Prediction of Friction Power via Machine Learning of Acoustic Emissions from a Ring-on-Disc Rotary Tribometer

Publikationen: Beitrag in FachzeitschriftArtikelForschung(peer-reviewed)

Standard

Prediction of Friction Power via Machine Learning of Acoustic Emissions from a Ring-on-Disc Rotary Tribometer. / Strablegg, Christopher; Summer, Florian; Renhart, Philipp et al.
in: Lubricants, Jahrgang 11.2023, Nr. 2, 37, 19.01.2023.

Publikationen: Beitrag in FachzeitschriftArtikelForschung(peer-reviewed)

Bibtex - Download

@article{6acddb582ca34b6894f98f328979c1c4,
title = "Prediction of Friction Power via Machine Learning of Acoustic Emissions from a Ring-on-Disc Rotary Tribometer",
abstract = "Acoustic emissions from tribological contacts have become an interesting field of science in recent years. This study focuses on predicting the friction power of a given system (lubricated ring-on-disc geometry), independently of the used sliding material and lubricant, from the acoustic emissions emitted from the system. The low-frequency (1 Hz), continuously measured RMS value of the acoustic data is combined with short-duration and high-frequency (850 kHz) signal data in form of the power spectra and hit rate with three prominence levels. The classification system then predicts the friction power of the test system continuously over the whole test time. Prediction is achieved by four different machine learning methods (tree-type, support vector machine, K-nearest-neighbor, neural network) trained with data from 54 ring-on-disc tests with high variation in material and oil combinations. The method allows for the quantifiable and step-free prediction of absolute values of friction power with accuracy of 97.6% on unseen data, with a weighted K-nearest-neighbor classifier, at any point in time during an experiment. The system reacts well to rapid changes in friction conditions due to changes in load and temperature. The study shows the high information degree of acoustic emissions, concerning the actual friction mechanisms occurring and the quantitative, and not only qualitative, information that one can gain about a tribological system by analyzing them.",
keywords = "acoustic emission; friction prediction; machine learning",
author = "Christopher Strablegg and Florian Summer and Philipp Renhart and Florian Gr{\"u}n",
note = "This pubication was a special issue in the kournal with the title: {"}Acoustic Emission in Friction{"}",
year = "2023",
month = jan,
day = "19",
doi = "10.3390/lubricants11020037",
language = "English",
volume = "11.2023",
journal = "Lubricants",
issn = "2075-4442",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Prediction of Friction Power via Machine Learning of Acoustic Emissions from a Ring-on-Disc Rotary Tribometer

AU - Strablegg, Christopher

AU - Summer, Florian

AU - Renhart, Philipp

AU - Grün, Florian

N1 - This pubication was a special issue in the kournal with the title: "Acoustic Emission in Friction"

PY - 2023/1/19

Y1 - 2023/1/19

N2 - Acoustic emissions from tribological contacts have become an interesting field of science in recent years. This study focuses on predicting the friction power of a given system (lubricated ring-on-disc geometry), independently of the used sliding material and lubricant, from the acoustic emissions emitted from the system. The low-frequency (1 Hz), continuously measured RMS value of the acoustic data is combined with short-duration and high-frequency (850 kHz) signal data in form of the power spectra and hit rate with three prominence levels. The classification system then predicts the friction power of the test system continuously over the whole test time. Prediction is achieved by four different machine learning methods (tree-type, support vector machine, K-nearest-neighbor, neural network) trained with data from 54 ring-on-disc tests with high variation in material and oil combinations. The method allows for the quantifiable and step-free prediction of absolute values of friction power with accuracy of 97.6% on unseen data, with a weighted K-nearest-neighbor classifier, at any point in time during an experiment. The system reacts well to rapid changes in friction conditions due to changes in load and temperature. The study shows the high information degree of acoustic emissions, concerning the actual friction mechanisms occurring and the quantitative, and not only qualitative, information that one can gain about a tribological system by analyzing them.

AB - Acoustic emissions from tribological contacts have become an interesting field of science in recent years. This study focuses on predicting the friction power of a given system (lubricated ring-on-disc geometry), independently of the used sliding material and lubricant, from the acoustic emissions emitted from the system. The low-frequency (1 Hz), continuously measured RMS value of the acoustic data is combined with short-duration and high-frequency (850 kHz) signal data in form of the power spectra and hit rate with three prominence levels. The classification system then predicts the friction power of the test system continuously over the whole test time. Prediction is achieved by four different machine learning methods (tree-type, support vector machine, K-nearest-neighbor, neural network) trained with data from 54 ring-on-disc tests with high variation in material and oil combinations. The method allows for the quantifiable and step-free prediction of absolute values of friction power with accuracy of 97.6% on unseen data, with a weighted K-nearest-neighbor classifier, at any point in time during an experiment. The system reacts well to rapid changes in friction conditions due to changes in load and temperature. The study shows the high information degree of acoustic emissions, concerning the actual friction mechanisms occurring and the quantitative, and not only qualitative, information that one can gain about a tribological system by analyzing them.

KW - acoustic emission; friction prediction; machine learning

U2 - 10.3390/lubricants11020037

DO - 10.3390/lubricants11020037

M3 - Article

VL - 11.2023

JO - Lubricants

JF - Lubricants

SN - 2075-4442

IS - 2

M1 - 37

ER -