TY - JOUR
T1 - Full-field temperature recovery during water quenching processes via physics-informed machine learning
AU - Zhao, Ze
AU - Stuebner, Michael
AU - Lua, Jim
AU - Phan, Nam
AU - Yan, Jinhui
N1 - This work is funded by the Naval Air Warfare Center, Aircraft Division under the Contract of N68335-21-C-0057 .
PY - 2022/5
Y1 - 2022/5
N2 - Water quenching is an effective heat treatment process to produce high-quality metallic structures. Accurate and efficient prediction of the full-field temperature inside the part to capture and control the residual stresses and part quality remains a challenging task. This paper proposes a simple and easy-to-use model for full-field temperature recovery during water quenching processes, using physics-informed machine learning (ML). The novelty of the ML framework is that it only needs temperature measurements of sparse locations to efficiently/accurately recover the full spatio-temporal temperature field without invoking sophisticated multiphysics simulations. The ML framework consists of two tightly connected neural network (NN) models: (1) Firstly, a physics-informed neural network (PINN)-based surrogate model is constructed. The surrogate model, which approximates a high-fidelity finite element model, is responsible for quickly outputting the full-field temperature distribution from the parameterized thermal boundary conditions (BCs). (2) Then, another neural network is constructed to project the available experimental data onto the surrogate model and learn the optimal thermal BC from the parametric space, which produces the best full-field temperature prediction in the surrogate model. The proposed ML framework features high efficiency, accuracy, and universality for temperature prediction in quenching processes. These features are carefully demonstrated and the framework is validated using experimental measurements.
AB - Water quenching is an effective heat treatment process to produce high-quality metallic structures. Accurate and efficient prediction of the full-field temperature inside the part to capture and control the residual stresses and part quality remains a challenging task. This paper proposes a simple and easy-to-use model for full-field temperature recovery during water quenching processes, using physics-informed machine learning (ML). The novelty of the ML framework is that it only needs temperature measurements of sparse locations to efficiently/accurately recover the full spatio-temporal temperature field without invoking sophisticated multiphysics simulations. The ML framework consists of two tightly connected neural network (NN) models: (1) Firstly, a physics-informed neural network (PINN)-based surrogate model is constructed. The surrogate model, which approximates a high-fidelity finite element model, is responsible for quickly outputting the full-field temperature distribution from the parameterized thermal boundary conditions (BCs). (2) Then, another neural network is constructed to project the available experimental data onto the surrogate model and learn the optimal thermal BC from the parametric space, which produces the best full-field temperature prediction in the surrogate model. The proposed ML framework features high efficiency, accuracy, and universality for temperature prediction in quenching processes. These features are carefully demonstrated and the framework is validated using experimental measurements.
KW - Heat treatment
KW - Physics-informed machine learning
KW - Quenching
UR - http://www.scopus.com/inward/record.url?scp=85125765313&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125765313&partnerID=8YFLogxK
U2 - 10.1016/j.jmatprotec.2022.117534
DO - 10.1016/j.jmatprotec.2022.117534
M3 - Article
AN - SCOPUS:85125765313
SN - 0924-0136
VL - 303
JO - Journal of Materials Processing Technology
JF - Journal of Materials Processing Technology
M1 - 117534
ER -