Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning

491 Ogledov
284 Prenosov
Izvoz citacije: ABNT
JIN, Zujin ;CHENG, Gang ;XU, Shichang ;YUAN, Dunpeng .
Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 68, n.3, p. 175-184, march 2022. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/sl/article/error-prediction-for-large-optical-mirror-processing-robot-based-on-deep-learning-2/>. Date accessed: 04 feb. 2023. 
doi:http://dx.doi.org/10.5545/sv-jme.2021.7455.
Jin, Z., Cheng, G., Xu, S., & Yuan, D.
(2022).
Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning.
Strojniški vestnik - Journal of Mechanical Engineering, 68(3), 175-184.
doi:http://dx.doi.org/10.5545/sv-jme.2021.7455
@article{sv-jmesv-jme.2021.7455,
	author = {Zujin  Jin and Gang  Cheng and Shichang  Xu and Dunpeng  Yuan},
	title = {Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {68},
	number = {3},
	year = {2022},
	keywords = {Bayesian optimization; BO-LSTM; error prediction; optical mirror processing; hybrid manipulator; hyperparametrics; },
	abstract = {Predicting the errors of a large optical mirror processing robot (LOMPR) is very important when studying a feedforward control error compensation strategy to improve the motion accuracy of the LOMPR. Therefore, an end trajectory error prediction model of a LOMPR based on a Bayesian optimized long short-term memory (BO-LSTM) was established. First, the batch size, number of hidden neurons and learning rate of LSTM were optimized using a Bayesian method. Then, the established prediction models were used to predict the errors in the X and Y directions of the spiral trajectory of the LOMPR, and the prediction results were compared with those of back-propagation (BP) neural network. The experimental results show that the training time of the BO-LSTM is reduced to 21.4 % and 15.2 %, respectively, in X and Y directions than that of the BP neural network. Moreover, the MSE, RMSE, and MAE of the prediction error in the X direction were reduced to 9.4 %, 30.5 %, and 31.8 %, respectively; the MSE, RMSE, and MAE of the prediction error in the Y direction were reduced to 9.6 %, 30.8 %, and 37.8 %, respectively. It is verified that the BO-LSTM prediction model could improve not only the accuracy of the end trajectory error prediction of the LOMPR but also the prediction efficiency, which provides a research basis for improving the surface accuracy of an optical mirror.},
	issn = {0039-2480},	pages = {175-184},	doi = {10.5545/sv-jme.2021.7455},
	url = {https://www.sv-jme.eu/sl/article/error-prediction-for-large-optical-mirror-processing-robot-based-on-deep-learning-2/}
}
Jin, Z.,Cheng, G.,Xu, S.,Yuan, D.
2022 March 68. Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 68:3
%A Jin, Zujin 
%A Cheng, Gang 
%A Xu, Shichang 
%A Yuan, Dunpeng 
%D 2022
%T Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning
%B 2022
%9 Bayesian optimization; BO-LSTM; error prediction; optical mirror processing; hybrid manipulator; hyperparametrics; 
%! Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning
%K Bayesian optimization; BO-LSTM; error prediction; optical mirror processing; hybrid manipulator; hyperparametrics; 
%X Predicting the errors of a large optical mirror processing robot (LOMPR) is very important when studying a feedforward control error compensation strategy to improve the motion accuracy of the LOMPR. Therefore, an end trajectory error prediction model of a LOMPR based on a Bayesian optimized long short-term memory (BO-LSTM) was established. First, the batch size, number of hidden neurons and learning rate of LSTM were optimized using a Bayesian method. Then, the established prediction models were used to predict the errors in the X and Y directions of the spiral trajectory of the LOMPR, and the prediction results were compared with those of back-propagation (BP) neural network. The experimental results show that the training time of the BO-LSTM is reduced to 21.4 % and 15.2 %, respectively, in X and Y directions than that of the BP neural network. Moreover, the MSE, RMSE, and MAE of the prediction error in the X direction were reduced to 9.4 %, 30.5 %, and 31.8 %, respectively; the MSE, RMSE, and MAE of the prediction error in the Y direction were reduced to 9.6 %, 30.8 %, and 37.8 %, respectively. It is verified that the BO-LSTM prediction model could improve not only the accuracy of the end trajectory error prediction of the LOMPR but also the prediction efficiency, which provides a research basis for improving the surface accuracy of an optical mirror.
%U https://www.sv-jme.eu/sl/article/error-prediction-for-large-optical-mirror-processing-robot-based-on-deep-learning-2/
%0 Journal Article
%R 10.5545/sv-jme.2021.7455
%& 175
%P 10
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 68
%N 3
%@ 0039-2480
%8 2022-03-15
%7 2022-03-15
Jin, Zujin, Gang  Cheng, Shichang  Xu, & Dunpeng  Yuan.
"Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning." Strojniški vestnik - Journal of Mechanical Engineering [Online], 68.3 (2022): 175-184. Web.  04 Feb. 2023
TY  - JOUR
AU  - Jin, Zujin 
AU  - Cheng, Gang 
AU  - Xu, Shichang 
AU  - Yuan, Dunpeng 
PY  - 2022
TI  - Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2021.7455
KW  - Bayesian optimization; BO-LSTM; error prediction; optical mirror processing; hybrid manipulator; hyperparametrics; 
N2  - Predicting the errors of a large optical mirror processing robot (LOMPR) is very important when studying a feedforward control error compensation strategy to improve the motion accuracy of the LOMPR. Therefore, an end trajectory error prediction model of a LOMPR based on a Bayesian optimized long short-term memory (BO-LSTM) was established. First, the batch size, number of hidden neurons and learning rate of LSTM were optimized using a Bayesian method. Then, the established prediction models were used to predict the errors in the X and Y directions of the spiral trajectory of the LOMPR, and the prediction results were compared with those of back-propagation (BP) neural network. The experimental results show that the training time of the BO-LSTM is reduced to 21.4 % and 15.2 %, respectively, in X and Y directions than that of the BP neural network. Moreover, the MSE, RMSE, and MAE of the prediction error in the X direction were reduced to 9.4 %, 30.5 %, and 31.8 %, respectively; the MSE, RMSE, and MAE of the prediction error in the Y direction were reduced to 9.6 %, 30.8 %, and 37.8 %, respectively. It is verified that the BO-LSTM prediction model could improve not only the accuracy of the end trajectory error prediction of the LOMPR but also the prediction efficiency, which provides a research basis for improving the surface accuracy of an optical mirror.
UR  - https://www.sv-jme.eu/sl/article/error-prediction-for-large-optical-mirror-processing-robot-based-on-deep-learning-2/
@article{{sv-jme}{sv-jme.2021.7455},
	author = {Jin, Z., Cheng, G., Xu, S., Yuan, D.},
	title = {Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {68},
	number = {3},
	year = {2022},
	doi = {10.5545/sv-jme.2021.7455},
	url = {https://www.sv-jme.eu/sl/article/error-prediction-for-large-optical-mirror-processing-robot-based-on-deep-learning-2/}
}
TY  - JOUR
AU  - Jin, Zujin 
AU  - Cheng, Gang 
AU  - Xu, Shichang 
AU  - Yuan, Dunpeng 
PY  - 2022/03/15
TI  - Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 68, No 3 (2022): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2021.7455
KW  - Bayesian optimization, BO-LSTM, error prediction, optical mirror processing, hybrid manipulator, hyperparametrics, 
N2  - Predicting the errors of a large optical mirror processing robot (LOMPR) is very important when studying a feedforward control error compensation strategy to improve the motion accuracy of the LOMPR. Therefore, an end trajectory error prediction model of a LOMPR based on a Bayesian optimized long short-term memory (BO-LSTM) was established. First, the batch size, number of hidden neurons and learning rate of LSTM were optimized using a Bayesian method. Then, the established prediction models were used to predict the errors in the X and Y directions of the spiral trajectory of the LOMPR, and the prediction results were compared with those of back-propagation (BP) neural network. The experimental results show that the training time of the BO-LSTM is reduced to 21.4 % and 15.2 %, respectively, in X and Y directions than that of the BP neural network. Moreover, the MSE, RMSE, and MAE of the prediction error in the X direction were reduced to 9.4 %, 30.5 %, and 31.8 %, respectively; the MSE, RMSE, and MAE of the prediction error in the Y direction were reduced to 9.6 %, 30.8 %, and 37.8 %, respectively. It is verified that the BO-LSTM prediction model could improve not only the accuracy of the end trajectory error prediction of the LOMPR but also the prediction efficiency, which provides a research basis for improving the surface accuracy of an optical mirror.
UR  - https://www.sv-jme.eu/sl/article/error-prediction-for-large-optical-mirror-processing-robot-based-on-deep-learning-2/
Jin, Zujin, Cheng, Gang, Xu, Shichang, AND Yuan, Dunpeng.
"Error Prediction for Large Optical Mirror Processing Robot Based on Deep Learning" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 68 Number 3 (15 March 2022)

Avtorji

Inštitucije

  • China University of Mining and Technology, School of Mechatronic Engineering, China 1

Informacije o papirju

Strojniški vestnik - Journal of Mechanical Engineering 68(2022)3, 175-184
© The Authors 2022. CC BY 4.0 Int.

https://doi.org/10.5545/sv-jme.2021.7455

Predicting the errors of a large optical mirror processing robot (LOMPR) is very important when studying a feedforward control error compensation strategy to improve the motion accuracy of the LOMPR. Therefore, an end trajectory error prediction model of a LOMPR based on a Bayesian optimized long short-term memory (BO-LSTM) was established. First, the batch size, number of hidden neurons and learning rate of LSTM were optimized using a Bayesian method. Then, the established prediction models were used to predict the errors in the X and Y directions of the spiral trajectory of the LOMPR, and the prediction results were compared with those of back-propagation (BP) neural network. The experimental results show that the training time of the BO-LSTM is reduced to 21.4 % and 15.2 %, respectively, in X and Y directions than that of the BP neural network. Moreover, the MSE, RMSE, and MAE of the prediction error in the X direction were reduced to 9.4 %, 30.5 %, and 31.8 %, respectively; the MSE, RMSE, and MAE of the prediction error in the Y direction were reduced to 9.6 %, 30.8 %, and 37.8 %, respectively. It is verified that the BO-LSTM prediction model could improve not only the accuracy of the end trajectory error prediction of the LOMPR but also the prediction efficiency, which provides a research basis for improving the surface accuracy of an optical mirror.

Bayesian optimization; BO-LSTM; error prediction; optical mirror processing; hybrid manipulator; hyperparametrics;