Open AccessRecognition of track defects through measured acceleration - part 1
Author(s) -
Sebastian Bahamon-Blanco,
Sebastian Rapp,
Chad T. Rupp,
J Liu,
Ullrich Martin
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/615/1/012121
Subject(s) - train , acceleration , track (disk drive) , computer science , waveform , signal (programming language) , scale (ratio) , artificial intelligence , axle , real time computing , pattern recognition (psychology) , engineering , telecommunications , structural engineering , radar , physics , cartography , classical mechanics , quantum mechanics , programming language , geography , operating system
For an optimized maintenance strategy, the early detection of track defects is necessary. Mounted sensors (e.g. acceleration sensors) on in-service trains are very suitable for track monitoring. With the continuous measurement of axle-box acceleration, short wavelength defects can be identified. For example, these defects can be rail breaks or cracks (i.e. rail defects), or local instabilities. Local instabilities can reduce the track quality in a short period of time. For an efficient data analysis of the acceleration signal and classification of different track defects, the development of appropriate methods is necessary. Therefore, a track-vehicle scale model was built to generate acceleration data used to detect typical types of failures. With the generated acceleration data, developed algorithms for pattern recognition can be easily tested. In the first part of this research, the vertical acceleration signals generated by the rail defects and local instabilities are collected, analysed, classified and prepared for being used in a model that can automatically identify these failures. The data is collected in a track-vehicle scale model, and after data analysis, the characteristics of the waveforms associated with each failure are examined using cross correlation. Every failure is classified both manually as well as automatically, and statistical features of the waveforms are extracted to create a database that is used to train a model using supervised learning. This model is described in the second part of the research.