Remaining useful life estimation of ball bearings by means of monotonic score calibration

J. A. Carino; D. Zurita; M. Delgado; J. A. Ortega; R. J. Romero-Troncoso

doi:10.1109/ICIT.2015.7125351

Remaining useful life estimation of ball bearings by means of monotonic score calibration

J. A. Carino
, D. Zurita
, M. Delgado
, J. A. Ortega
, R. J. Romero-Troncoso

Polytechnic University of Catalonia
Universidad de Guanajuato

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

29 Citations (Scopus)

Abstract

The estimation of remaining useful life applied to industrial machinery and its components is one of the current trends in the advanced manufacturing field. In this context, this work presents a reliable methodology applied to ball bearings health monitoring. First, the proposed methodology analyses the available vibration and temperature data by means of the Spearman coefficient. This step allows the identification of the most significant monotonic relationship between features and the evolution of the remaining useful life. The method is complemented by means of the application of one-class support vector machine in order to obtain the remaining useful life indication trough the mapping of the classification scores. The proposed scheme shows a significant accuracy and reliability of the degradation detection due to the coherent management of the information. This fact is experimentally demonstrated by a run-to-failure test bench and the comparison with classical approaches.

Original language	English
Title of host publication	2015 IEEE International Conference on Industrial Technology, ICIT 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1752-1758
Number of pages	7
Edition	June
ISBN (Electronic)	9781479978007
DOIs	https://doi.org/10.1109/ICIT.2015.7125351
Publication status	Published - 16 Jun 2015
Externally published	Yes
Event	2015 IEEE International Conference on Industrial Technology, ICIT 2015 - Seville, Spain Duration: 17 Mar 2015 → 19 Mar 2015

Publication series

Name	Proceedings of the IEEE International Conference on Industrial Technology
Number	June
Volume	2015-June

Conference

Conference	2015 IEEE International Conference on Industrial Technology, ICIT 2015
Country/Territory	Spain
City	Seville
Period	17/03/15 → 19/03/15

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Keywords

Artificial Intelligence
Classification Algorithms
Machine Learning
One Class Support Vector Machines
Remeaning Useful Life

Access to Document

10.1109/ICIT.2015.7125351

Cite this

Carino, J. A., Zurita, D., Delgado, M., Ortega, J. A., & Romero-Troncoso, R. J. (2015). Remaining useful life estimation of ball bearings by means of monotonic score calibration. In 2015 IEEE International Conference on Industrial Technology, ICIT 2015 (June ed., pp. 1752-1758). Article 7125351 (Proceedings of the IEEE International Conference on Industrial Technology; Vol. 2015-June, No. June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIT.2015.7125351

Carino, J. A. ; Zurita, D. ; Delgado, M. et al. / Remaining useful life estimation of ball bearings by means of monotonic score calibration. 2015 IEEE International Conference on Industrial Technology, ICIT 2015. June. ed. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1752-1758 (Proceedings of the IEEE International Conference on Industrial Technology; June).

@inproceedings{eb876d7c18a445c8b65f649489037a0e,

title = "Remaining useful life estimation of ball bearings by means of monotonic score calibration",

abstract = "The estimation of remaining useful life applied to industrial machinery and its components is one of the current trends in the advanced manufacturing field. In this context, this work presents a reliable methodology applied to ball bearings health monitoring. First, the proposed methodology analyses the available vibration and temperature data by means of the Spearman coefficient. This step allows the identification of the most significant monotonic relationship between features and the evolution of the remaining useful life. The method is complemented by means of the application of one-class support vector machine in order to obtain the remaining useful life indication trough the mapping of the classification scores. The proposed scheme shows a significant accuracy and reliability of the degradation detection due to the coherent management of the information. This fact is experimentally demonstrated by a run-to-failure test bench and the comparison with classical approaches.",

keywords = "Artificial Intelligence, Classification Algorithms, Machine Learning, One Class Support Vector Machines, Remeaning Useful Life",

author = "Carino, \{J. A.\} and D. Zurita and M. Delgado and Ortega, \{J. A.\} and Romero-Troncoso, \{R. J.\}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 2015 IEEE International Conference on Industrial Technology, ICIT 2015 ; Conference date: 17-03-2015 Through 19-03-2015",

year = "2015",

month = jun,

day = "16",

doi = "10.1109/ICIT.2015.7125351",

language = "English",

series = "Proceedings of the IEEE International Conference on Industrial Technology",

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

number = "June",

pages = "1752--1758",

booktitle = "2015 IEEE International Conference on Industrial Technology, ICIT 2015",

address = "United States",

edition = "June",

}

Carino, JA, Zurita, D, Delgado, M, Ortega, JA & Romero-Troncoso, RJ 2015, Remaining useful life estimation of ball bearings by means of monotonic score calibration. in 2015 IEEE International Conference on Industrial Technology, ICIT 2015. June edn, 7125351, Proceedings of the IEEE International Conference on Industrial Technology, no. June, vol. 2015-June, Institute of Electrical and Electronics Engineers Inc., pp. 1752-1758, 2015 IEEE International Conference on Industrial Technology, ICIT 2015, Seville, Spain, 17/03/15. https://doi.org/10.1109/ICIT.2015.7125351

Remaining useful life estimation of ball bearings by means of monotonic score calibration. / Carino, J. A.; Zurita, D.; Delgado, M. et al.
2015 IEEE International Conference on Industrial Technology, ICIT 2015. June. ed. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1752-1758 7125351 (Proceedings of the IEEE International Conference on Industrial Technology; Vol. 2015-June, No. June).

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

TY - GEN

T1 - Remaining useful life estimation of ball bearings by means of monotonic score calibration

AU - Carino, J. A.

AU - Zurita, D.

AU - Delgado, M.

AU - Ortega, J. A.

AU - Romero-Troncoso, R. J.

PY - 2015/6/16

Y1 - 2015/6/16

N2 - The estimation of remaining useful life applied to industrial machinery and its components is one of the current trends in the advanced manufacturing field. In this context, this work presents a reliable methodology applied to ball bearings health monitoring. First, the proposed methodology analyses the available vibration and temperature data by means of the Spearman coefficient. This step allows the identification of the most significant monotonic relationship between features and the evolution of the remaining useful life. The method is complemented by means of the application of one-class support vector machine in order to obtain the remaining useful life indication trough the mapping of the classification scores. The proposed scheme shows a significant accuracy and reliability of the degradation detection due to the coherent management of the information. This fact is experimentally demonstrated by a run-to-failure test bench and the comparison with classical approaches.

AB - The estimation of remaining useful life applied to industrial machinery and its components is one of the current trends in the advanced manufacturing field. In this context, this work presents a reliable methodology applied to ball bearings health monitoring. First, the proposed methodology analyses the available vibration and temperature data by means of the Spearman coefficient. This step allows the identification of the most significant monotonic relationship between features and the evolution of the remaining useful life. The method is complemented by means of the application of one-class support vector machine in order to obtain the remaining useful life indication trough the mapping of the classification scores. The proposed scheme shows a significant accuracy and reliability of the degradation detection due to the coherent management of the information. This fact is experimentally demonstrated by a run-to-failure test bench and the comparison with classical approaches.

KW - Artificial Intelligence

KW - Classification Algorithms

KW - Machine Learning

KW - One Class Support Vector Machines

KW - Remeaning Useful Life

UR - https://www.scopus.com/pages/publications/84937698436

U2 - 10.1109/ICIT.2015.7125351

DO - 10.1109/ICIT.2015.7125351

M3 - Conference contribution

AN - SCOPUS:84937698436

T3 - Proceedings of the IEEE International Conference on Industrial Technology

SP - 1752

EP - 1758

BT - 2015 IEEE International Conference on Industrial Technology, ICIT 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 IEEE International Conference on Industrial Technology, ICIT 2015

Y2 - 17 March 2015 through 19 March 2015

ER -

Carino JA, Zurita D, Delgado M, Ortega JA, Romero-Troncoso RJ. Remaining useful life estimation of ball bearings by means of monotonic score calibration. In 2015 IEEE International Conference on Industrial Technology, ICIT 2015. June ed. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1752-1758. 7125351. (Proceedings of the IEEE International Conference on Industrial Technology; June). doi: 10.1109/ICIT.2015.7125351

Remaining useful life estimation of ball bearings by means of monotonic score calibration

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this