In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process
This paper proposes a novel approach for inprocess endpoint detection of weld seam removal during robotic abrasive belt grinding process using discrete wavelet transform (DWT) and support vector machine (SVM). A virtual sensing system is developed consisting of a force sensor, accelerometer sen...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/105856 http://hdl.handle.net/10220/48132 |
| _version_ | 1826130113595441152 |
|---|---|
| author | Pandiyan, Vigneashwara Tjahjowidodo, Tegoeh |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Pandiyan, Vigneashwara Tjahjowidodo, Tegoeh |
| author_sort | Pandiyan, Vigneashwara |
| collection | NTU |
| description | This paper proposes a novel approach for inprocess
endpoint detection of weld seam removal during robotic
abrasive belt grinding process using discrete wavelet
transform (DWT) and support vector machine (SVM). A virtual
sensing system is developed consisting of a force sensor,
accelerometer sensor and machine learning algorithm. This
work also presents the trend of the sensor signature at each
stage of weld seam evolution during its removal process. The
wavelet decomposition coefficient is used to represent all possible
types of transients in vibration and force signals generated
during grinding over weld seam. “Daubechies-4” wavelet
function was used to extract features from the sensors. An
experimental investigation using three different weld profile
conditions resulting from the weld seam removal process
using abrasive belt grinding was identified. The SVM-based
classifier was employed to predict the weld state. The results
demonstrate that the developed diagnostic methodology can
reliably predict endpoint at which weld seam is removed in
real time during compliant abrasive belt grinding. |
| first_indexed | 2024-10-01T07:51:32Z |
| format | Journal Article |
| id | ntu-10356/105856 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:51:32Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/1058562023-03-04T17:21:34Z In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process Pandiyan, Vigneashwara Tjahjowidodo, Tegoeh School of Mechanical and Aerospace Engineering Rolls-Royce@NTU Corporate Lab Abrasive Belt Grinding DWT DRNTU::Engineering::Mechanical engineering This paper proposes a novel approach for inprocess endpoint detection of weld seam removal during robotic abrasive belt grinding process using discrete wavelet transform (DWT) and support vector machine (SVM). A virtual sensing system is developed consisting of a force sensor, accelerometer sensor and machine learning algorithm. This work also presents the trend of the sensor signature at each stage of weld seam evolution during its removal process. The wavelet decomposition coefficient is used to represent all possible types of transients in vibration and force signals generated during grinding over weld seam. “Daubechies-4” wavelet function was used to extract features from the sensors. An experimental investigation using three different weld profile conditions resulting from the weld seam removal process using abrasive belt grinding was identified. The SVM-based classifier was employed to predict the weld state. The results demonstrate that the developed diagnostic methodology can reliably predict endpoint at which weld seam is removed in real time during compliant abrasive belt grinding. NRF (Natl Research Foundation, S’pore) Accepted version 2019-05-09T01:28:57Z 2019-12-06T21:59:20Z 2019-05-09T01:28:57Z 2019-12-06T21:59:20Z 2017 Journal Article Pandiyan, V., & Tjahjowidodo, T. (2017). In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process. The International Journal of Advanced Manufacturing Technology, 93(5-8), 1699-1714. doi:10.1007/s00170-017-0646-x 0268-3768 https://hdl.handle.net/10356/105856 http://hdl.handle.net/10220/48132 10.1007/s00170-017-0646-x en The International Journal of Advanced Manufacturing Technology © 2017 Springer-Verlag London Ltd. All rights reserved. This paper was published in The International Journal of Advanced Manufacturing Technology and is made available with permission of Springer-Verlag London Ltd. 21 p. application/pdf |
| spellingShingle | Abrasive Belt Grinding DWT DRNTU::Engineering::Mechanical engineering Pandiyan, Vigneashwara Tjahjowidodo, Tegoeh In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process |
| title | In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process |
| title_full | In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process |
| title_fullStr | In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process |
| title_full_unstemmed | In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process |
| title_short | In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process |
| title_sort | in process endpoint detection of weld seam removal in robotic abrasive belt grinding process |
| topic | Abrasive Belt Grinding DWT DRNTU::Engineering::Mechanical engineering |
| url | https://hdl.handle.net/10356/105856 http://hdl.handle.net/10220/48132 |
| work_keys_str_mv | AT pandiyanvigneashwara inprocessendpointdetectionofweldseamremovalinroboticabrasivebeltgrindingprocess AT tjahjowidodotegoeh inprocessendpointdetectionofweldseamremovalinroboticabrasivebeltgrindingprocess |