In-situ defect detection in laser-directed energy deposition with machine learning and multi-sensor fusion
Early defect identification in laser-directed energy deposition (L-DED) additive manufacturing (AM) is pivotal for preventing build failures. Traditional single-modal monitoring approaches lack the capability to fully comprehend process dynamics, leading to a gap in multisensor monitoring strategies...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/180840 |
| _version_ | 1826123536118317056 |
|---|---|
| author | Chen, Lequn Moon, Seung Ki |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Chen, Lequn Moon, Seung Ki |
| author_sort | Chen, Lequn |
| collection | NTU |
| description | Early defect identification in laser-directed energy deposition (L-DED) additive manufacturing (AM) is pivotal for preventing build failures. Traditional single-modal monitoring approaches lack the capability to fully comprehend process dynamics, leading to a gap in multisensor monitoring strategies. This research proposes a novel in-situ monitoring method using a multi-sensor fusion-based digital twin (MFDT) for localized quality prediction, coupled with machine learning (ML) models for data fusion. It investigates acoustic signals from laser-material interactions as defect indicators, crafting a ML-based pipeline for rapid defect detection via feature extraction, fusion, and classification. This approach not only explores acoustic features across multiple domains, as well as coaxial melt pool images for ML model training, but it also introduces a novel MFDT framework that combines data from coaxial melt pool vision cameras and microphones, synchronized with robotic movements, to predict localized quality attributes. The key novelty in this research is the exploration of intra-modality and cross-modality multisensor feature correlations, revealing key vision and acoustic signatures associated with varying process dynamics. A comprehensive understanding of how multi-sensor signature varies with process dynamics improves the effectiveness of the proposed multi-sensor fusion model. The proposed model outperforms conventional methods with a 96.4 % accuracy, thereby setting a solid foundation for future self-adaptive quality improvement strategies in AM. |
| first_indexed | 2025-03-09T13:31:54Z |
| format | Journal Article |
| id | ntu-10356/180840 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-03-09T13:31:54Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1808402024-10-29T05:23:21Z In-situ defect detection in laser-directed energy deposition with machine learning and multi-sensor fusion Chen, Lequn Moon, Seung Ki School of Mechanical and Aerospace Engineering Advanced Remanufacturing and Technology Centre, A*STAR Engineering Additive manufacturing In-situ monitoring Early defect identification in laser-directed energy deposition (L-DED) additive manufacturing (AM) is pivotal for preventing build failures. Traditional single-modal monitoring approaches lack the capability to fully comprehend process dynamics, leading to a gap in multisensor monitoring strategies. This research proposes a novel in-situ monitoring method using a multi-sensor fusion-based digital twin (MFDT) for localized quality prediction, coupled with machine learning (ML) models for data fusion. It investigates acoustic signals from laser-material interactions as defect indicators, crafting a ML-based pipeline for rapid defect detection via feature extraction, fusion, and classification. This approach not only explores acoustic features across multiple domains, as well as coaxial melt pool images for ML model training, but it also introduces a novel MFDT framework that combines data from coaxial melt pool vision cameras and microphones, synchronized with robotic movements, to predict localized quality attributes. The key novelty in this research is the exploration of intra-modality and cross-modality multisensor feature correlations, revealing key vision and acoustic signatures associated with varying process dynamics. A comprehensive understanding of how multi-sensor signature varies with process dynamics improves the effectiveness of the proposed multi-sensor fusion model. The proposed model outperforms conventional methods with a 96.4 % accuracy, thereby setting a solid foundation for future self-adaptive quality improvement strategies in AM. Agency for Science, Technology and Research (A*STAR) Nanyang Technological University National Research Foundation (NRF) This research is funded by the Agency for Science, Technology and Research (A*STAR) of Singapore through the Career Development Fund (Grant No. C210812030), and RIE2025 MTC IAF-PP grant (Grant No. M22K5a0045). It is supported by Singapore Centre for 3D Printing (SC3DP), the National Research Foundation, Prime Minister's Office, Singapore under its Medium-Sized Centre funding scheme. It is conducted with the support of the Industrial Technology Innovation Program (KEIT project no. 20023042, Demonstration of an intelligent DED system for reducing process time) funded by the Ministry of Trade, Industry & Energy of the Republic of Korea. 2024-10-29T05:23:21Z 2024-10-29T05:23:21Z 2024 Journal Article Chen, L. & Moon, S. K. (2024). In-situ defect detection in laser-directed energy deposition with machine learning and multi-sensor fusion. Journal of Mechanical Science and Technology, 38(9), 4477-4484. https://dx.doi.org/10.1007/s12206-024-2401-1 1738-494X https://hdl.handle.net/10356/180840 10.1007/s12206-024-2401-1 2-s2.0-85203069960 9 38 4477 4484 en C210812030 M22K5a0045 Journal of Mechanical Science and Technology © 2024 The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature. All rights reserved. |
| spellingShingle | Engineering Additive manufacturing In-situ monitoring Chen, Lequn Moon, Seung Ki In-situ defect detection in laser-directed energy deposition with machine learning and multi-sensor fusion |
| title | In-situ defect detection in laser-directed energy deposition with machine learning and multi-sensor fusion |
| title_full | In-situ defect detection in laser-directed energy deposition with machine learning and multi-sensor fusion |
| title_fullStr | In-situ defect detection in laser-directed energy deposition with machine learning and multi-sensor fusion |
| title_full_unstemmed | In-situ defect detection in laser-directed energy deposition with machine learning and multi-sensor fusion |
| title_short | In-situ defect detection in laser-directed energy deposition with machine learning and multi-sensor fusion |
| title_sort | in situ defect detection in laser directed energy deposition with machine learning and multi sensor fusion |
| topic | Engineering Additive manufacturing In-situ monitoring |
| url | https://hdl.handle.net/10356/180840 |
| work_keys_str_mv | AT chenlequn insitudefectdetectioninlaserdirectedenergydepositionwithmachinelearningandmultisensorfusion AT moonseungki insitudefectdetectioninlaserdirectedenergydepositionwithmachinelearningandmultisensorfusion |