High-Precision Peg-in-Hole Assembly with Flexible Components Based on Deep Reinforcement Learning
The lateral thrust device is a typical high-pressure sealed cavity structure with dual O-rings. Because the O-ring is easily damaged during the assembly process, the product quality is unqualified. To achieve high-precision assembly for this structure, this paper proposes a reinforcement learning as...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-04-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/12/5/287 |
| _version_ | 1831881685818408960 |
|---|---|
| author | Songkai Liu Geng Liu Xiaoyang Zhang |
| author_facet | Songkai Liu Geng Liu Xiaoyang Zhang |
| author_sort | Songkai Liu |
| collection | DOAJ |
| description | The lateral thrust device is a typical high-pressure sealed cavity structure with dual O-rings. Because the O-ring is easily damaged during the assembly process, the product quality is unqualified. To achieve high-precision assembly for this structure, this paper proposes a reinforcement learning assembly research method based on O-ring simulation. First, a simulation study of the damage mechanism during O-ring assembly is conducted using finite element software to obtain damage data under different deformation conditions. Secondly, deep reinforcement learning is used to plan the assembly path, resulting in high-precision assembly paths for the inner and outer cylinder under different initial poses. Experimental results demonstrate that the above method not only effectively solves the problem that the O-ring is easily damaged but also provides a novel, efficient, and practical assembly technique for similar high-precision assemblies. |
| first_indexed | 2025-03-21T22:21:07Z |
| format | Article |
| id | doaj.art-a3a6cb1526164196abc63b1e22aada30 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2025-03-21T22:21:07Z |
| publishDate | 2024-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-a3a6cb1526164196abc63b1e22aada302024-05-24T13:29:28ZengMDPI AGMachines2075-17022024-04-0112528710.3390/machines12050287High-Precision Peg-in-Hole Assembly with Flexible Components Based on Deep Reinforcement LearningSongkai Liu0Geng Liu1Xiaoyang Zhang2Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaThe lateral thrust device is a typical high-pressure sealed cavity structure with dual O-rings. Because the O-ring is easily damaged during the assembly process, the product quality is unqualified. To achieve high-precision assembly for this structure, this paper proposes a reinforcement learning assembly research method based on O-ring simulation. First, a simulation study of the damage mechanism during O-ring assembly is conducted using finite element software to obtain damage data under different deformation conditions. Secondly, deep reinforcement learning is used to plan the assembly path, resulting in high-precision assembly paths for the inner and outer cylinder under different initial poses. Experimental results demonstrate that the above method not only effectively solves the problem that the O-ring is easily damaged but also provides a novel, efficient, and practical assembly technique for similar high-precision assemblies.https://www.mdpi.com/2075-1702/12/5/287docking assemblyhigh precision dockingreinforcement learningdocking qualityassessment method |
| spellingShingle | Songkai Liu Geng Liu Xiaoyang Zhang High-Precision Peg-in-Hole Assembly with Flexible Components Based on Deep Reinforcement Learning Machines docking assembly high precision docking reinforcement learning docking quality assessment method |
| title | High-Precision Peg-in-Hole Assembly with Flexible Components Based on Deep Reinforcement Learning |
| title_full | High-Precision Peg-in-Hole Assembly with Flexible Components Based on Deep Reinforcement Learning |
| title_fullStr | High-Precision Peg-in-Hole Assembly with Flexible Components Based on Deep Reinforcement Learning |
| title_full_unstemmed | High-Precision Peg-in-Hole Assembly with Flexible Components Based on Deep Reinforcement Learning |
| title_short | High-Precision Peg-in-Hole Assembly with Flexible Components Based on Deep Reinforcement Learning |
| title_sort | high precision peg in hole assembly with flexible components based on deep reinforcement learning |
| topic | docking assembly high precision docking reinforcement learning docking quality assessment method |
| url | https://www.mdpi.com/2075-1702/12/5/287 |
| work_keys_str_mv | AT songkailiu highprecisionpeginholeassemblywithflexiblecomponentsbasedondeepreinforcementlearning AT gengliu highprecisionpeginholeassemblywithflexiblecomponentsbasedondeepreinforcementlearning AT xiaoyangzhang highprecisionpeginholeassemblywithflexiblecomponentsbasedondeepreinforcementlearning |