [J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2009, 223(1): 1-14

[14] SahooH K, DashP K, RathN P. NARX model based nonlinear dynamic system identification using low complexity neural networks and robust H-infinity filter [J]. Applied Soft Computing, 2013, 13(7): 3324-3334

[15] LiuZ-g, HanZ-wei. Power spectrum research of catenary irregularities of electrified railway [J]. Electric Railway, 20111-3

[16] GuoJ-boStability of current collection and control for high-speed locomotive [D], 2006, Beijing, Beijing Jiaotong University

[17] ChoY H, LeeK, KangB, KimK N. Influence of contact wire pre-sag on the dynamics of pantograph-railway catenary [J]. International Journal of Mechanical Sciences, 2010, 52(11): 1471-1490

[18] TerzicE, NagarajahC R, AlamgirM. Capacitive sensor-based fluid level measurement in a dynamic environment using neural network [J]. Engineering Applications of Artificial Intelligence, 2010, 23(4): 614-619

[19] LiuY-q, MaG-f, ShiZhong. NARX network for dynamic system identification in adaptive inverse control [J]. Journal of Harbin Institute of Technology, 2005, 37(2): 173-176

[20] SumitG, GyanendraK G. Time-delay simulated artificial neural network models for predicting shelf life of processed cheese [J]. International Journal of Intelligent Systems and Applications, 2012, 4(5): 30-37

[21] OkutH, GianolaD, RosaG J M, KentA W. Prediction of body mass index in mice using dense molecular markers and a regularized neural network [J]. Genetics Research, 2011, 93(3): 189-201

[22] HirschenK, SchaferM. Bayesian regularization neural networks for optimizing fluid flow processes [J]. Computer Methods in Applied Mechanics and Engineering, 2006, 195(7/8): 481-500