TY - CONF
T1 - Accelerometer Placement Comparison for Crack Detection in Railway Axles Using Vibration Signals and Machine Learning
AU - Lucero, Pablo
AU - Sánchez, Réne Vinicio
AU - MacAncela, Jean Carlo
AU - Cabrera, Diego
AU - Cerrada, Mariela
AU - Li, Chuan
AU - Alonso, Higinio Rubio
PY - 2019/7/12
Y1 - 2019/7/12
N2 - In this paper, a methodology for accelerometer placement comparison for crack detection in railway axles, using vibration signals and machine learning, was shown. Different vibration signals from six accelerometers were obtained by several conditions of load and speed, with crack depths in axles from 5.7 to 15 mm. This paper describes three stages: acquisition, processing, and analysis. The findings suggest that using the vertical or longitudinal accelerometer located in left allow obtaining higher accuracy than 90% with three features, also called condition indicators. On the other hand, an accuracy such as 96.43% is obtained using a left vertical sensor and 95,98% using a left longitudinal sensor, both with ten features. With this methodology, high accuracy in crack detection was obtained using an accelerometer effective placement. Different vibration signals using six accelerometers were obtained, under several conditions of load and speed, with crack depths in axles from 5.7 to 15 mm.
AB - In this paper, a methodology for accelerometer placement comparison for crack detection in railway axles, using vibration signals and machine learning, was shown. Different vibration signals from six accelerometers were obtained by several conditions of load and speed, with crack depths in axles from 5.7 to 15 mm. This paper describes three stages: acquisition, processing, and analysis. The findings suggest that using the vertical or longitudinal accelerometer located in left allow obtaining higher accuracy than 90% with three features, also called condition indicators. On the other hand, an accuracy such as 96.43% is obtained using a left vertical sensor and 95,98% using a left longitudinal sensor, both with ten features. With this methodology, high accuracy in crack detection was obtained using an accelerometer effective placement. Different vibration signals using six accelerometers were obtained, under several conditions of load and speed, with crack depths in axles from 5.7 to 15 mm.
KW - crack detection
KW - feature selection
KW - machine learning
KW - railway
KW - vibration signal
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85070514712&origin=inward
UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85070514712&origin=inward
UR - http://www.mendeley.com/research/accelerometer-placement-comparison-crack-detection-railway-axles-using-vibration-signals-machine-lea
U2 - 10.1109/PHM-Paris.2019.00056
DO - 10.1109/PHM-Paris.2019.00056
M3 - Capítulo
SP - 291
EP - 296
T2 - Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019
Y2 - 1 May 2019
ER -