Relating track geometry to vehicle performance using neural network approach

Abstract

As part of a research that led to the development of the performance-based track geometry (PBTG) inspection technology, the Transportation Technology Center, Inc., Pueblo, CO, USA, a wholly owned subsidiary of the Association of American Railroads, has developed a technique relating track geometry to vehicle performance, real-time. This technique is based on the neural network (NN) approach, an emerging powerful tool in recognizing complex patterns and non-linear relationships between many inputs and an output, such as the relationship between track geometry and vehicle response. On the basis of this technique, many NNs have been developed (trained) from actual vehicle/track interaction test results. For a given vehicle type, the trained NNs directly relate three-dimensional track geometry and vehicle operating speed to vehicle performance. The effects of other track conditions such as lubrication, rail profile, and track stiffness are indirectly considered on the basis of their statistical distributions from test results. Because the PBTG inspection is intended to optimize the track geometry maintenance, the vehicle types selected for testing to date were the ones most sensitive to track geometry (in North America, these are the tank car, covered hopper car, and coal gondola car). However, more NNs for other vehicle types can be easily trained on the basis of the NN technique developed using actual vehicle performance and track geometry test results.

Road and track irregularities: measurement, assessment and simulation

“…A similar approach has been developed by the Transportation Technology Center, Inc. (TTCI). [121,122] It is called 'performance-based track geometry' (PBTG) and uses the NN technique to relate real-time track irregularities to vehicle response. Neural networks are composed of simple elements operating in parallel.…”

“…As in nature, the connections between elements largely determine the network function. Figure 22 shows a simplified NN architecture used in [122]. The input variables include curvature, super-elevation and cross level, vertical and lateral irregularity of rails, gauge and speed.…”

Describing and assessing track geometry quality

“…[19,20] It is based on the neural network (NN) approach, an emerging powerful tool in recognising complex patterns and non-linear relationships between many inputs and an output, such as the relationship between track geometry and vehicle response. Many NNs have been Downloaded by [Umeå University Library] at 09:56 01 April 2015 developed (trained) from actual vehicle-track interaction test results.…”

A finite element approach to develop track geometrical irregularity thresholds from the safety aspect

“…Others studied the effect of track geometrical irregularities on the performance and conditional assessment of the track, such as initiation and evolution of rail corrugation (Jin et al, 2005), effects of maintenance operations on track quality (Ataei et al, 2014), proposing an inspection interval for track geometrical parameters (Arasteh Khouy et al, 2013), and evaluating the probability of derailment (Mohammadzadeh et al, 2011). Also, there are emerging technologies such as the performance-based track geometry inspection system that relate geometrical parameters of track to vehicle performance in real time (Li et al, 2006). In a recent study by Arasteh Khouy et al (2014) a cost model is proposed to specify the cost-effective maintenance limits for track geometry maintenance.…”