Deep learning or interpolation for inverse modelling of heat and fluid flow problems?

Löhner, Rainald; Antil, Harbir; Tamaddon-Jahromi, H.R.; Chakshu, Neeraj Kavan; Nithiarasu, Perumal

doi:10.1108/hff-11-2020-0684

Cited by 13 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, the DNN understands the complex non-linear pattern from the input and output layers considering the backpropagation. The non-linear tendency from input and output layers can be validated in hidden layers (Chauhan et al , 2019; Løhner et al , 2021). As research on the thermal regression with the hidden layer effect have been lacking, this study will look at those afterwards.…”

Section: Methodsmentioning

confidence: 99%

Deep neural network prediction for effective thermal conductivity and spreading thermal resistance for flat heat pipe

Kim

Moon

2022

HFF

View full text Add to dashboard Cite

Purpose This study aims to introduce a deep neural network (DNN) to estimate the effective thermal conductivity of the flat heat pipe with spreading thermal resistance. Design/methodology/approach A total of 2,160 computational fluid dynamics simulation cases over up to 2,000 W/mK are conducted to regress big data and predict a wider range of effective thermal conductivity up to 10,000 W/mK. The deep neural networking is trained with reinforcement learning from 10–12 steps minimizing errors in each step. Another 8,640 CFD cases are used to validate. Findings Experimental, simulational and theoretical approaches are used to validate the DNN estimation for the same independent variables. The results from the two approaches show a good agreement with each other. In addition, the DNN method required less time when compared to the CFD. Originality/value The DNN method opens a new way to secure data while predicting in a wide range without experiments or simulations. If these technologies can be applied to thermal and materials engineering, they will be the key to solve thermal obstacles that many longing to overcome.

show abstract

Section: Methodsmentioning

confidence: 99%

Deep neural network prediction for effective thermal conductivity and spreading thermal resistance for flat heat pipe

Kim

Moon

2022

HFF

View full text Add to dashboard Cite

show abstract

“…However, a challenge arises due to the fact that traditional 2D/3D simulations are still distant from being capable of exchanging real-time data with the physical system. To address this issue, AI, especially ML and DL, becomes a HFF highly useful tool for constructing predictive reduced models of the real system (Xuereb Conti et al, 2023;Grabe et al, 2023), optimization purposes (Lin et al, 2018;Guo et al, 2023;Keramati et al, 2022;Aldaghi et al, 2023;Zeeshan et al, 2023), solving inverse problems (Tamaddon-Jahromi et al, 2020;Löhner et al, 2020) and effectively mitigating the computational costs associated with conventional simulations (Zhu et al, 2023;Park and Kim, 2023;Zhang et al, 2023). It must be specified that the standalone CAE simulations do not represent a DT.…”

Section: Introductionmentioning

confidence: 99%

A physics-driven and machine learning-based digital twinning approach to transient thermal systems

Di Meglio,

Massarotti,

Nithiarasu

2024

HFF

Self Cite

View full text Add to dashboard Cite

Purpose In this study, the authors propose a novel digital twinning approach specifically designed for controlling transient thermal systems. The purpose of this study is to harness the combined power of deep learning (DL) and physics-based methods (PBM) to create an active virtual replica of the physical system. Design/methodology/approach To achieve this goal, we introduce a deep neural network (DNN) as the digital twin and a Finite Element (FE) model as the physical system. This integrated approach is used to address the challenges of controlling an unsteady heat transfer problem with an integrated feedback loop. Findings The results of our study demonstrate the effectiveness of the proposed digital twinning approach in regulating the maximum temperature within the system under varying and unsteady heat flux conditions. The DNN, trained on stationary data, plays a crucial role in determining the heat transfer coefficients necessary to maintain temperatures below a defined threshold value, such as the material’s melting point. The system is successfully controlled in 1D, 2D and 3D case studies. However, careful evaluations should be conducted if such a training approach, based on steady-state data, is applied to completely different transient heat transfer problems. Originality/value The present work represents one of the first examples of a comprehensive digital twinning approach to transient thermal systems, driven by data. One of the noteworthy features of this approach is its robustness. Adopting a training based on dimensionless data, the approach can seamlessly accommodate changes in thermal capacity and thermal conductivity without the need for retraining.

show abstract

“…Najafi [29] utilized an ANN as a digital filter and achieved an approximate real-time estimation of surface thermal conditions based on temperature measurements from past and future time steps. Lohner [30] applied the ANN to achieve the inversion of nonlinear heat transfer problems and compared the results with those from interpolation algorithms, finding that the ANN method provided more accurate results. Wan [31] combined the PID algorithm with a single neuron to automatically adjust the PID tuning parameters.…”

Section: Introductionmentioning

confidence: 99%

A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer Problems

Chen,

Pan

2023

Energies

View full text Add to dashboard Cite

Inverse heat transfer problems are important in numerous scientific research and engineering applications. This paper proposes a network-based method utilizing the nonlinear autoregressive with exogenous inputs (NARX) neural network, which can achieve real-time identification of thermal boundary conditions for nonlinear transient heat transfer processes. With the introduction of the NARX neural network, the proposed method offers two key advantages: (1) The proposed method can obtain inversion results using only surface temperature time series. (2) The heat flux can be estimated even when the state equation of the system is unknown. The NARX neural network is trained using the Bayesian regularization algorithm with a dataset comprising exact surface temperature and heat flux data. The neural network takes current and historical surface temperature measurements as inputs to calculate the heat flux at the current time. The capability of the NARX method has been verified through numerical simulation experiments. Experimental results demonstrate that the NARX method has high precision, strong noise resistance, and broad applicability. The composition of the input data, the surface temperature measurement noise, and the boundary heat flux shape have been studied in detail for their impact on the inversion results. The NARX method is a highly competitive solution to inverse heat transfer problems.

show abstract

Deep learning or interpolation for inverse modelling of heat and fluid flow problems?

Cited by 13 publications

References 16 publications

Deep neural network prediction for effective thermal conductivity and spreading thermal resistance for flat heat pipe

Deep neural network prediction for effective thermal conductivity and spreading thermal resistance for flat heat pipe

A physics-driven and machine learning-based digital twinning approach to transient thermal systems

A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer Problems

Contact Info

Product

Resources

About