Abstract
Classification of fault severity in gearboxes using Acoustic Emission (AE) signals is challenging because such signals represent a highly non-linear and possibly chaotic system. Due to the common assumption of linearity, the statistical features extracted from these systems are suboptimal for the classification of fault severity. Hence, this paper uses the Poincaré plot (PP) of Acoustic Emission (AE) signals to extract useful features to classify fault type and severity in gearboxes. For this development, four fault types were applied over different gears and then tested on an experimental condition monitoring bench: broken tooth, pitting, scuffing, and cracks, each with nine severity levels. Then, the feature set was extracted from the conventional 2-D PP, composed of shape-related features and a set of features known as complex correlation measurements (CCM). The fault type and severity classification was performed using four frequency bands. Low and band-pass filtered signals obtained the highest classification accuracy with Random Forest (RF): the fault type was classified with an accuracy of 99.69%, the severity was classified with an accuracy depending on the fault type corresponding to pitting 98.76%, cracks 98.71%, broken tooth 98.96%, and scuffing 98.51%. The PP features set has a low computational cost even for large datasets representing AE signals, which can benefit the practical possibility of the implementation with high classification accuracy for different types of fault and severity levels in a gearbox.
Original language | English |
---|---|
Article number | 109918 |
Journal | Applied Acoustics |
Volume | 219 |
DOIs | |
State | Published - 30 Mar 2024 |
Keywords
- Acoustic emission
- Fault severity
- Gearboxes
- Machine monitoring
- Random forest
Access to Document
Other files and links
Fingerprint
Dive into the research topics of 'Gearbox faults severity classification using Poincaré plots of acoustic emission signals'. Together they form a unique fingerprint.
View full fingerprint
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver
Medina, R., Sánchez, R. V., Cabrera, D., Cerrada, M., Estupiñan, E., Ao, W., & Vásquez, R. E. (2024). Gearbox faults severity classification using Poincaré plots of acoustic emission signals. Applied Acoustics, 219, Article 109918. https://doi.org/10.1016/j.apacoust.2024.109918
Medina, Rubén ; Sánchez, René Vinicio ; Cabrera, Diego et al. / Gearbox faults severity classification using Poincaré plots of acoustic emission signals. In: Applied Acoustics. 2024 ; Vol. 219.
@article{aa95b64e9aaf48bcb78cfd4ee5c148f4,
title = "Gearbox faults severity classification using Poincar{\'e} plots of acoustic emission signals",
abstract = "Classification of fault severity in gearboxes using Acoustic Emission (AE) signals is challenging because such signals represent a highly non-linear and possibly chaotic system. Due to the common assumption of linearity, the statistical features extracted from these systems are suboptimal for the classification of fault severity. Hence, this paper uses the Poincar{\'e} plot (PP) of Acoustic Emission (AE) signals to extract useful features to classify fault type and severity in gearboxes. For this development, four fault types were applied over different gears and then tested on an experimental condition monitoring bench: broken tooth, pitting, scuffing, and cracks, each with nine severity levels. Then, the feature set was extracted from the conventional 2-D PP, composed of shape-related features and a set of features known as complex correlation measurements (CCM). The fault type and severity classification was performed using four frequency bands. Low and band-pass filtered signals obtained the highest classification accuracy with Random Forest (RF): the fault type was classified with an accuracy of 99.69%, the severity was classified with an accuracy depending on the fault type corresponding to pitting 98.76%, cracks 98.71%, broken tooth 98.96%, and scuffing 98.51%. The PP features set has a low computational cost even for large datasets representing AE signals, which can benefit the practical possibility of the implementation with high classification accuracy for different types of fault and severity levels in a gearbox.",
keywords = "Acoustic emission, Fault severity, Gearboxes, Machine monitoring, Random forest",
author = "Rub{\'e}n Medina and S{\'a}nchez, {Ren{\'e} Vinicio} and Diego Cabrera and Mariela Cerrada and Edgar Estupi{\~n}an and Wengang Ao and V{\'a}squez, {Rafael E.}",
note = "Publisher Copyright: {\textcopyright} 2024 The Author(s)",
year = "2024",
month = mar,
day = "30",
doi = "10.1016/j.apacoust.2024.109918",
language = "English",
volume = "219",
journal = "Applied Acoustics",
issn = "0003-682X",
}
Medina, R, Sánchez, RV, Cabrera, D, Cerrada, M, Estupiñan, E, Ao, W & Vásquez, RE 2024, 'Gearbox faults severity classification using Poincaré plots of acoustic emission signals', Applied Acoustics, vol. 219, 109918. https://doi.org/10.1016/j.apacoust.2024.109918
Gearbox faults severity classification using Poincaré plots of acoustic emission signals. / Medina, Rubén; Sánchez, René Vinicio; Cabrera, Diego et al.
In: Applied Acoustics, Vol. 219, 109918, 30.03.2024.
Research output: Contribution to journal › Article › peer-review
TY - JOUR
T1 - Gearbox faults severity classification using Poincaré plots of acoustic emission signals
AU - Medina, Rubén
AU - Sánchez, René Vinicio
AU - Cabrera, Diego
AU - Cerrada, Mariela
AU - Estupiñan, Edgar
AU - Ao, Wengang
AU - Vásquez, Rafael E.
N1 - Publisher Copyright:© 2024 The Author(s)
PY - 2024/3/30
Y1 - 2024/3/30
N2 - Classification of fault severity in gearboxes using Acoustic Emission (AE) signals is challenging because such signals represent a highly non-linear and possibly chaotic system. Due to the common assumption of linearity, the statistical features extracted from these systems are suboptimal for the classification of fault severity. Hence, this paper uses the Poincaré plot (PP) of Acoustic Emission (AE) signals to extract useful features to classify fault type and severity in gearboxes. For this development, four fault types were applied over different gears and then tested on an experimental condition monitoring bench: broken tooth, pitting, scuffing, and cracks, each with nine severity levels. Then, the feature set was extracted from the conventional 2-D PP, composed of shape-related features and a set of features known as complex correlation measurements (CCM). The fault type and severity classification was performed using four frequency bands. Low and band-pass filtered signals obtained the highest classification accuracy with Random Forest (RF): the fault type was classified with an accuracy of 99.69%, the severity was classified with an accuracy depending on the fault type corresponding to pitting 98.76%, cracks 98.71%, broken tooth 98.96%, and scuffing 98.51%. The PP features set has a low computational cost even for large datasets representing AE signals, which can benefit the practical possibility of the implementation with high classification accuracy for different types of fault and severity levels in a gearbox.
AB - Classification of fault severity in gearboxes using Acoustic Emission (AE) signals is challenging because such signals represent a highly non-linear and possibly chaotic system. Due to the common assumption of linearity, the statistical features extracted from these systems are suboptimal for the classification of fault severity. Hence, this paper uses the Poincaré plot (PP) of Acoustic Emission (AE) signals to extract useful features to classify fault type and severity in gearboxes. For this development, four fault types were applied over different gears and then tested on an experimental condition monitoring bench: broken tooth, pitting, scuffing, and cracks, each with nine severity levels. Then, the feature set was extracted from the conventional 2-D PP, composed of shape-related features and a set of features known as complex correlation measurements (CCM). The fault type and severity classification was performed using four frequency bands. Low and band-pass filtered signals obtained the highest classification accuracy with Random Forest (RF): the fault type was classified with an accuracy of 99.69%, the severity was classified with an accuracy depending on the fault type corresponding to pitting 98.76%, cracks 98.71%, broken tooth 98.96%, and scuffing 98.51%. The PP features set has a low computational cost even for large datasets representing AE signals, which can benefit the practical possibility of the implementation with high classification accuracy for different types of fault and severity levels in a gearbox.
KW - Acoustic emission
KW - Fault severity
KW - Gearboxes
KW - Machine monitoring
KW - Random forest
UR - http://www.scopus.com/inward/record.url?scp=85185538448&partnerID=8YFLogxK
U2 - 10.1016/j.apacoust.2024.109918
DO - 10.1016/j.apacoust.2024.109918
M3 - Article
AN - SCOPUS:85185538448
SN - 0003-682X
VL - 219
JO - Applied Acoustics
JF - Applied Acoustics
M1 - 109918
ER -
Medina R, Sánchez RV, Cabrera D, Cerrada M, Estupiñan E, Ao W et al. Gearbox faults severity classification using Poincaré plots of acoustic emission signals. Applied Acoustics. 2024 Mar 30;219:109918. doi: 10.1016/j.apacoust.2024.109918