Data-Driven Gearbox Fault Severity Diagnosis Based on Concept Drift

Mario Peña; Laura Lanzarini; Mariela Cerrada; Diego Cabrera; René Vinicio Sánchez

doi:10.1109/ETCM53643.2021.9590689

Data-Driven Gearbox Fault Severity Diagnosis Based on Concept Drift

Mario Peña, Laura Lanzarini, Mariela Cerrada, Diego Cabrera, René Vinicio Sánchez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Condition-based maintenance aims to determine the machine state in real time, by monitoring the signals it emits. Such signals are potentially unlimited, generated at a high rate, and can evolve over time. These conditions tend to produce changes in the distribution of the data, known as concept drift. This phenomenon is analyzed and used to establish changes in the state of the machine. The present article proposes a methodological framework for the diagnosis of fault severity based on concept drift. A parsimonious unsupervised algorithm based on KNN is proposed to detect concept evolution. The results show that the algorithm is quite effective in declaring a concept evolution that is associated with a change in the failure condition of the machine. Finally, the results show that there is a high correlation between the displacement of the centroids of the emerging concepts and the % of deterioration of the machine.

Original language	English
Title of host publication	ETCM 2021 - 5th Ecuador Technical Chapters Meeting
Editors	Monica Karel Huerta, Sebastian Quevedo, Carlos Monsalve
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665441414
DOIs	https://doi.org/10.1109/ETCM53643.2021.9590689
State	Published - 12 Oct 2021
Event	5th IEEE Ecuador Technical Chapters Meeting, ETCM 2021 - Cuenca, Ecuador Duration: 12 Oct 2021 → 15 Oct 2021

Publication series

Name	ETCM 2021 - 5th Ecuador Technical Chapters Meeting

Conference

Conference	5th IEEE Ecuador Technical Chapters Meeting, ETCM 2021
Country/Territory	Ecuador
City	Cuenca
Period	12/10/21 → 15/10/21

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This paper is supported by the research group GIDTEC of the Universidad Politécnica Salesiana, sede Cuenca-Ecuador and the LIDI Computer Science Research Institute of the Universidad Nacional de La Plata.

Publisher Copyright:
© 2021 IEEE.

Keywords

Concept drift
concept evolution
fault detection
Jensen-Shannon divergence
Kullback-Leibler divergence

Access to Document

10.1109/ETCM53643.2021.9590689

Cite this

Peña, M., Lanzarini, L., Cerrada, M., Cabrera, D., & Sánchez, R. V. (2021). Data-Driven Gearbox Fault Severity Diagnosis Based on Concept Drift. In M. K. Huerta, S. Quevedo, & C. Monsalve (Eds.), ETCM 2021 - 5th Ecuador Technical Chapters Meeting (ETCM 2021 - 5th Ecuador Technical Chapters Meeting). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ETCM53643.2021.9590689

@inproceedings{0a86f8af9e4647699f8490d4b7aa136d,

title = "Data-Driven Gearbox Fault Severity Diagnosis Based on Concept Drift",

abstract = "Condition-based maintenance aims to determine the machine state in real time, by monitoring the signals it emits. Such signals are potentially unlimited, generated at a high rate, and can evolve over time. These conditions tend to produce changes in the distribution of the data, known as concept drift. This phenomenon is analyzed and used to establish changes in the state of the machine. The present article proposes a methodological framework for the diagnosis of fault severity based on concept drift. A parsimonious unsupervised algorithm based on KNN is proposed to detect concept evolution. The results show that the algorithm is quite effective in declaring a concept evolution that is associated with a change in the failure condition of the machine. Finally, the results show that there is a high correlation between the displacement of the centroids of the emerging concepts and the % of deterioration of the machine.",

keywords = "Concept drift, concept evolution, fault detection, Jensen-Shannon divergence, Kullback-Leibler divergence",

author = "Mario Pe{\~n}a and Laura Lanzarini and Mariela Cerrada and Diego Cabrera and S{\'a}nchez, {Ren{\'e} Vinicio}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 5th IEEE Ecuador Technical Chapters Meeting, ETCM 2021 ; Conference date: 12-10-2021 Through 15-10-2021",

year = "2021",

month = oct,

day = "12",

doi = "10.1109/ETCM53643.2021.9590689",

language = "English",

series = "ETCM 2021 - 5th Ecuador Technical Chapters Meeting",

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

editor = "Huerta, {Monica Karel} and Sebastian Quevedo and Carlos Monsalve",

booktitle = "ETCM 2021 - 5th Ecuador Technical Chapters Meeting",

address = "United States",

}

Peña, M, Lanzarini, L, Cerrada, M , Cabrera, D & Sánchez, RV 2021, Data-Driven Gearbox Fault Severity Diagnosis Based on Concept Drift. in MK Huerta, S Quevedo & C Monsalve (eds), ETCM 2021 - 5th Ecuador Technical Chapters Meeting. ETCM 2021 - 5th Ecuador Technical Chapters Meeting, Institute of Electrical and Electronics Engineers Inc., 5th IEEE Ecuador Technical Chapters Meeting, ETCM 2021, Cuenca, Ecuador, 12/10/21. https://doi.org/10.1109/ETCM53643.2021.9590689

Data-Driven Gearbox Fault Severity Diagnosis Based on Concept Drift. / Peña, Mario; Lanzarini, Laura; Cerrada, Mariela et al.
ETCM 2021 - 5th Ecuador Technical Chapters Meeting. ed. / Monica Karel Huerta; Sebastian Quevedo; Carlos Monsalve. Institute of Electrical and Electronics Engineers Inc., 2021. (ETCM 2021 - 5th Ecuador Technical Chapters Meeting).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Data-Driven Gearbox Fault Severity Diagnosis Based on Concept Drift

AU - Peña, Mario

AU - Lanzarini, Laura

AU - Cerrada, Mariela

AU - Cabrera, Diego

AU - Sánchez, René Vinicio

PY - 2021/10/12

Y1 - 2021/10/12

N2 - Condition-based maintenance aims to determine the machine state in real time, by monitoring the signals it emits. Such signals are potentially unlimited, generated at a high rate, and can evolve over time. These conditions tend to produce changes in the distribution of the data, known as concept drift. This phenomenon is analyzed and used to establish changes in the state of the machine. The present article proposes a methodological framework for the diagnosis of fault severity based on concept drift. A parsimonious unsupervised algorithm based on KNN is proposed to detect concept evolution. The results show that the algorithm is quite effective in declaring a concept evolution that is associated with a change in the failure condition of the machine. Finally, the results show that there is a high correlation between the displacement of the centroids of the emerging concepts and the % of deterioration of the machine.

AB - Condition-based maintenance aims to determine the machine state in real time, by monitoring the signals it emits. Such signals are potentially unlimited, generated at a high rate, and can evolve over time. These conditions tend to produce changes in the distribution of the data, known as concept drift. This phenomenon is analyzed and used to establish changes in the state of the machine. The present article proposes a methodological framework for the diagnosis of fault severity based on concept drift. A parsimonious unsupervised algorithm based on KNN is proposed to detect concept evolution. The results show that the algorithm is quite effective in declaring a concept evolution that is associated with a change in the failure condition of the machine. Finally, the results show that there is a high correlation between the displacement of the centroids of the emerging concepts and the % of deterioration of the machine.

KW - Concept drift

KW - concept evolution

KW - fault detection

KW - Jensen-Shannon divergence

KW - Kullback-Leibler divergence

UR - http://www.scopus.com/inward/record.url?scp=85119452884&partnerID=8YFLogxK

U2 - 10.1109/ETCM53643.2021.9590689

DO - 10.1109/ETCM53643.2021.9590689

M3 - Conference contribution

AN - SCOPUS:85119452884

T3 - ETCM 2021 - 5th Ecuador Technical Chapters Meeting

BT - ETCM 2021 - 5th Ecuador Technical Chapters Meeting

A2 - Huerta, Monica Karel

A2 - Quevedo, Sebastian

A2 - Monsalve, Carlos

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th IEEE Ecuador Technical Chapters Meeting, ETCM 2021

Y2 - 12 October 2021 through 15 October 2021

ER -

Peña M, Lanzarini L, Cerrada M , Cabrera D , Sánchez RV. Data-Driven Gearbox Fault Severity Diagnosis Based on Concept Drift. In Huerta MK, Quevedo S, Monsalve C, editors, ETCM 2021 - 5th Ecuador Technical Chapters Meeting. Institute of Electrical and Electronics Engineers Inc. 2021. (ETCM 2021 - 5th Ecuador Technical Chapters Meeting). doi: 10.1109/ETCM53643.2021.9590689

Data-Driven Gearbox Fault Severity Diagnosis Based on Concept Drift

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this