Accelerometer Placement Comparison for Crack Detection in Railway Axles Using Vibration Signals and Machine Learning

Pablo Lucero; Réne Vinicio Sánchez; Jean Carlo MacAncela; Diego Cabrera; Mariela Cerrada; Chuan Li; Higinio Rubio Alonso

doi:10.1109/PHM-Paris.2019.00056

Accelerometer Placement Comparison for Crack Detection in Railway Axles Using Vibration Signals and Machine Learning

Pablo Lucero
, Réne Vinicio Sánchez
, Jean Carlo MacAncela
, Diego Cabrera
, Mariela Cerrada
, Chuan Li
, Higinio Rubio Alonso

Grupo de Investigación y Desarrollo en Tecnologías Industriales (GIDTEC)

Research output: Capítulo

Abstract

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.

Original language	English
Pages	291-296
Number of pages	6
DOIs	https://doi.org/10.1109/PHM-Paris.2019.00056
Publication status	Published - 12 Jul 2019
Event	Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019 - Duration: 1 May 2019 → …

Conference

Conference	Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019
Period	1/05/19 → …

Areas de Conocimiento del CACES

827A Mantenimiento industrial

Access to Document

10.1109/PHM-Paris.2019.00056

Cite this

@conference{18f1b3c1b88b4b83a92d548cf0100b22,

title = "Accelerometer Placement Comparison for Crack Detection in Railway Axles Using Vibration Signals and Machine Learning",

abstract = "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.",

keywords = "crack detection, feature selection, machine learning, railway, vibration signal",

author = "Pablo Lucero and S{\'a}nchez, \{R{\'e}ne Vinicio\} and MacAncela, \{Jean Carlo\} and Diego Cabrera and Mariela Cerrada and Chuan Li and Alonso, \{Higinio Rubio\}",

year = "2019",

month = jul,

day = "12",

doi = "10.1109/PHM-Paris.2019.00056",

language = "English",

pages = "291--296",

note = "Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019 ; Conference date: 01-05-2019",

}

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 -

Accelerometer Placement Comparison for Crack Detection in Railway Axles Using Vibration Signals and Machine Learning

Abstract

Conference

Areas de Conocimiento del CACES

Access to Document

Other files and links

Fingerprint

Monitoreo Inteligente de la Condición de Maquinaria Rotativa Mediante la Fusión de Señales de Audio, Emisión Acústica, Vibración y Corriente

Cite this

Accelerometer Placement Comparison for Crack Detection in Railway Axles Using Vibration Signals and Machine Learning

Abstract

Conference

Areas de Conocimiento del CACES

Access to Document

Other files and links

Fingerprint

Projects

Monitoreo Inteligente de la Condición de Maquinaria Rotativa Mediante la Fusión de Señales de Audio, Emisión Acústica, Vibración y Corriente

Cite this