Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads

Rene Vinicio Sanchez; Pablo Lucero; Jean Carlo Macancela; Mariela Cerrada; Diego Cabrera; Rafael Vasquez

doi:10.1109/SDPC.2018.8664979

Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads

Rene Vinicio Sanchez
, Pablo Lucero
, Jean Carlo Macancela
, Mariela Cerrada
, Diego Cabrera
, Rafael Vasquez

Research output: Chapter in Book/Conference proceeding › Conference and proceedings › peer-review

8 Scopus citations

Abstract

Diagnosing failures during their initial stage is important to avoid unexpected stops and catastrophic damages, specially for gear boxes that are crucial components in industrial machines. This work addresses the classification of nine levels of crack failure severity in a gearbox. First of all, features are extracted in time domain from signals coming from an acoustic emission (AE) sensor, and then selected by using four different ranking methods. The classification stage uses the k-Nearest Neighbors (KNN) technique. The results indicate that presented levels of severity can be successfully classified with five features extracted from the AE signal for the four ranking methods.

Original language	English
Title of host publication	Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018
Editors	Chuan Li, Dian Wang, Diego Cabrera, Yong Zhou, Chunlin Zhang
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	465-470
Number of pages	6
ISBN (Electronic)	9781538660577
DOIs	https://doi.org/10.1109/SDPC.2018.8664979
State	Published - 2 Jul 2018
Event	2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018 - Xi'an, China Duration: 15 Aug 2018 → 17 Aug 2018

Publication series

Name	Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018

Conference

Conference	2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018
Country/Territory	China
City	Xi'an
Period	15/08/18 → 17/08/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Keywords

Acoustic emission
K-nearest neighbors
fault diagnosis
feature time-domain
gear crack

Types Minciencias

Scientific events with a public engagement component

Access to Document

10.1109/SDPC.2018.8664979

Cite this

Sanchez, R. V., Lucero, P., Macancela, J. C., Cerrada, M., Cabrera, D., & Vasquez, R. (2018). Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads. In C. Li, D. Wang, D. Cabrera, Y. Zhou, & C. Zhang (Eds.), Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018 (pp. 465-470). Article 8664979 (Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SDPC.2018.8664979

Sanchez, Rene Vinicio ; Lucero, Pablo ; Macancela, Jean Carlo et al. / Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads. Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018. editor / Chuan Li ; Dian Wang ; Diego Cabrera ; Yong Zhou ; Chunlin Zhang. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 465-470 (Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018).

@inproceedings{58507fc6366e4d06bb1683177e384bba,

title = "Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads",

abstract = "Diagnosing failures during their initial stage is important to avoid unexpected stops and catastrophic damages, specially for gear boxes that are crucial components in industrial machines. This work addresses the classification of nine levels of crack failure severity in a gearbox. First of all, features are extracted in time domain from signals coming from an acoustic emission (AE) sensor, and then selected by using four different ranking methods. The classification stage uses the k-Nearest Neighbors (KNN) technique. The results indicate that presented levels of severity can be successfully classified with five features extracted from the AE signal for the four ranking methods.",

keywords = "Acoustic emission, K-nearest neighbors, fault diagnosis, feature time-domain, gear crack",

author = "Sanchez, \{Rene Vinicio\} and Pablo Lucero and Macancela, \{Jean Carlo\} and Mariela Cerrada and Diego Cabrera and Rafael Vasquez",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018 ; Conference date: 15-08-2018 Through 17-08-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/SDPC.2018.8664979",

language = "Ingl{\'e}s",

series = "Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "465--470",

editor = "Chuan Li and Dian Wang and Diego Cabrera and Yong Zhou and Chunlin Zhang",

booktitle = "Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018",

}

Sanchez, RV, Lucero, P, Macancela, JC, Cerrada, M, Cabrera, D & Vasquez, R 2018, Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads. in C Li, D Wang, D Cabrera, Y Zhou & C Zhang (eds), Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018., 8664979, Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018, Institute of Electrical and Electronics Engineers Inc., pp. 465-470, 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018, Xi'an, China, 15/08/18. https://doi.org/10.1109/SDPC.2018.8664979

Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads. / Sanchez, Rene Vinicio; Lucero, Pablo; Macancela, Jean Carlo et al.
Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018. ed. / Chuan Li; Dian Wang; Diego Cabrera; Yong Zhou; Chunlin Zhang. Institute of Electrical and Electronics Engineers Inc., 2018. p. 465-470 8664979 (Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018).

Research output: Chapter in Book/Conference proceeding › Conference and proceedings › peer-review

TY - GEN

T1 - Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads

AU - Sanchez, Rene Vinicio

AU - Lucero, Pablo

AU - Macancela, Jean Carlo

AU - Cerrada, Mariela

AU - Cabrera, Diego

AU - Vasquez, Rafael

PY - 2018/7/2

Y1 - 2018/7/2

N2 - Diagnosing failures during their initial stage is important to avoid unexpected stops and catastrophic damages, specially for gear boxes that are crucial components in industrial machines. This work addresses the classification of nine levels of crack failure severity in a gearbox. First of all, features are extracted in time domain from signals coming from an acoustic emission (AE) sensor, and then selected by using four different ranking methods. The classification stage uses the k-Nearest Neighbors (KNN) technique. The results indicate that presented levels of severity can be successfully classified with five features extracted from the AE signal for the four ranking methods.

AB - Diagnosing failures during their initial stage is important to avoid unexpected stops and catastrophic damages, specially for gear boxes that are crucial components in industrial machines. This work addresses the classification of nine levels of crack failure severity in a gearbox. First of all, features are extracted in time domain from signals coming from an acoustic emission (AE) sensor, and then selected by using four different ranking methods. The classification stage uses the k-Nearest Neighbors (KNN) technique. The results indicate that presented levels of severity can be successfully classified with five features extracted from the AE signal for the four ranking methods.

KW - Acoustic emission

KW - K-nearest neighbors

KW - fault diagnosis

KW - feature time-domain

KW - gear crack

UR - https://www.scopus.com/pages/publications/85064119794

U2 - 10.1109/SDPC.2018.8664979

DO - 10.1109/SDPC.2018.8664979

M3 - Ponencia publicada en las memorias del evento con ISBN

AN - SCOPUS:85064119794

T3 - Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018

SP - 465

EP - 470

BT - Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018

A2 - Li, Chuan

A2 - Wang, Dian

A2 - Cabrera, Diego

A2 - Zhou, Yong

A2 - Zhang, Chunlin

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018

Y2 - 15 August 2018 through 17 August 2018

ER -

Sanchez RV, Lucero P, Macancela JC, Cerrada M, Cabrera D, Vasquez R. Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads. In Li C, Wang D, Cabrera D, Zhou Y, Zhang C, editors, Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 465-470. 8664979. (Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018). doi: 10.1109/SDPC.2018.8664979

Gear Crack Level Classification by Using KNN and Time-Domain Features from Acoustic Emission Signals under Different Motor Speeds and Loads

Abstract

Publication series

Conference

Bibliographical note

Keywords

Types Minciencias

Access to Document

Fingerprint

Cite this