A Physics-Informed Convolutional Neural Network with Custom Loss Functions for Porosity Prediction in Laser Metal Deposition

TY - JOUR

T1 - A Physics-Informed Convolutional Neural Network with Custom Loss Functions for Porosity Prediction in Laser Metal Deposition

AU - McGowan, Erin

AU - Gawade, Vidita

AU - Guo, Weihong

N1 - Funding Information: Funding: This work was carried out while one of the authors, Erin McGowan, was a participant in the 2021 DIMACS REU program at Rutgers University, supported by NSF grant CCF-1852215. Publisher Copyright: © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

PY - 2022/1/1

Y1 - 2022/1/1

N2 - Physics-informed machine learning is emerging through vast methodologies and in various applications. This paper discovers physics-based custom loss functions as an implementable solution to additive manufacturing (AM). Specifically, laser metal deposition (LMD) is an AM process where a laser beam melts deposited powder, and the dissolved particles fuse to produce metal components. Porosity, or small cavities that form in this printed structure, is generally considered one of the most destructive defects in metal AM. Traditionally, computer tomography scans measure porosity. While this is useful for understanding the nature of pore formation and its characteristics, purely physics-driven models lack real-time prediction ability. Meanwhile, a purely deep learning approach to porosity prediction leaves valuable physics knowledge behind. In this paper, a hybrid model that uses both empirical and simulated LMD data is created to show how various physics-informed loss functions impact the accuracy, precision, and recall of a baseline deep learning model for porosity prediction. In particular, some versions of the physics-informed model can improve the precision of the baseline deep learning-only model (albeit at the expense of overall accuracy).

AB - Physics-informed machine learning is emerging through vast methodologies and in various applications. This paper discovers physics-based custom loss functions as an implementable solution to additive manufacturing (AM). Specifically, laser metal deposition (LMD) is an AM process where a laser beam melts deposited powder, and the dissolved particles fuse to produce metal components. Porosity, or small cavities that form in this printed structure, is generally considered one of the most destructive defects in metal AM. Traditionally, computer tomography scans measure porosity. While this is useful for understanding the nature of pore formation and its characteristics, purely physics-driven models lack real-time prediction ability. Meanwhile, a purely deep learning approach to porosity prediction leaves valuable physics knowledge behind. In this paper, a hybrid model that uses both empirical and simulated LMD data is created to show how various physics-informed loss functions impact the accuracy, precision, and recall of a baseline deep learning model for porosity prediction. In particular, some versions of the physics-informed model can improve the precision of the baseline deep learning-only model (albeit at the expense of overall accuracy).

KW - Data fusion

KW - Deep learning

KW - In situ porosity detection

KW - Inspection and quality control

KW - Laser-based additive manufacturing

KW - Monitoring and diagnostics

KW - Sensing

UR - http://www.scopus.com/inward/record.url?scp=85122372019&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85122372019&partnerID=8YFLogxK

U2 - https://doi.org/10.3390/s22020494

DO - https://doi.org/10.3390/s22020494

M3 - Article

C2 - 35062455

SN - 1424-3210

VL - 22

JO - Sensors (Basel, Switzerland)

JF - Sensors (Basel, Switzerland)

IS - 2

M1 - 494

ER -