Error prediction for large optical mirror processing robot based on deep learning

Jin, Zujin (author), Cheng, Gang (author), Xu, Shichang (author), Yuan, Dunpeng (author)

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.

• Language: English
• Keywords: Bayesian optimization, error prediction, optical mirror processing, hybrid manipulators, hyperparametrics, deep learning
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FS - Faculty of Mechanical Engineering
• Publication status: Published
• Publication version: Version of Record
• Publication date: 01.03.2022
• Year: 2022
• Number of pages: Str. 175-184
• Numbering: Vol. 68, no. 3
• PID: 20.500.12556/RUL-136403
• UDC: 007.52:620.19
• ISSN on article: 0039-2480
• DOI: 10.5545/sv-jme.2021.7455
• COBISS.SI-ID: 105665027
• Publication date in RUL: 29.04.2022

Record is a part of a journal

• Title: Strojniški vestnik
• Shortened title: Stroj. vestn.
• Publisher: Zveza strojnih inženirjev in tehnikov Slovenije [etc.], = Association of Mechanical Engineers and Technicians of Slovenia [etc.
• ISSN: 0039-2480
• COBISS.SI-ID: 762116

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.
• Licensing start date: 09.02.2022
• Applies to: Accepted for publication

Secondary language

• Language: Slovenian
• Title: Napovedovanje napak robotov za obdelavo velikih optičnih zrcal na osnovi globokega učenja
• Keywords: Bayesova optimizacija, napovedovanje napak, obdelava optičnih zrcal, hibridni manipulatorji, hiperparametrika, globoko učenej

Projects

• Funder: Other - Other funder or multiple funders
• Funding programme: Financial support for this work, provided by the Priority Academic Program Development of Jiangsu Higher Education Institutions

• Funder: Other - Other funder or multiple funders
• Funding programme: National Key R&D Program of China