Hybrid full-field thermal characterization of additive manufacturing
processes using physics-informed neural networks with data
- URL: http://arxiv.org/abs/2206.07756v1
- Date: Wed, 15 Jun 2022 18:27:10 GMT
- Title: Hybrid full-field thermal characterization of additive manufacturing
processes using physics-informed neural networks with data
- Authors: Shuheng Liao, Tianju Xue, Jihoon Jeong, Samantha Webster, Kornel
Ehmann, Jian Cao
- Abstract summary: We develop a hybrid physics-based data-driven thermal modeling approach of AM processes using physics-informed neural networks.
Partially observed temperature data measured from an infrared camera is combined with the physics laws to predict full-field temperature history.
Results show that the hybrid thermal model can effectively identify unknown parameters and capture the full-field temperature accurately.
- Score: 5.653328302363391
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Understanding the thermal behavior of additive manufacturing (AM) processes
is crucial for enhancing the quality control and enabling customized process
design. Most purely physics-based computational models suffer from intensive
computational costs, thus not suitable for online control and iterative design
application. Data-driven models taking advantage of the latest developed
computational tools can serve as a more efficient surrogate, but they are
usually trained over a large amount of simulation data and often fail to
effectively use small but high-quality experimental data. In this work, we
developed a hybrid physics-based data-driven thermal modeling approach of AM
processes using physics-informed neural networks. Specifically, partially
observed temperature data measured from an infrared camera is combined with the
physics laws to predict full-field temperature history and to discover unknown
material and process parameters. In the numerical and experimental examples,
the effectiveness of adding auxiliary training data and using the technique of
transfer learning on training efficiency and prediction accuracy, as well as
the ability to identify unknown parameters with partially observed data, are
demonstrated. The results show that the hybrid thermal model can effectively
identify unknown parameters and capture the full-field temperature accurately,
and thus it has the potential to be used in iterative process design and
real-time process control of AM.
Related papers
- AFSD-Physics: Exploring the governing equations of temperature evolution
during additive friction stir deposition by a human-AI teaming approach [0.0]
AFSD is an emerging solid-state additive manufacturing technology that deposits materials without melting.
A human-AI teaming approach is proposed to combine models based on first principles with AI.
The resulting human-informed machine learning method, denoted as AFSD-Physics, can effectively learn the governing equations of temperature evolution at the tool.
arXiv Detail & Related papers (2024-01-29T19:17:42Z) - Online Variational Sequential Monte Carlo [49.97673761305336]
We build upon the variational sequential Monte Carlo (VSMC) method, which provides computationally efficient and accurate model parameter estimation and Bayesian latent-state inference.
Online VSMC is capable of performing efficiently, entirely on-the-fly, both parameter estimation and particle proposal adaptation.
arXiv Detail & Related papers (2023-12-19T21:45:38Z) - Gradual Optimization Learning for Conformational Energy Minimization [69.36925478047682]
Gradual Optimization Learning Framework (GOLF) for energy minimization with neural networks significantly reduces the required additional data.
Our results demonstrate that the neural network trained with GOLF performs on par with the oracle on a benchmark of diverse drug-like molecules.
arXiv Detail & Related papers (2023-11-05T11:48:08Z) - Machine learning enabled experimental design and parameter estimation
for ultrafast spin dynamics [54.172707311728885]
We introduce a methodology that combines machine learning with Bayesian optimal experimental design (BOED)
Our method employs a neural network model for large-scale spin dynamics simulations for precise distribution and utility calculations in BOED.
Our numerical benchmarks demonstrate the superior performance of our method in guiding XPFS experiments, predicting model parameters, and yielding more informative measurements within limited experimental time.
arXiv Detail & Related papers (2023-06-03T06:19:20Z) - A machine learning approach to the prediction of heat-transfer
coefficients in micro-channels [4.724825031148412]
The accurate prediction of the two-phase heat transfer coefficient (HTC) is key to the optimal design and operation of compact heat exchangers.
We use a multi-output Gaussian process regression (GPR) to estimate the HTC in microchannels as a function of the mass flow rate, heat flux, system pressure and channel diameter and length.
arXiv Detail & Related papers (2023-05-28T15:48:01Z) - Multi-fidelity surrogate modeling for temperature field prediction using
deep convolution neural network [8.98674326282801]
This paper proposes a pithy deep multi-fidelity model (DMFM) for temperature field prediction.
It takes advantage of low-fidelity data to boost the performance with less high-fidelity data.
A self-supervised learning method for training the physics-driven deep multi-fidelity model (PD-DMFM) is proposed.
arXiv Detail & Related papers (2023-01-17T03:13:45Z) - Physics-constrained deep learning postprocessing of temperature and
humidity [0.0]
We propose to achieve physical consistency in deep learning-based postprocessing models.
We find that constraining a neural network to enforce thermodynamic state equations yields physically-consistent predictions.
arXiv Detail & Related papers (2022-12-07T09:31:25Z) - An Adversarial Active Sampling-based Data Augmentation Framework for
Manufacturable Chip Design [55.62660894625669]
Lithography modeling is a crucial problem in chip design to ensure a chip design mask is manufacturable.
Recent developments in machine learning have provided alternative solutions in replacing the time-consuming lithography simulations with deep neural networks.
We propose a litho-aware data augmentation framework to resolve the dilemma of limited data and improve the machine learning model performance.
arXiv Detail & Related papers (2022-10-27T20:53:39Z) - Advancing Reacting Flow Simulations with Data-Driven Models [50.9598607067535]
Key to effective use of machine learning tools in multi-physics problems is to couple them to physical and computer models.
The present chapter reviews some of the open opportunities for the application of data-driven reduced-order modeling of combustion systems.
arXiv Detail & Related papers (2022-09-05T16:48:34Z) - Predictive modeling approaches in laser-based material processing [59.04160452043105]
This study aims to automate and forecast the effect of laser processing on material structures.
The focus is centred on the performance of representative statistical and machine learning algorithms.
Results can set the basis for a systematic methodology towards reducing material design, testing and production cost.
arXiv Detail & Related papers (2020-06-13T17:28:52Z) - Data-Driven Permanent Magnet Temperature Estimation in Synchronous
Motors with Supervised Machine Learning [0.0]
Monitoring the magnet temperature in permanent magnet synchronous motors (PMSMs) for automotive applications is a challenging task.
Overheating results in severe motor deterioration and is thus of high concern for the machine's control strategy and its design.
Several machine learning (ML) models are empirically evaluated on their estimation accuracy for the task of predicting latent high-dynamic magnet temperature profiles.
arXiv Detail & Related papers (2020-01-17T11:41:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.