TY - GEN
T1 - Gearbox Fault Diagnostics
T2 - 8th International Conference on Robot Intelligence Technology and Applications, RiTA 2020
AU - Hasan, Md Jahid
AU - Rashid, Mamunur
AU - Ahmad, Ahmad Fakhri
AU - Mohd Khairuddin, Ismail
AU - Mohd Razman, Mohd Azraai
AU - Musa, Rabiu Muazu
AU - P. P. Abdul Majeed, Anwar
N1 - Publisher Copyright:
© 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2021
Y1 - 2021
N2 - More often than not, gearbox defects have been reported in the literature to be one of the primary causes of rotating machinery failure. In this paper, we explore different types of time-domain as well as frequency domain features towards the classification of gearbox fault diagnostics via Support Vector Machine (SVM). The proposed architecture was evaluated on an online repository dataset which comprises nine classes in which eight are faulty under both loaded and unloaded environments. It was shown from the study that the fast standard deviation-based feature extracted from the Fast-Fourier based transformed signals could yield a classification accuracy of 99.4% and 98.69% for both training and testing dataset, respectively on the 20 Hz-0V loading condition. The preliminary results presented here are non-trivial towards achieving low computational expense-based gearbox fault diagnostics.
AB - More often than not, gearbox defects have been reported in the literature to be one of the primary causes of rotating machinery failure. In this paper, we explore different types of time-domain as well as frequency domain features towards the classification of gearbox fault diagnostics via Support Vector Machine (SVM). The proposed architecture was evaluated on an online repository dataset which comprises nine classes in which eight are faulty under both loaded and unloaded environments. It was shown from the study that the fast standard deviation-based feature extracted from the Fast-Fourier based transformed signals could yield a classification accuracy of 99.4% and 98.69% for both training and testing dataset, respectively on the 20 Hz-0V loading condition. The preliminary results presented here are non-trivial towards achieving low computational expense-based gearbox fault diagnostics.
KW - Fast Fourier transform (FFT)
KW - Gearbox fault detection
KW - Machine learning
KW - Support Vector Machines (SVM)
UR - http://www.scopus.com/inward/record.url?scp=85113765043&partnerID=8YFLogxK
U2 - 10.1007/978-981-16-4803-8_40
DO - 10.1007/978-981-16-4803-8_40
M3 - Conference Proceeding
AN - SCOPUS:85113765043
SN - 9789811648021
T3 - Lecture Notes in Mechanical Engineering
SP - 409
EP - 413
BT - RiTA 2020 - Proceedings of the 8th International Conference on Robot Intelligence Technology and Applications
A2 - Chew, Esyin
A2 - P. P. Abdul Majeed, Anwar
A2 - Liu, Pengcheng
A2 - Platts, Jon
A2 - Myung, Hyun
A2 - Kim, Junmo
A2 - Kim, Jong-Hwan
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 11 December 2020 through 13 December 2020
ER -