Semi-supervised machine learning of optical in-situ monitoring data for anomaly detection in laser powder bed fusion
Laser powder bed fusion (L-PBF) is one of the most widely used metal additive manufacturing technology for fabrication of functional and structural components. However, inconsistency in quality and reliability of L-PBF products is still a significant barrier preventing it from wider adoption. Machin...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/168586 |
| _version_ | 1811680419603546112 |
|---|---|
| author | Nguyen, Ngoc Vu Hum, Allen Jun Wee Do, Truong Tran, Tuan |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Nguyen, Ngoc Vu Hum, Allen Jun Wee Do, Truong Tran, Tuan |
| author_sort | Nguyen, Ngoc Vu |
| collection | NTU |
| description | Laser powder bed fusion (L-PBF) is one of the most widely used metal additive manufacturing technology for fabrication of functional and structural components. However, inconsistency in quality and reliability of L-PBF products is still a significant barrier preventing it from wider adoption. Machine learning (ML) of monitoring data offers a unique solution to effectively identify possible defects and predict the quality of L-PBF products. In this work, we introduce a semi-supervised ML approach to detect anomalies that occurred in L-PBF products. We train the ML model to classify surface appearances in the reference monitoring data. We then correlate the classified appearances to post-process characteristics, e.g. surface roughness, morphology, or tensile strength. We demonstrate that the established correlation enables the determination of key appearances indicative of the quality of the printed samples including anomaly-free, lack-of-fusion and overheated. We further validate our ML approach by performing prediction on test samples having various geometries. |
| first_indexed | 2024-10-01T03:24:45Z |
| format | Journal Article |
| id | ntu-10356/168586 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:24:45Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1685862023-06-07T15:37:29Z Semi-supervised machine learning of optical in-situ monitoring data for anomaly detection in laser powder bed fusion Nguyen, Ngoc Vu Hum, Allen Jun Wee Do, Truong Tran, Tuan School of Mechanical and Aerospace Engineering Singapore Centre for 3D Printing Engineering::Mechanical engineering Machine Learning Additive Manufacturing Laser powder bed fusion (L-PBF) is one of the most widely used metal additive manufacturing technology for fabrication of functional and structural components. However, inconsistency in quality and reliability of L-PBF products is still a significant barrier preventing it from wider adoption. Machine learning (ML) of monitoring data offers a unique solution to effectively identify possible defects and predict the quality of L-PBF products. In this work, we introduce a semi-supervised ML approach to detect anomalies that occurred in L-PBF products. We train the ML model to classify surface appearances in the reference monitoring data. We then correlate the classified appearances to post-process characteristics, e.g. surface roughness, morphology, or tensile strength. We demonstrate that the established correlation enables the determination of key appearances indicative of the quality of the printed samples including anomaly-free, lack-of-fusion and overheated. We further validate our ML approach by performing prediction on test samples having various geometries. National Research Foundation (NRF) Published version This research is supported by Republic of Singapore’s National Research Foundation Singapore under its Innovation Cluster Programme (NAMIC), and VinUniversity, Vietnam. 2023-06-06T08:05:14Z 2023-06-06T08:05:14Z 2023 Journal Article Nguyen, N. V., Hum, A. J. W., Do, T. & Tran, T. (2023). Semi-supervised machine learning of optical in-situ monitoring data for anomaly detection in laser powder bed fusion. Virtual and Physical Prototyping, 18(1), e2129396-. https://dx.doi.org/10.1080/17452759.2022.2129396 1745-2759 https://hdl.handle.net/10356/168586 10.1080/17452759.2022.2129396 2-s2.0-85140835770 1 18 e2129396 en Virtual and Physical Prototyping © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. application/pdf |
| spellingShingle | Engineering::Mechanical engineering Machine Learning Additive Manufacturing Nguyen, Ngoc Vu Hum, Allen Jun Wee Do, Truong Tran, Tuan Semi-supervised machine learning of optical in-situ monitoring data for anomaly detection in laser powder bed fusion |
| title | Semi-supervised machine learning of optical in-situ monitoring data for anomaly detection in laser powder bed fusion |
| title_full | Semi-supervised machine learning of optical in-situ monitoring data for anomaly detection in laser powder bed fusion |
| title_fullStr | Semi-supervised machine learning of optical in-situ monitoring data for anomaly detection in laser powder bed fusion |
| title_full_unstemmed | Semi-supervised machine learning of optical in-situ monitoring data for anomaly detection in laser powder bed fusion |
| title_short | Semi-supervised machine learning of optical in-situ monitoring data for anomaly detection in laser powder bed fusion |
| title_sort | semi supervised machine learning of optical in situ monitoring data for anomaly detection in laser powder bed fusion |
| topic | Engineering::Mechanical engineering Machine Learning Additive Manufacturing |
| url | https://hdl.handle.net/10356/168586 |
| work_keys_str_mv | AT nguyenngocvu semisupervisedmachinelearningofopticalinsitumonitoringdataforanomalydetectioninlaserpowderbedfusion AT humallenjunwee semisupervisedmachinelearningofopticalinsitumonitoringdataforanomalydetectioninlaserpowderbedfusion AT dotruong semisupervisedmachinelearningofopticalinsitumonitoringdataforanomalydetectioninlaserpowderbedfusion AT trantuan semisupervisedmachinelearningofopticalinsitumonitoringdataforanomalydetectioninlaserpowderbedfusion |