Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network

226 Views
153 Downloads
Export citation: ABNT
YANG, Shuai ;LUO, Xing ;LI, Chuan .
Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 67, n.10, p. 489-500, october 2021. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/fault-diagnosis-of-rotation-vector-reducer-for-industrial-robot-based-on-convolutional-neural-network/>. Date accessed: 27 jan. 2022. 
doi:http://dx.doi.org/10.5545/sv-jme.2021.7284.
Yang, S., Luo, X., & Li, C.
(2021).
Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network.
Strojniški vestnik - Journal of Mechanical Engineering, 67(10), 489-500.
doi:http://dx.doi.org/10.5545/sv-jme.2021.7284
@article{sv-jmesv-jme.2021.7284,
	author = {Shuai  Yang and Xing  Luo and Chuan  Li},
	title = {Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {67},
	number = {10},
	year = {2021},
	keywords = {fault diagnosis, convolutional neural network, RV reducer},
	abstract = {As a key component of a mechanical drive system, the failure of the reducer will usually cause huge economic losses and even lead to serious casualties in extreme cases. To solve this problem, a two-dimensional convolutional neural network (2D-CNN) is proposed for the fault diagnosis of the rotation vector (RV) reducer installed on the industrial robot (IR). The proposed method can automatically extract the features from the data and reduce the connections between neurons and the parameters that need to be trained with its local receptive field, weight sharing, and subsampling features. Due to the aforementioned characteristics, the efficiency of network training is significantly improved, and verified by the experimental simulations. Comparative experiments with other mainstream methods are carried out to further validate the fault classification accuracy of the proposed method. The results indicate that the proposed method out-performs all the selected methods.},
	issn = {0039-2480},	pages = {489-500},	doi = {10.5545/sv-jme.2021.7284},
	url = {https://www.sv-jme.eu/article/fault-diagnosis-of-rotation-vector-reducer-for-industrial-robot-based-on-convolutional-neural-network/}
}
Yang, S.,Luo, X.,Li, C.
2021 October 67. Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 67:10
%A Yang, Shuai 
%A Luo, Xing 
%A Li, Chuan 
%D 2021
%T Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network
%B 2021
%9 fault diagnosis, convolutional neural network, RV reducer
%! Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network
%K fault diagnosis, convolutional neural network, RV reducer
%X As a key component of a mechanical drive system, the failure of the reducer will usually cause huge economic losses and even lead to serious casualties in extreme cases. To solve this problem, a two-dimensional convolutional neural network (2D-CNN) is proposed for the fault diagnosis of the rotation vector (RV) reducer installed on the industrial robot (IR). The proposed method can automatically extract the features from the data and reduce the connections between neurons and the parameters that need to be trained with its local receptive field, weight sharing, and subsampling features. Due to the aforementioned characteristics, the efficiency of network training is significantly improved, and verified by the experimental simulations. Comparative experiments with other mainstream methods are carried out to further validate the fault classification accuracy of the proposed method. The results indicate that the proposed method out-performs all the selected methods.
%U https://www.sv-jme.eu/article/fault-diagnosis-of-rotation-vector-reducer-for-industrial-robot-based-on-convolutional-neural-network/
%0 Journal Article
%R 10.5545/sv-jme.2021.7284
%& 489
%P 12
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 67
%N 10
%@ 0039-2480
%8 2021-10-22
%7 2021-10-22
Yang, Shuai, Xing  Luo, & Chuan  Li.
"Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network." Strojniški vestnik - Journal of Mechanical Engineering [Online], 67.10 (2021): 489-500. Web.  27 Jan. 2022
TY  - JOUR
AU  - Yang, Shuai 
AU  - Luo, Xing 
AU  - Li, Chuan 
PY  - 2021
TI  - Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2021.7284
KW  - fault diagnosis, convolutional neural network, RV reducer
N2  - As a key component of a mechanical drive system, the failure of the reducer will usually cause huge economic losses and even lead to serious casualties in extreme cases. To solve this problem, a two-dimensional convolutional neural network (2D-CNN) is proposed for the fault diagnosis of the rotation vector (RV) reducer installed on the industrial robot (IR). The proposed method can automatically extract the features from the data and reduce the connections between neurons and the parameters that need to be trained with its local receptive field, weight sharing, and subsampling features. Due to the aforementioned characteristics, the efficiency of network training is significantly improved, and verified by the experimental simulations. Comparative experiments with other mainstream methods are carried out to further validate the fault classification accuracy of the proposed method. The results indicate that the proposed method out-performs all the selected methods.
UR  - https://www.sv-jme.eu/article/fault-diagnosis-of-rotation-vector-reducer-for-industrial-robot-based-on-convolutional-neural-network/
@article{{sv-jme}{sv-jme.2021.7284},
	author = {Yang, S., Luo, X., Li, C.},
	title = {Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {67},
	number = {10},
	year = {2021},
	doi = {10.5545/sv-jme.2021.7284},
	url = {https://www.sv-jme.eu/article/fault-diagnosis-of-rotation-vector-reducer-for-industrial-robot-based-on-convolutional-neural-network/}
}
TY  - JOUR
AU  - Yang, Shuai 
AU  - Luo, Xing 
AU  - Li, Chuan 
PY  - 2021/10/22
TI  - Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 67, No 10 (2021): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2021.7284
KW  - fault diagnosis, convolutional neural network, RV reducer
N2  - As a key component of a mechanical drive system, the failure of the reducer will usually cause huge economic losses and even lead to serious casualties in extreme cases. To solve this problem, a two-dimensional convolutional neural network (2D-CNN) is proposed for the fault diagnosis of the rotation vector (RV) reducer installed on the industrial robot (IR). The proposed method can automatically extract the features from the data and reduce the connections between neurons and the parameters that need to be trained with its local receptive field, weight sharing, and subsampling features. Due to the aforementioned characteristics, the efficiency of network training is significantly improved, and verified by the experimental simulations. Comparative experiments with other mainstream methods are carried out to further validate the fault classification accuracy of the proposed method. The results indicate that the proposed method out-performs all the selected methods.
UR  - https://www.sv-jme.eu/article/fault-diagnosis-of-rotation-vector-reducer-for-industrial-robot-based-on-convolutional-neural-network/
Yang, Shuai, Luo, Xing, AND Li, Chuan.
"Fault Diagnosis of Rotation Vector Reducer for Industrial Robot Based on a Convolutional Neural Network" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 67 Number 10 (22 October 2021)

Authors

Affiliations

  • Chongqing Technology and Business University, National Research Base of Intelligent Manufacturing Service, China 1
  • Chongqing Technology and Business University, School of Management Science and Engineering, China 2

Paper's information

Strojniški vestnik - Journal of Mechanical Engineering 67(2021)10, 489-500

https://doi.org/10.5545/sv-jme.2021.7284

As a key component of a mechanical drive system, the failure of the reducer will usually cause huge economic losses and even lead to serious casualties in extreme cases. To solve this problem, a two-dimensional convolutional neural network (2D-CNN) is proposed for the fault diagnosis of the rotation vector (RV) reducer installed on the industrial robot (IR). The proposed method can automatically extract the features from the data and reduce the connections between neurons and the parameters that need to be trained with its local receptive field, weight sharing, and subsampling features. Due to the aforementioned characteristics, the efficiency of network training is significantly improved, and verified by the experimental simulations. Comparative experiments with other mainstream methods are carried out to further validate the fault classification accuracy of the proposed method. The results indicate that the proposed method out-performs all the selected methods.

fault diagnosis, convolutional neural network, RV reducer