Generating accuracy and integrity aware train movement maps using GNSS and MEMS sensors

Colceriu, Vlad; Ștefănuț, Teodor; Bacu, Victor; Gorgan, Dorian

doi:10.1109/iccp.2015.7312699

Cited by 5 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, some defined points on the digital map can be assumed as virtual balises ; that is, a point specified in the digital track map whose real position is known (Acharya, Sadhu, & Ghoshal, ; J. Liu, Cai, & Wang, ). Filtering models are commonly used for data fusion; a filtering model is able to consider a series of measurements of variables, each with some random noise, and estimate the most likely true value for each variable (Colceriu, Ştefǎnut, Bâcu, & Gorgan, ; Heirich, Lehner, Robertson, & Strang, ). In Europe, current railway applications are developed within the general framework for the use of positioning systems, for example, GNSS‐enhanced odometry (GNSS‐EO) (Georgy, Noureldin, Korenberg, & Bayoumi, ; González, Prado, Antón, & Kennes, ).…”

Section: Literature Review On Gnss In Railwaysmentioning

confidence: 99%

Filtering approaches for online train motion estimation with onboard power measurements

Sessa

Martinis

Corman

2019

Computer aided Civil Eng

View full text Add to dashboard Cite

Future railway systems will need the support of more precise and reliable information on train motion during operation, to fully exploit the potential of new technologies. Train motion information are here intended as time series of train state characteristics, that is, position, speed, and acceleration. This paper investigates the use of two different filtering formulations for better online estimations of train state along the track. Specifically, extended Kalman filters (EKFs) and particle filters (PFs) are used to fuse kinematic measurements collected by means of Global Navigation Satellite Systems (GNSSs) with information collected by the trains on the used tractive power. The EKFs need linearity assumptions and are based on statistical evaluations of the train state, the PFs are instead conceived for nonlinear models and they are based on probability functions related to train state measurements and estimates. A set of experiments with real data of trains operating on a Swiss line is presented to analyze the capabilities of these two filters when applied to rail operation in non‐urban environments. We discuss the extent by which the proposed filtering approaches match the latest technical requirements for implementation. We expect such an enhanced train motion estimation to enable reliable and continuous positioning, available at train level and at the traffic control center, while trackside equipment will be gradually reduced.

show abstract

Section: Literature Review On Gnss In Railwaysmentioning

confidence: 99%

Filtering approaches for online train motion estimation with onboard power measurements

Sessa

Martinis

Corman

2019

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…Hence a crowd sourced approach is being used. A satellite image-based approach is used for representation and a parallel image processing algorithm is applied to the resulting data [11]. A sensor fault detection observer is designed to generate fault detection residual.…”

Section: Measurement Science and Technologymentioning

confidence: 99%

A new methodology for optimal rail track condition measurement using acceleration signals

Chellaswamy¹,

Muthammal

Geetha³

2018

Meas. Sci. Technol.

View full text Add to dashboard Cite

This paper describes the possibility of estimating the health of a rail track in order to improve the comfort and ride quality of rail transportation by using the measured acceleration signal. The irregularities present in the track are the primary causes of vibration and these should be identified and the faults rectified to increase the safety of train travel. In this paper, a differential evolution technique based track measurement system (DE-TMS) is proposed to measure the health of the track. The abnormality of the track has been measured using micro electro mechanical system (MEMS) accelerometers which are mounted in the axle box. A new sensing method is used to estimate the exact location of the irregularity even when the signal is absent. The DE-TMS is simulated and compared with two other optimization techniques such as the particle swarm optimization technique and the covariance matrix adaptation with evolutionary strategy to evaluate the performance. The comparison results from the investigation show that the proposed DE-TMS provides cost-effective maintenance, and increase the safety of rail transportation. Finally, an experimental study was performed in four different irregularity cases and the results are estimated.

show abstract

“…Out of these, of interest are two solutions, mainly TrainGuard [25] and Satloc [4], both of which approach localization by using high-end EGNOS (European Geostationary Navigation Overlay System) receivers to improve the accuracy of the GPS, by removing atmospheric effects on the signal. Although not enough to offer the desired safety levels, these applications take another route to assuring safety, by modeling ahead of time the worst-case scenario for satellite constellations and by assuring that no obstructions may exist Before delving into the localization issues and signal filtering approaches it is worthwhile briefly discussing another concept presented in a previous work of the authors [11]: a novel conceptual methodology of obtaining a track description by using only MEMS sensors, such as accelerometer and gyroscope. These are used to create representations of the track environment by mapping their signal values to their along track location.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, all time intervals for which train speed has fallen below 2 m/s, have been cut out of the signal. More about the reasoning for keeping a minimal speed of transformation is explained in [10] and [11].…”

Section: Signal Shift Adjustmentmentioning

confidence: 99%

“…In paper [11] we proposed an algorithm to collect gyroscopic and acceleration data from multiple devices placed in the same rail cart, across multiple journeys on the same line, in order to generate a uniform representation of the track at a given point. In some respects, the mentioned algorithm has succeeded in generating a visually appealing result, which may be used in line annotation for the benefit of human users, but not for an algorithm hoping to recognize the signal over multiple journeys and generate a unique representation.…”

Section: Max-av Localization Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Annotation and Position Recall from Low Grade Sensorial Data in the Context of Topological Railway Maps

Colceriu¹,

Stefanut²,

Bacu³

et al. 2017

STUD INFORM CONTROL

Self Cite

View full text Add to dashboard Cite

Describing high quality track maps is an important prerequisite for the localization algorithms, which depend on relatively unreliable and unsafe triangulation technologies, such as the Global Navigation Satellite System solutions available on modern mobile devices. The state of the art studies and experiments concerning the maps annotation methodologies have been focused on using large quantities of crowdsourcing sensorial data and open source topological maps. The objective is to produce a low-cost platform for regional railway operators, to visualize the track's geometry and to generate a track representation, which can be then recalled across multiple journeys. The paper aims to develop and experiment with a sensorial signature representation toward providing a flexible solution for signal alignment based on Genetic Algorithms. The alignment solution intends to describe the sensorial signals of the track line in a relevant manner that makes localization algorithms possible based on the nonlinear state estimation.

show abstract

Generating accuracy and integrity aware train movement maps using GNSS and MEMS sensors

Cited by 5 publications

References 13 publications

Filtering approaches for online train motion estimation with onboard power measurements

Filtering approaches for online train motion estimation with onboard power measurements

A new methodology for optimal rail track condition measurement using acceleration signals

Annotation and Position Recall from Low Grade Sensorial Data in the Context of Topological Railway Maps

Contact Info

Product

Resources

About