Physics-Informed Deep Reversible Regression Model for Temperature Field
Reconstruction of Heat-Source Systems
- URL: http://arxiv.org/abs/2106.11929v2
- Date: Thu, 24 Jun 2021 03:25:01 GMT
- Title: Physics-Informed Deep Reversible Regression Model for Temperature Field
Reconstruction of Heat-Source Systems
- Authors: Zhiqiang Gong and Weien Zhou and Jun Zhang and Wei Peng and Wen Yao
- Abstract summary: This work develops a novel physics-informed deep reversible regression models for temperature field reconstruction of heat-source systems.
First, we define the temperature field reconstruction task of heat-source systems mathematically, numerically model the problem, and further transform the problem as an image-to-image regression problem.
Based on the law of forward and backward propagation of deep models, this work develops the deep reversible regression model which can better learn the physical information near the boundary.
- Score: 10.151316399254718
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Temperature monitoring during the life time of heat source components in
engineering systems becomes essential to ensure the normal work and even the
long working life of these heat sources. However, prior methods, which mainly
use the interpolate estimation to reconstruct the whole temperature field with
the temperature value from limited monitoring points, require large amounts of
temperature tensors for an accurate estimation. This may decrease the
availability and reliability of the system and sharply increase the monitoring
cost. Furthermore, limited number of labelled training samples are available
for the training of deep models. To solve this problem, this work develops a
novel physics-informed deep reversible regression models for temperature field
reconstruction of heat-source systems (TFR-HSS), which can better reconstruct
the temperature field with the given limited monitoring points unsupervisedly.
First, we define the temperature field reconstruction task of heat-source
systems mathematically, numerically model the problem, and further transform
the problem as an image-to-image regression problem. Then, based on the law of
forward and backward propagation of deep models, this work develops the deep
reversible regression model which can better learn the physical information
near the boundary and improve the reconstruction performance. Finally,
considering the physical characteristics of heat conduction as well as the
boundary conditions, this work proposes the physics-informed reconstruction
loss including four training losses and joint learns the deep surrogate model
with these losses unsupervisedly. Experimental studies have conducted over
typical two-dimensional heat-source systems to demonstrate the effectiveness
and efficiency of the proposed physics-informed deep reversible regression
models for TFR-HSS task.
Related papers
- Trajectory Flow Matching with Applications to Clinical Time Series Modeling [77.58277281319253]
Trajectory Flow Matching (TFM) trains a Neural SDE in a simulation-free manner, bypassing backpropagation through the dynamics.
We demonstrate improved performance on three clinical time series datasets in terms of absolute performance and uncertainty prediction.
arXiv Detail & Related papers (2024-10-28T15:54:50Z) - Temperature Balancing, Layer-wise Weight Analysis, and Neural Network
Training [58.20089993899729]
This paper proposes TempBalance, a straightforward yet effective layerwise learning rate method.
We show that TempBalance significantly outperforms ordinary SGD and carefully-tuned spectral norm regularization.
We also show that TempBalance outperforms a number of state-of-the-art metrics and schedulers.
arXiv Detail & Related papers (2023-12-01T05:38:17Z) - Deep convolutional encoder-decoder hierarchical neural networks for
conjugate heat transfer surrogate modeling [0.0]
Conjugate heat transfer (CHT) models are vital for the design of many engineering systems.
High-fidelity CHT models are computationally intensive, which limits their use in applications such as design optimization.
We develop a modular deep convolutional encoder-decoder hierarchical (DeepEDH) neural network, a novel deep-learning-based surrogate modeling methodology.
arXiv Detail & Related papers (2023-11-24T21:45:11Z) - Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance.
Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs.
In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
arXiv Detail & Related papers (2023-11-20T08:27:56Z) - Physics-Driven Turbulence Image Restoration with Stochastic Refinement [80.79900297089176]
Image distortion by atmospheric turbulence is a critical problem in long-range optical imaging systems.
Fast and physics-grounded simulation tools have been introduced to help the deep-learning models adapt to real-world turbulence conditions.
This paper proposes the Physics-integrated Restoration Network (PiRN) to help the network to disentangle theity from the degradation and the underlying image.
arXiv Detail & Related papers (2023-07-20T05:49:21Z) - DistilPose: Tokenized Pose Regression with Heatmap Distillation [81.21273854769765]
We propose a novel human pose estimation framework termed DistilPose, which bridges the gaps between heatmap-based and regression-based methods.
DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling (TDE) and Simulated Heatmaps.
arXiv Detail & Related papers (2023-03-04T16:56:29Z) - Unsupervised Restoration of Weather-affected Images using Deep Gaussian
Process-based CycleGAN [92.15895515035795]
We describe an approach for supervising deep networks that are based on CycleGAN.
We introduce new losses for training CycleGAN that lead to more effective training, resulting in high-quality reconstructions.
We demonstrate that the proposed method can be effectively applied to different restoration tasks like de-raining, de-hazing and de-snowing.
arXiv Detail & Related papers (2022-04-23T01:30:47Z) - Physics-based Learning of Parameterized Thermodynamics from Real-time
Thermography [0.0]
We present a novel physics-based approach to learning a thermal process's dynamics from real-time thermographic data.
We show that our approach is robust against noise, and can be used to further refine parameter estimates.
arXiv Detail & Related papers (2022-03-24T16:06:31Z) - A deep learning method based on patchwise training for reconstructing
temperature field [10.422905687540172]
This work proposes a novel deep learning method based on patchwise training to reconstruct the temperature field of electronic equipment accurately from limited observation.
The maximum absolute errors of the reconstructed temperature field are less than 1K under the patchwise training approach.
arXiv Detail & Related papers (2022-01-26T10:42:23Z) - TFRD: A Benchmark Dataset for Research on Temperature Field
Reconstruction of Heat-Source Systems [10.609815608017065]
Temperature field reconstruction of heat source systems (TFR-HSS) performs an essential role in heat management.
There exists no public dataset for widely research of reconstruction methods.
This work construct a specific dataset, namely TFRD, for TFR-HSS task with commonly used methods.
arXiv Detail & Related papers (2021-08-17T15:32:58Z) - A Deep Neural Network Surrogate Modeling Benchmark for Temperature Field
Prediction of Heat Source Layout [0.0]
Deep neural network (DNN) regression method is a feasible way for its good computation performance.
This paper proposes a DNN based surrogate modeling task benchmark.
Experiments are conducted with ten representative state-of-the-art DNN models.
arXiv Detail & Related papers (2021-03-20T13:26:21Z)
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.