Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing
Finding actionable trends in laser-based metal additive manufacturing process monitoring data is challenging owing to the diversity and complexity of the underlying physical interactions. A single monitoring solution that captures a particular process phenomenon, such as a photodiode that tracks mel...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-09-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S026412752200541X |
| _version_ | 1817998515375177728 |
|---|---|
| author | Aniruddha Gaikwad Richard J. Williams Harry de Winton Benjamin D. Bevans Ziyad Smoqi Prahalada Rao Paul A. Hooper |
| author_facet | Aniruddha Gaikwad Richard J. Williams Harry de Winton Benjamin D. Bevans Ziyad Smoqi Prahalada Rao Paul A. Hooper |
| author_sort | Aniruddha Gaikwad |
| collection | DOAJ |
| description | Finding actionable trends in laser-based metal additive manufacturing process monitoring data is challenging owing to the diversity and complexity of the underlying physical interactions. A single monitoring solution that captures a particular process phenomenon, such as a photodiode that tracks melt pool intensity, is not alone capable of evaluating process stability or detecting flaw formation with sufficient precision for routine application in industry. In this work, to improve flaw detection performance, we adopted a data fusion approach that captures multiple process phenomena. To demonstrate this, we acquired data from laser powder bed fusion (LPBF) builds of cylindrical specimens produced with different laser spot sizes, emulating defocusing due to process faults such as thermal lensing. The resulting specimens had porosity of varying types and severity, quantified by post-build non-destructive X-ray computed tomography, Archimedes density measurements, and destructive metallographic characterization. During the build, the melt pool state was monitored with two coaxial high-speed video cameras and a temperature field imaging system. Physically intuitive low-level melt pool signatures, such as melt pool temperature, shape and size, and spatter intensity were extracted from this high-dimensional, image-based sensor data. These process signatures were subsequently used as input features in relatively simple machine learning models, such as a support vector machine, which were trained to detect laser defocusing, and in addition, predict porosity type and severity. The results show that the data fusion approach significantly enhanced system performance by reducing the overall false positive rate from ∼ 0.1 to ∼ 0.001 without sacrificing the true positive rate (∼0.90). These results were at par with a black-box, deep machine learning approach (convolutional neural network). |
| first_indexed | 2024-04-14T02:54:14Z |
| format | Article |
| id | doaj.art-089fb9ba0b444070a8b3d059811e37e9 |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-04-14T02:54:14Z |
| publishDate | 2022-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-089fb9ba0b444070a8b3d059811e37e92022-12-22T02:16:10ZengElsevierMaterials & Design0264-12752022-09-01221110919Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturingAniruddha Gaikwad0Richard J. Williams1Harry de Winton2Benjamin D. Bevans3Ziyad Smoqi4Prahalada Rao5Paul A. Hooper6Mechanical and Materials Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA; Corresponding author.Mechanical Engineering, Imperial College, London, UKMechanical Engineering, Imperial College, London, UKMechanical and Materials Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA; Grado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA, USAMechanical and Materials Engineering, University of Nebraska-Lincoln, Lincoln, NE, USAMechanical and Materials Engineering, University of Nebraska-Lincoln, Lincoln, NE, USA; Grado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA, USAMechanical Engineering, Imperial College, London, UKFinding actionable trends in laser-based metal additive manufacturing process monitoring data is challenging owing to the diversity and complexity of the underlying physical interactions. A single monitoring solution that captures a particular process phenomenon, such as a photodiode that tracks melt pool intensity, is not alone capable of evaluating process stability or detecting flaw formation with sufficient precision for routine application in industry. In this work, to improve flaw detection performance, we adopted a data fusion approach that captures multiple process phenomena. To demonstrate this, we acquired data from laser powder bed fusion (LPBF) builds of cylindrical specimens produced with different laser spot sizes, emulating defocusing due to process faults such as thermal lensing. The resulting specimens had porosity of varying types and severity, quantified by post-build non-destructive X-ray computed tomography, Archimedes density measurements, and destructive metallographic characterization. During the build, the melt pool state was monitored with two coaxial high-speed video cameras and a temperature field imaging system. Physically intuitive low-level melt pool signatures, such as melt pool temperature, shape and size, and spatter intensity were extracted from this high-dimensional, image-based sensor data. These process signatures were subsequently used as input features in relatively simple machine learning models, such as a support vector machine, which were trained to detect laser defocusing, and in addition, predict porosity type and severity. The results show that the data fusion approach significantly enhanced system performance by reducing the overall false positive rate from ∼ 0.1 to ∼ 0.001 without sacrificing the true positive rate (∼0.90). These results were at par with a black-box, deep machine learning approach (convolutional neural network).http://www.sciencedirect.com/science/article/pii/S026412752200541XLaser powder bed fusionLaser defocusThermal lensingPorosityHigh-speed melt pool imagingSpatter |
| spellingShingle | Aniruddha Gaikwad Richard J. Williams Harry de Winton Benjamin D. Bevans Ziyad Smoqi Prahalada Rao Paul A. Hooper Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing Materials & Design Laser powder bed fusion Laser defocus Thermal lensing Porosity High-speed melt pool imaging Spatter |
| title | Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing |
| title_full | Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing |
| title_fullStr | Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing |
| title_full_unstemmed | Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing |
| title_short | Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing |
| title_sort | multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing |
| topic | Laser powder bed fusion Laser defocus Thermal lensing Porosity High-speed melt pool imaging Spatter |
| url | http://www.sciencedirect.com/science/article/pii/S026412752200541X |
| work_keys_str_mv | AT aniruddhagaikwad multiphenomenameltpoolsensordatafusionforenhancedprocessmonitoringoflaserpowderbedfusionadditivemanufacturing AT richardjwilliams multiphenomenameltpoolsensordatafusionforenhancedprocessmonitoringoflaserpowderbedfusionadditivemanufacturing AT harrydewinton multiphenomenameltpoolsensordatafusionforenhancedprocessmonitoringoflaserpowderbedfusionadditivemanufacturing AT benjamindbevans multiphenomenameltpoolsensordatafusionforenhancedprocessmonitoringoflaserpowderbedfusionadditivemanufacturing AT ziyadsmoqi multiphenomenameltpoolsensordatafusionforenhancedprocessmonitoringoflaserpowderbedfusionadditivemanufacturing AT prahaladarao multiphenomenameltpoolsensordatafusionforenhancedprocessmonitoringoflaserpowderbedfusionadditivemanufacturing AT paulahooper multiphenomenameltpoolsensordatafusionforenhancedprocessmonitoringoflaserpowderbedfusionadditivemanufacturing |