Poincaré plot features from vibration signal for gearbox fault diagnosis

Ruben Medina; Ximena Alvarez; Diana Jadan; Mariela Cerrada; Rene Vinicio Sanchez; Jean Carlo Macancela

doi:10.1109/ETCM.2017.8247500

Poincaré plot features from vibration signal for gearbox fault diagnosis

Ruben Medina, Ximena Alvarez, Diana Jadan, Mariela Cerrada, Rene Vinicio Sanchez, Jean Carlo Macancela

Research and Development Group in Industrial Technologies (GIDTEC)

Research output: Contribution to conference › Paper

Abstract

This paper describes a method for fault diagnosis in gearboxes using features extracted from the Poincare plot of the vibration signal. Several features describing the geometrical shape of the Poincare plot are calculated and three of these features are selected for performing the classification of 10 types of faults recorded in the gearbox vibration signal dataset. A multi-class Error-Correcting Output Code Support Vector Machine is trained for performing the classification of faults. The cross-validation performed show that the highest accuracy attained is 95.3% when signals recorded using the load L1 are considered.

Original language	English
Pages	1-6
Number of pages	6
DOIs	https://doi.org/10.1109/ETCM.2017.8247500
State	Published - 4 Jan 2018
Event	2017 IEEE 2nd Ecuador Technical Chapters Meeting, ETCM 2017 - Salinas, Ecuador Duration: 16 Oct 2017 → 20 Oct 2017

Conference

Conference	2017 IEEE 2nd Ecuador Technical Chapters Meeting, ETCM 2017
Abbreviated title	ETCM 2017
Country/Territory	Ecuador
City	Salinas
Period	16/10/17 → 20/10/17

Keywords

Gearbox faults classification
Multi-class Support Vector Machines
Poincare plots
Rotatory machines

Access to Document

10.1109/ETCM.2017.8247500

Cite this

@conference{bbf8bd15603a42068bb1805e22ae25a4,

title = "Poincar{\'e} plot features from vibration signal for gearbox fault diagnosis",

abstract = "This paper describes a method for fault diagnosis in gearboxes using features extracted from the Poincare plot of the vibration signal. Several features describing the geometrical shape of the Poincare plot are calculated and three of these features are selected for performing the classification of 10 types of faults recorded in the gearbox vibration signal dataset. A multi-class Error-Correcting Output Code Support Vector Machine is trained for performing the classification of faults. The cross-validation performed show that the highest accuracy attained is 95.3% when signals recorded using the load L1 are considered.",

keywords = "Gearbox faults classification, Multi-class Support Vector Machines, Poincare plots, Rotatory machines",

author = "Ruben Medina and Ximena Alvarez and Diana Jadan and Mariela Cerrada and Sanchez, {Rene Vinicio} and Macancela, {Jean Carlo}",

year = "2018",

month = jan,

day = "4",

doi = "10.1109/ETCM.2017.8247500",

language = "English",

pages = "1--6",

note = "2017 IEEE Second Ecuador Technical Chapters Meeting (ETCM 2017)<br/> ; Conference date: 16-10-2017 Through 20-10-2017",

}

TY - CONF

T1 - Poincaré plot features from vibration signal for gearbox fault diagnosis

AU - Medina, Ruben

AU - Alvarez, Ximena

AU - Jadan, Diana

AU - Cerrada, Mariela

AU - Sanchez, Rene Vinicio

AU - Macancela, Jean Carlo

PY - 2018/1/4

Y1 - 2018/1/4

N2 - This paper describes a method for fault diagnosis in gearboxes using features extracted from the Poincare plot of the vibration signal. Several features describing the geometrical shape of the Poincare plot are calculated and three of these features are selected for performing the classification of 10 types of faults recorded in the gearbox vibration signal dataset. A multi-class Error-Correcting Output Code Support Vector Machine is trained for performing the classification of faults. The cross-validation performed show that the highest accuracy attained is 95.3% when signals recorded using the load L1 are considered.

AB - This paper describes a method for fault diagnosis in gearboxes using features extracted from the Poincare plot of the vibration signal. Several features describing the geometrical shape of the Poincare plot are calculated and three of these features are selected for performing the classification of 10 types of faults recorded in the gearbox vibration signal dataset. A multi-class Error-Correcting Output Code Support Vector Machine is trained for performing the classification of faults. The cross-validation performed show that the highest accuracy attained is 95.3% when signals recorded using the load L1 are considered.

KW - Gearbox faults classification

KW - Multi-class Support Vector Machines

KW - Poincare plots

KW - Rotatory machines

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85045739957&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85045739957&origin=inward

UR - http://www.mendeley.com/research/poincar%C3%A9-plot-features-vibration-signal-gearbox-fault-diagnosis

U2 - 10.1109/ETCM.2017.8247500

DO - 10.1109/ETCM.2017.8247500

M3 - Paper

SP - 1

EP - 6

T2 - 2017 IEEE Second Ecuador Technical Chapters Meeting (ETCM 2017)<br/>

Y2 - 16 October 2017 through 20 October 2017

ER -

Poincaré plot features from vibration signal for gearbox fault diagnosis

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this