QIN, Bo ;LI, Zixian ;QIN, Yan . A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes. Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 66, n.6, p. 385-394, june 2020. ISSN 0039-2480. Available at: <https://www.sv-jme.eu/article/a-transient-feature-presentation-based-intelligent-fault-diagnosis-method-for-planetary-gearbox/>. Date accessed: 22 dec. 2024. doi:http://dx.doi.org/10.5545/sv-jme.2020.6546.
Qin, B., Li, Z., & Qin, Y. (2020). A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes. Strojniški vestnik - Journal of Mechanical Engineering, 66(6), 385-394. doi:http://dx.doi.org/10.5545/sv-jme.2020.6546
@article{sv-jmesv-jme.2020.6546,
author = {Bo Qin and Zixian Li and Yan Qin},
title = {A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {66},
number = {6},
year = {2020},
keywords = {transient features; kurtosis information; extreme learning machine; variational mode decomposition; fault diagnosis for planetary gearbox},
abstract = {Sensitive and accurate fault features from the vibration signals of planetary gearboxes are essential for fault diagnosis, in which extreme learning machine (ELM) techniques have been widely adopted. To increase the sensitivity of extracted features fed in ELM, a novel feature extraction method is put forward, which takes advantage of the transient dynamics and the reconstructed high-dimensional data from the original vibration signal. First, based on fast kurtosis analysis, the range of transient dynamics of a vibration signal is located. Next, with the extracted kurtosis information, with variational mode decomposition, a series of intrinsic mode functions are decomposed; the ones that fall into the obtained ranges are selected as transient features, corresponding to maximum kurtosis value. Fed by the transient features, a hierarchical ELM model is well-trained for fault classification. Furthermore, a denoising auto-encoder is used to optimize input weight and threshold of implicit learning node of ELM, satisfying orthogonal condition to realize the layering of its hidden layers. Finally, a numerical case and an experiment are conducted to verify the performance of the proposed method. In comparison with its counterparts, the proposed method has a better classification accuracy in the aiding of transient features.},
issn = {0039-2480}, pages = {385-394}, doi = {10.5545/sv-jme.2020.6546},
url = {https://www.sv-jme.eu/article/a-transient-feature-presentation-based-intelligent-fault-diagnosis-method-for-planetary-gearbox/}
}
Qin, B.,Li, Z.,Qin, Y. 2020 June 66. A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 66:6
%A Qin, Bo %A Li, Zixian %A Qin, Yan %D 2020 %T A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes %B 2020 %9 transient features; kurtosis information; extreme learning machine; variational mode decomposition; fault diagnosis for planetary gearbox %! A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes %K transient features; kurtosis information; extreme learning machine; variational mode decomposition; fault diagnosis for planetary gearbox %X Sensitive and accurate fault features from the vibration signals of planetary gearboxes are essential for fault diagnosis, in which extreme learning machine (ELM) techniques have been widely adopted. To increase the sensitivity of extracted features fed in ELM, a novel feature extraction method is put forward, which takes advantage of the transient dynamics and the reconstructed high-dimensional data from the original vibration signal. First, based on fast kurtosis analysis, the range of transient dynamics of a vibration signal is located. Next, with the extracted kurtosis information, with variational mode decomposition, a series of intrinsic mode functions are decomposed; the ones that fall into the obtained ranges are selected as transient features, corresponding to maximum kurtosis value. Fed by the transient features, a hierarchical ELM model is well-trained for fault classification. Furthermore, a denoising auto-encoder is used to optimize input weight and threshold of implicit learning node of ELM, satisfying orthogonal condition to realize the layering of its hidden layers. Finally, a numerical case and an experiment are conducted to verify the performance of the proposed method. In comparison with its counterparts, the proposed method has a better classification accuracy in the aiding of transient features. %U https://www.sv-jme.eu/article/a-transient-feature-presentation-based-intelligent-fault-diagnosis-method-for-planetary-gearbox/ %0 Journal Article %R 10.5545/sv-jme.2020.6546 %& 385 %P 10 %J Strojniški vestnik - Journal of Mechanical Engineering %V 66 %N 6 %@ 0039-2480 %8 2020-06-17 %7 2020-06-17
Qin, Bo, Zixian Li, & Yan Qin. "A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes." Strojniški vestnik - Journal of Mechanical Engineering [Online], 66.6 (2020): 385-394. Web. 22 Dec. 2024
TY - JOUR AU - Qin, Bo AU - Li, Zixian AU - Qin, Yan PY - 2020 TI - A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes JF - Strojniški vestnik - Journal of Mechanical Engineering DO - 10.5545/sv-jme.2020.6546 KW - transient features; kurtosis information; extreme learning machine; variational mode decomposition; fault diagnosis for planetary gearbox N2 - Sensitive and accurate fault features from the vibration signals of planetary gearboxes are essential for fault diagnosis, in which extreme learning machine (ELM) techniques have been widely adopted. To increase the sensitivity of extracted features fed in ELM, a novel feature extraction method is put forward, which takes advantage of the transient dynamics and the reconstructed high-dimensional data from the original vibration signal. First, based on fast kurtosis analysis, the range of transient dynamics of a vibration signal is located. Next, with the extracted kurtosis information, with variational mode decomposition, a series of intrinsic mode functions are decomposed; the ones that fall into the obtained ranges are selected as transient features, corresponding to maximum kurtosis value. Fed by the transient features, a hierarchical ELM model is well-trained for fault classification. Furthermore, a denoising auto-encoder is used to optimize input weight and threshold of implicit learning node of ELM, satisfying orthogonal condition to realize the layering of its hidden layers. Finally, a numerical case and an experiment are conducted to verify the performance of the proposed method. In comparison with its counterparts, the proposed method has a better classification accuracy in the aiding of transient features. UR - https://www.sv-jme.eu/article/a-transient-feature-presentation-based-intelligent-fault-diagnosis-method-for-planetary-gearbox/
@article{{sv-jme}{sv-jme.2020.6546},
author = {Qin, B., Li, Z., Qin, Y.},
title = {A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {66},
number = {6},
year = {2020},
doi = {10.5545/sv-jme.2020.6546},
url = {https://www.sv-jme.eu/article/a-transient-feature-presentation-based-intelligent-fault-diagnosis-method-for-planetary-gearbox/}
}
TY - JOUR AU - Qin, Bo AU - Li, Zixian AU - Qin, Yan PY - 2020/06/17 TI - A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes JF - Strojniški vestnik - Journal of Mechanical Engineering; Vol 66, No 6 (2020): Strojniški vestnik - Journal of Mechanical Engineering DO - 10.5545/sv-jme.2020.6546 KW - transient features, kurtosis information, extreme learning machine, variational mode decomposition, fault diagnosis for planetary gearbox N2 - Sensitive and accurate fault features from the vibration signals of planetary gearboxes are essential for fault diagnosis, in which extreme learning machine (ELM) techniques have been widely adopted. To increase the sensitivity of extracted features fed in ELM, a novel feature extraction method is put forward, which takes advantage of the transient dynamics and the reconstructed high-dimensional data from the original vibration signal. First, based on fast kurtosis analysis, the range of transient dynamics of a vibration signal is located. Next, with the extracted kurtosis information, with variational mode decomposition, a series of intrinsic mode functions are decomposed; the ones that fall into the obtained ranges are selected as transient features, corresponding to maximum kurtosis value. Fed by the transient features, a hierarchical ELM model is well-trained for fault classification. Furthermore, a denoising auto-encoder is used to optimize input weight and threshold of implicit learning node of ELM, satisfying orthogonal condition to realize the layering of its hidden layers. Finally, a numerical case and an experiment are conducted to verify the performance of the proposed method. In comparison with its counterparts, the proposed method has a better classification accuracy in the aiding of transient features. UR - https://www.sv-jme.eu/article/a-transient-feature-presentation-based-intelligent-fault-diagnosis-method-for-planetary-gearbox/
Qin, Bo, Li, Zixian, AND Qin, Yan. "A Transient Feature Learning-Based Intelligent Fault Diagnosis Method for Planetary Gearboxes" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 66 Number 6 (17 June 2020)
Strojniški vestnik - Journal of Mechanical Engineering 66(2020)6, 385-394
© The Authors, CC-BY 4.0 Int. Change in copyright policy from 2022, Jan 1st.
Sensitive and accurate fault features from the vibration signals of planetary gearboxes are essential for fault diagnosis, in which extreme learning machine (ELM) techniques have been widely adopted. To increase the sensitivity of extracted features fed in ELM, a novel feature extraction method is put forward, which takes advantage of the transient dynamics and the reconstructed high-dimensional data from the original vibration signal. First, based on fast kurtosis analysis, the range of transient dynamics of a vibration signal is located. Next, with the extracted kurtosis information, with variational mode decomposition, a series of intrinsic mode functions are decomposed; the ones that fall into the obtained ranges are selected as transient features, corresponding to maximum kurtosis value. Fed by the transient features, a hierarchical ELM model is well-trained for fault classification. Furthermore, a denoising auto-encoder is used to optimize input weight and threshold of implicit learning node of ELM, satisfying orthogonal condition to realize the layering of its hidden layers. Finally, a numerical case and an experiment are conducted to verify the performance of the proposed method. In comparison with its counterparts, the proposed method has a better classification accuracy in the aiding of transient features.