Intelligent Diagnostics of Radial Internal Clearance in Ball Bearings with Machine Learning Methods

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Intelligent Diagnostics of Radial Internal Clearance in Ball Bearings with Machine Learning Methods. / Ambrożkiewicz, Bartłomiej; Syta, Arkadiusz; Georgiadis, Anthimos et al.
In: Sensors, Vol. 23, No. 13, 5875, 25.06.2023.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Ambrożkiewicz B, Syta A, Georgiadis A, Gassner A, Litak G, Meier N. Intelligent Diagnostics of Radial Internal Clearance in Ball Bearings with Machine Learning Methods. Sensors. 2023 Jun 25;23(13):5875. doi: 10.3390/s23135875

Bibtex

@article{46747cd206a342d3b675207799c9cdc2,
title = "Intelligent Diagnostics of Radial Internal Clearance in Ball Bearings with Machine Learning Methods",
abstract = "This article classifies the dynamic response of rolling bearings in terms of radial internal clearance values. The value of the radial internal clearance in rolling-element bearings cannot be described in a deterministic manner, which shows the challenge of its detection through the analysis of the bearing{\textquoteright}s dynamics. In this article, we show the original approach to its intelligent detection through the analysis of short-time intervals and the calculation of chosen indicators, which can be assigned to the specific clearance class. The tests were carried out on a set of 10 brand new bearings of the same type (double row self-aligning ball bearing NTN 2309SK) with different radial internal clearances corresponding to individual classes of the ISO-1132 standard. The classification was carried out based on the time series of vibrations recorded by the accelerometer and then digitally processed. Window statistical indicators widely used in the diagnosis of rolling bearings, which served as features for the machine learning models, were calculated. The accuracy of the classification turned out to be unsatisfactory; therefore, it was decided to use a more advanced method of time series processing, which allows for the extraction of subsequent dominant frequencies into experimental modes (Variational Mode Decomposition (VMD)). Applying the same statistical indicators to the modes allowed for an increase in classification accuracy to over 90%.",
keywords = "ball bearings, machine learning, radial internal clearance, time-series analysis, Engineering",
author = "Bart{\l}omiej Ambro{\.z}kiewicz and Arkadiusz Syta and Anthimos Georgiadis and Alexander Gassner and Grzegorz Litak and Nicolas Meier",
note = "The authors would like to thank to the company NTN-SNR EUROPE for the delivery of bearings and all necessary equipment used in the conducted experiment in the Institute of Process and Product Innovation at the Leuphana University of L{\"u}neburg. Publisher Copyright: {\textcopyright} 2023 by the authors.",
year = "2023",
month = jun,
day = "25",
doi = "10.3390/s23135875",
language = "English",
volume = "23",
journal = "Sensors",
issn = "1424-8239",
publisher = "MDPI AG",
number = "13",

}

RIS

TY - JOUR

T1 - Intelligent Diagnostics of Radial Internal Clearance in Ball Bearings with Machine Learning Methods

AU - Ambrożkiewicz, Bartłomiej

AU - Syta, Arkadiusz

AU - Georgiadis, Anthimos

AU - Gassner, Alexander

AU - Litak, Grzegorz

AU - Meier, Nicolas

N1 - The authors would like to thank to the company NTN-SNR EUROPE for the delivery of bearings and all necessary equipment used in the conducted experiment in the Institute of Process and Product Innovation at the Leuphana University of Lüneburg. Publisher Copyright: © 2023 by the authors.

PY - 2023/6/25

Y1 - 2023/6/25

N2 - This article classifies the dynamic response of rolling bearings in terms of radial internal clearance values. The value of the radial internal clearance in rolling-element bearings cannot be described in a deterministic manner, which shows the challenge of its detection through the analysis of the bearing’s dynamics. In this article, we show the original approach to its intelligent detection through the analysis of short-time intervals and the calculation of chosen indicators, which can be assigned to the specific clearance class. The tests were carried out on a set of 10 brand new bearings of the same type (double row self-aligning ball bearing NTN 2309SK) with different radial internal clearances corresponding to individual classes of the ISO-1132 standard. The classification was carried out based on the time series of vibrations recorded by the accelerometer and then digitally processed. Window statistical indicators widely used in the diagnosis of rolling bearings, which served as features for the machine learning models, were calculated. The accuracy of the classification turned out to be unsatisfactory; therefore, it was decided to use a more advanced method of time series processing, which allows for the extraction of subsequent dominant frequencies into experimental modes (Variational Mode Decomposition (VMD)). Applying the same statistical indicators to the modes allowed for an increase in classification accuracy to over 90%.

AB - This article classifies the dynamic response of rolling bearings in terms of radial internal clearance values. The value of the radial internal clearance in rolling-element bearings cannot be described in a deterministic manner, which shows the challenge of its detection through the analysis of the bearing’s dynamics. In this article, we show the original approach to its intelligent detection through the analysis of short-time intervals and the calculation of chosen indicators, which can be assigned to the specific clearance class. The tests were carried out on a set of 10 brand new bearings of the same type (double row self-aligning ball bearing NTN 2309SK) with different radial internal clearances corresponding to individual classes of the ISO-1132 standard. The classification was carried out based on the time series of vibrations recorded by the accelerometer and then digitally processed. Window statistical indicators widely used in the diagnosis of rolling bearings, which served as features for the machine learning models, were calculated. The accuracy of the classification turned out to be unsatisfactory; therefore, it was decided to use a more advanced method of time series processing, which allows for the extraction of subsequent dominant frequencies into experimental modes (Variational Mode Decomposition (VMD)). Applying the same statistical indicators to the modes allowed for an increase in classification accuracy to over 90%.

KW - ball bearings

KW - machine learning

KW - radial internal clearance

KW - time-series analysis

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=85164843473&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/5f4f9aed-07e8-30c9-9e54-75897e94a6ca/

U2 - 10.3390/s23135875

DO - 10.3390/s23135875

M3 - Journal articles

C2 - 37447725

AN - SCOPUS:85164843473

VL - 23

JO - Sensors

JF - Sensors

SN - 1424-8239

IS - 13

M1 - 5875

ER -

DOI