Robotics and Computer-Integrated Manufacturing
Transforming the manufacturing environment from manually operated production units to unsupervised robotic machining centres requires a presence of reliable in-process monitoring system. In this paper, we demonstrate a technique for automatic endpoint detection of weld seam removal in a robotic ab...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/104889 http://hdl.handle.net/10220/48057 |
| _version_ | 1826115155458523136 |
|---|---|
| author | Pandiyan, Vigneashwara Murugan, Pushparaja Tjahjowidodo, Tegoeh Caesarendra, Wahyu Manyar, Omey Mohan Then, David Jin Hong |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Pandiyan, Vigneashwara Murugan, Pushparaja Tjahjowidodo, Tegoeh Caesarendra, Wahyu Manyar, Omey Mohan Then, David Jin Hong |
| author_sort | Pandiyan, Vigneashwara |
| collection | NTU |
| description | Transforming the manufacturing environment from manually operated production units to unsupervised robotic
machining centres requires a presence of reliable in-process monitoring system. In this paper, we demonstrate a
technique for automatic endpoint detection of weld seam removal in a robotic abrasive belt grinding process
with the help of a vision system using deep learning. The paper presents the results of the first investigative stage
of semantic segmentation of weld seam removal states using encoder-decoder convolutional neural networks
(EDCNN). An experimental investigation using four different weld seam states on mild steel work coupon are
trained using the VGG-16 network based on encoder-decoder architecture. The results demonstrate the potential
of the developed vision based methodology as a tool for endpoint prediction of the weld seam removal in real
time during a compliant abrasive belt grinding process. The prediction system based on semantic segmentation is
able to monitor weld profile geometry evolution taking into account the varying belt grinding parameters during
machining which will allow further process optimisation. |
| first_indexed | 2024-10-01T03:50:55Z |
| format | Journal Article |
| id | ntu-10356/104889 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:50:55Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/1048892023-03-04T17:11:24Z Robotics and Computer-Integrated Manufacturing Pandiyan, Vigneashwara Murugan, Pushparaja Tjahjowidodo, Tegoeh Caesarendra, Wahyu Manyar, Omey Mohan Then, David Jin Hong School of Mechanical and Aerospace Engineering Rolls-Royce@NTU Corporate Lab Deep Learning Abrasive Belt Grinding DRNTU::Engineering::Mechanical engineering Transforming the manufacturing environment from manually operated production units to unsupervised robotic machining centres requires a presence of reliable in-process monitoring system. In this paper, we demonstrate a technique for automatic endpoint detection of weld seam removal in a robotic abrasive belt grinding process with the help of a vision system using deep learning. The paper presents the results of the first investigative stage of semantic segmentation of weld seam removal states using encoder-decoder convolutional neural networks (EDCNN). An experimental investigation using four different weld seam states on mild steel work coupon are trained using the VGG-16 network based on encoder-decoder architecture. The results demonstrate the potential of the developed vision based methodology as a tool for endpoint prediction of the weld seam removal in real time during a compliant abrasive belt grinding process. The prediction system based on semantic segmentation is able to monitor weld profile geometry evolution taking into account the varying belt grinding parameters during machining which will allow further process optimisation. Accepted version 2019-04-23T06:46:37Z 2019-12-06T21:42:02Z 2019-04-23T06:46:37Z 2019-12-06T21:42:02Z 2019 Journal Article Pandiyan, V., Murugan, P., Tjahjowidodo, T., Caesarendra, W., Manyar, O. M., & Then, D. J. H. (2019). In-process virtual verification of weld seam removal in robotic abrasive belt grinding process using deep learning. Robotics and Computer-Integrated Manufacturing, 57, 477-487. doi:10.1016/j.rcim.2019.01.006 0736-5845 https://hdl.handle.net/10356/104889 http://hdl.handle.net/10220/48057 10.1016/j.rcim.2019.01.006 57 477 487 en Robotics and Computer-Integrated Manufacturing © 2019 Elsevier. All rights reserved. This paper was published in Robotics and Computer-Integrated Manufacturing and is made available with permission of Elsevier. 15 p. application/pdf |
| spellingShingle | Deep Learning Abrasive Belt Grinding DRNTU::Engineering::Mechanical engineering Pandiyan, Vigneashwara Murugan, Pushparaja Tjahjowidodo, Tegoeh Caesarendra, Wahyu Manyar, Omey Mohan Then, David Jin Hong Robotics and Computer-Integrated Manufacturing |
| title | Robotics and Computer-Integrated Manufacturing |
| title_full | Robotics and Computer-Integrated Manufacturing |
| title_fullStr | Robotics and Computer-Integrated Manufacturing |
| title_full_unstemmed | Robotics and Computer-Integrated Manufacturing |
| title_short | Robotics and Computer-Integrated Manufacturing |
| title_sort | robotics and computer integrated manufacturing |
| topic | Deep Learning Abrasive Belt Grinding DRNTU::Engineering::Mechanical engineering |
| url | https://hdl.handle.net/10356/104889 http://hdl.handle.net/10220/48057 |
| work_keys_str_mv | AT pandiyanvigneashwara roboticsandcomputerintegratedmanufacturing AT muruganpushparaja roboticsandcomputerintegratedmanufacturing AT tjahjowidodotegoeh roboticsandcomputerintegratedmanufacturing AT caesarendrawahyu roboticsandcomputerintegratedmanufacturing AT manyaromeymohan roboticsandcomputerintegratedmanufacturing AT thendavidjinhong roboticsandcomputerintegratedmanufacturing |