Systematic fault detection and control during laser powder bed fusion (L-PBF) has been a long-standing objective for system manufacturers and researchers in the additive manufacturing (AM) industry. This manuscript investigates a data fusion approach for detection of keyhole porosity formation during laser irradiation of Ti-6Al-4V substrates by concurrent recording of thermally induced optical emission measured using both off-axis and coaxial photodiode sensors, and acoustic emission. Subsurface defect formation was monitored via high-speed synchrotron X-ray imaging at 20,000 frames per second, enabling temporal registration of keyhole pore formation events to the monitoring signals at a resolution of 50 µs. We developed data fusion machine learning (ML) models for localized prediction of keyhole pore formation at various time scales ranging from 0.5 ms to 2 ms. The signal segments were featurized using two independent approaches: (1) power spectral density (PSD) and (2) highly comparative time series analysis (HCTSA) framework. The extracted features from different sensor modalities were fused together to construct a multimodal feature space and sequential feature selection was used to determine the most informative features for training the ML models. The predictive performance was evaluated for three classifying algorithms: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Gaussian Naive Bayes (GNB). As a result, pore formation events were predicted with up to 0.95 F1-score, 1.0 recall and 0.94 accuracy. The most heavily weighted features indicate that model performance is chiefly governed by the acoustic monitoring signal, with a secondary contribution from the optical emission sensors.
Gorgannejad, Sanam, et al. "Localized keyhole pore prediction during laser powder bed fusion via multimodal process monitoring and X-ray radiography." Additive Manufacturing, vol. 78, no. N/A, Oct. 2023. https://doi.org/10.1016/j.addma.2023.103810
Gorgannejad, Sanam, Martin, Aiden A., Nicolino, Jenny W., Strantza, Maria, Guss, Gabriel M., Khairallah, Saad, Forien, Jean-Baptiste, Thampy, Vivek, Liu, Sen, Quan, Peiyu, Tassone, Christopher J., & Calta, Nicholas P. (2023). Localized keyhole pore prediction during laser powder bed fusion via multimodal process monitoring and X-ray radiography. Additive Manufacturing, 78(N/A). https://doi.org/10.1016/j.addma.2023.103810
Gorgannejad, Sanam, Martin, Aiden A., Nicolino, Jenny W., et al., "Localized keyhole pore prediction during laser powder bed fusion via multimodal process monitoring and X-ray radiography," Additive Manufacturing 78, no. N/A (2023), https://doi.org/10.1016/j.addma.2023.103810
@article{osti_2280478,
author = {Gorgannejad, Sanam and Martin, Aiden A. and Nicolino, Jenny W. and Strantza, Maria and Guss, Gabriel M. and Khairallah, Saad and Forien, Jean-Baptiste and Thampy, Vivek and Liu, Sen and Quan, Peiyu and others},
title = {Localized keyhole pore prediction during laser powder bed fusion via multimodal process monitoring and X-ray radiography},
annote = {Systematic fault detection and control during laser powder bed fusion (L-PBF) has been a long-standing objective for system manufacturers and researchers in the additive manufacturing (AM) industry. This manuscript investigates a data fusion approach for detection of keyhole porosity formation during laser irradiation of Ti-6Al-4V substrates by concurrent recording of thermally induced optical emission measured using both off-axis and coaxial photodiode sensors, and acoustic emission. Subsurface defect formation was monitored via high-speed synchrotron X-ray imaging at 20,000 frames per second, enabling temporal registration of keyhole pore formation events to the monitoring signals at a resolution of 50 µs. We developed data fusion machine learning (ML) models for localized prediction of keyhole pore formation at various time scales ranging from 0.5 ms to 2 ms. The signal segments were featurized using two independent approaches: (1) power spectral density (PSD) and (2) highly comparative time series analysis (HCTSA) framework. The extracted features from different sensor modalities were fused together to construct a multimodal feature space and sequential feature selection was used to determine the most informative features for training the ML models. The predictive performance was evaluated for three classifying algorithms: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Gaussian Naive Bayes (GNB). As a result, pore formation events were predicted with up to 0.95 F1-score, 1.0 recall and 0.94 accuracy. The most heavily weighted features indicate that model performance is chiefly governed by the acoustic monitoring signal, with a secondary contribution from the optical emission sensors.},
doi = {10.1016/j.addma.2023.103810},
url = {https://www.osti.gov/biblio/2280478},
journal = {Additive Manufacturing},
issn = {ISSN 2214-8604},
number = {N/A},
volume = {78},
place = {United States},
publisher = {Elsevier},
year = {2023},
month = {10}}
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA); USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Laboratory Directed Research and Development (LDRD) Program
