A GAN-BPNN-Based Surface Roughness Measurement Method for Robotic Grinding
Existing machine vision-based roughness measurement methods cannot accurately measure the roughness of free-form surfaces (with large curvature variations). To overcome this problem, this paper proposes a roughness measurement method based on a generative adversarial network (GAN) and a BP neural ne...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/10/11/1026 |
| _version_ | 1797467504647340032 |
|---|---|
| author | Guojun Zhang Changyuan Liu Kang Min Hong Liu Fenglei Ni |
| author_facet | Guojun Zhang Changyuan Liu Kang Min Hong Liu Fenglei Ni |
| author_sort | Guojun Zhang |
| collection | DOAJ |
| description | Existing machine vision-based roughness measurement methods cannot accurately measure the roughness of free-form surfaces (with large curvature variations). To overcome this problem, this paper proposes a roughness measurement method based on a generative adversarial network (GAN) and a BP neural network. Firstly, this method takes images and curvature of free-form surfaces as training samples. Then, GAN is trained for roughness measurement through each game between generator and discriminant network by using real samples and pseudosamples (from generator). Finally, the BP neural network maps the image discriminant value of GAN and radius of curvature into roughness value (Ra). Our proposed method automatically learns the features in the image by GAN, omitting the independent feature extraction step, and improves the measurement accuracy by BP neural network. The experiments show that the accuracy of the proposed roughness measurement method can measure free-form surfaces with a minimum roughness of 0.2 μm, and measurement results have a margin of 10%. |
| first_indexed | 2024-03-09T18:54:37Z |
| format | Article |
| id | doaj.art-38ed1f57ced2482db0e9a5397ff8aa61 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-09T18:54:37Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-38ed1f57ced2482db0e9a5397ff8aa612023-11-24T05:33:09ZengMDPI AGMachines2075-17022022-11-011011102610.3390/machines10111026A GAN-BPNN-Based Surface Roughness Measurement Method for Robotic GrindingGuojun Zhang0Changyuan Liu1Kang Min2Hong Liu3Fenglei Ni4Department of State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, ChinaDepartment of State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, ChinaDepartment of State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, ChinaDepartment of State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, ChinaDepartment of State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, ChinaExisting machine vision-based roughness measurement methods cannot accurately measure the roughness of free-form surfaces (with large curvature variations). To overcome this problem, this paper proposes a roughness measurement method based on a generative adversarial network (GAN) and a BP neural network. Firstly, this method takes images and curvature of free-form surfaces as training samples. Then, GAN is trained for roughness measurement through each game between generator and discriminant network by using real samples and pseudosamples (from generator). Finally, the BP neural network maps the image discriminant value of GAN and radius of curvature into roughness value (Ra). Our proposed method automatically learns the features in the image by GAN, omitting the independent feature extraction step, and improves the measurement accuracy by BP neural network. The experiments show that the accuracy of the proposed roughness measurement method can measure free-form surfaces with a minimum roughness of 0.2 μm, and measurement results have a margin of 10%.https://www.mdpi.com/2075-1702/10/11/1026robotic belt grindingsurface roughness measurementgenerative adversarial network |
| spellingShingle | Guojun Zhang Changyuan Liu Kang Min Hong Liu Fenglei Ni A GAN-BPNN-Based Surface Roughness Measurement Method for Robotic Grinding Machines robotic belt grinding surface roughness measurement generative adversarial network |
| title | A GAN-BPNN-Based Surface Roughness Measurement Method for Robotic Grinding |
| title_full | A GAN-BPNN-Based Surface Roughness Measurement Method for Robotic Grinding |
| title_fullStr | A GAN-BPNN-Based Surface Roughness Measurement Method for Robotic Grinding |
| title_full_unstemmed | A GAN-BPNN-Based Surface Roughness Measurement Method for Robotic Grinding |
| title_short | A GAN-BPNN-Based Surface Roughness Measurement Method for Robotic Grinding |
| title_sort | gan bpnn based surface roughness measurement method for robotic grinding |
| topic | robotic belt grinding surface roughness measurement generative adversarial network |
| url | https://www.mdpi.com/2075-1702/10/11/1026 |
| work_keys_str_mv | AT guojunzhang aganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding AT changyuanliu aganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding AT kangmin aganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding AT hongliu aganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding AT fengleini aganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding AT guojunzhang ganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding AT changyuanliu ganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding AT kangmin ganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding AT hongliu ganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding AT fengleini ganbpnnbasedsurfaceroughnessmeasurementmethodforroboticgrinding |