Feature selection for helicopter swashplate bearing fault diagnosis

Yong Wang; Lin Li

doi:10.1115/MSEC2017-2643

Feature selection for helicopter swashplate bearing fault diagnosis

Yong Wang
, Lin Li

School of Sys Sci Ind Engr

Binghamton University

University of Illinois at Chicago

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

Abstract

This paper provides a case study of diagnosing helicopter swashplate ball bearing faults using vibration signals. We develop and apply feature extraction and selection techniques in the time, frequency, and joint time-frequency domains to differentiate six types of swashplate bearing conditions: low-time, to-be-overhauled, corroded, cage-popping, spalled, and case-overlapping. With proper selection of the features, it is shown that even the simple k-nearest neighbor (k-NN) algorithm is able to correctly identify these six types of conditions on the tested data. The developed method is useful for helicopter swashplate condition monitoring and maintenance scheduling. It is also helpful for testing the manufactured swashplate ball bearings for quality control purposes.

Original language	English
Title of host publication	Manufacturing Equipment and Systems
Publisher	American Society of Mechanical Engineers
ISBN (Electronic)	9780791850749
DOIs	https://doi.org/10.1115/MSEC2017-2643
State	Published - 2017
Event	ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing - Los Angeles, United States Duration: Jun 4 2017 → Jun 8 2017

Publication series

Name	ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing
Volume	3

Conference

Conference	ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing
Country/Territory	United States
City	Los Angeles
Period	06/4/17 → 06/8/17

Keywords

Condition monitoring
Fault diagnosis
Helicopter
K-nearest neighbors
Swashplate bearing

Access to Document

10.1115/MSEC2017-2643

Cite this

Wang, Y., & Li, L. (2017). Feature selection for helicopter swashplate bearing fault diagnosis. In Manufacturing Equipment and Systems (ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing; Vol. 3). American Society of Mechanical Engineers. https://doi.org/10.1115/MSEC2017-2643

@inproceedings{df50ce9a7f2c49f8aa63bc9fc5dafdbf,

title = "Feature selection for helicopter swashplate bearing fault diagnosis",

abstract = "This paper provides a case study of diagnosing helicopter swashplate ball bearing faults using vibration signals. We develop and apply feature extraction and selection techniques in the time, frequency, and joint time-frequency domains to differentiate six types of swashplate bearing conditions: low-time, to-be-overhauled, corroded, cage-popping, spalled, and case-overlapping. With proper selection of the features, it is shown that even the simple k-nearest neighbor (k-NN) algorithm is able to correctly identify these six types of conditions on the tested data. The developed method is useful for helicopter swashplate condition monitoring and maintenance scheduling. It is also helpful for testing the manufactured swashplate ball bearings for quality control purposes.",

keywords = "Condition monitoring, Fault diagnosis, Helicopter, K-nearest neighbors, Swashplate bearing",

author = "Yong Wang and Lin Li",

note = "Publisher Copyright: {\textcopyright} Copyright 2017 ASME.; ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing ; Conference date: 04-06-2017 Through 08-06-2017",

year = "2017",

doi = "10.1115/MSEC2017-2643",

language = "English",

series = "ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing",

publisher = "American Society of Mechanical Engineers",

booktitle = "Manufacturing Equipment and Systems",

}

Wang, Y & Li, L 2017, Feature selection for helicopter swashplate bearing fault diagnosis. in Manufacturing Equipment and Systems. ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing, vol. 3, American Society of Mechanical Engineers, ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing, Los Angeles, United States, 06/4/17. https://doi.org/10.1115/MSEC2017-2643

Feature selection for helicopter swashplate bearing fault diagnosis. / Wang, Yong; Li, Lin.
Manufacturing Equipment and Systems. American Society of Mechanical Engineers, 2017. (ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing; Vol. 3).

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

TY - GEN

T1 - Feature selection for helicopter swashplate bearing fault diagnosis

AU - Wang, Yong

AU - Li, Lin

PY - 2017

Y1 - 2017

N2 - This paper provides a case study of diagnosing helicopter swashplate ball bearing faults using vibration signals. We develop and apply feature extraction and selection techniques in the time, frequency, and joint time-frequency domains to differentiate six types of swashplate bearing conditions: low-time, to-be-overhauled, corroded, cage-popping, spalled, and case-overlapping. With proper selection of the features, it is shown that even the simple k-nearest neighbor (k-NN) algorithm is able to correctly identify these six types of conditions on the tested data. The developed method is useful for helicopter swashplate condition monitoring and maintenance scheduling. It is also helpful for testing the manufactured swashplate ball bearings for quality control purposes.

AB - This paper provides a case study of diagnosing helicopter swashplate ball bearing faults using vibration signals. We develop and apply feature extraction and selection techniques in the time, frequency, and joint time-frequency domains to differentiate six types of swashplate bearing conditions: low-time, to-be-overhauled, corroded, cage-popping, spalled, and case-overlapping. With proper selection of the features, it is shown that even the simple k-nearest neighbor (k-NN) algorithm is able to correctly identify these six types of conditions on the tested data. The developed method is useful for helicopter swashplate condition monitoring and maintenance scheduling. It is also helpful for testing the manufactured swashplate ball bearings for quality control purposes.

KW - Condition monitoring

KW - Fault diagnosis

KW - Helicopter

KW - K-nearest neighbors

KW - Swashplate bearing

UR - https://www.scopus.com/pages/publications/85027830378

U2 - 10.1115/MSEC2017-2643

DO - 10.1115/MSEC2017-2643

M3 - Conference contribution

T3 - ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing

BT - Manufacturing Equipment and Systems

PB - American Society of Mechanical Engineers

T2 - ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing

Y2 - 4 June 2017 through 8 June 2017

ER -

Wang Y, Li L. Feature selection for helicopter swashplate bearing fault diagnosis. In Manufacturing Equipment and Systems. American Society of Mechanical Engineers. 2017. (ASME 2017 12th International Manufacturing Science and Engineering Conference, MSEC 2017 collocated with the JSME/ASME 2017 6th International Conference on Materials and Processing). doi: 10.1115/MSEC2017-2643

Feature selection for helicopter swashplate bearing fault diagnosis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this