4.7 Review

Solution approaches to inverse heat transfer problems with and without phase changes: A state-of-the-art review

Related references

Note: Only part of the references are listed.
Article Thermodynamics

Fouling prediction of heat exchanger surface under alternating magnetic field based on IGWO-SVR

Jianguo Wang et al.

Summary: This study investigated the crystallization fouling of a heat exchanger surface under an alternating magnetic field. Experimental data, including conductivity, induced current, and fouling resistance, were obtained at various magnetic induction intensities. The results showed that a magnetic induction intensity of 300 Gs had the best fouling inhibition effect with a fouling inhibition rate of 78.89%. The induced current was found to be related to magnetic induction intensity and salt concentration, providing insights into fouling resistance and the alternating magnetic field. A support vector regression (SVR) model optimized by improved grey wolf algorithm (IGWO) was proposed to predict fouling resistance based on the strong correlation with conductivity and induced current. The prediction results demonstrated the high accuracy and adaptability of the IGWO-SVR model compared to other methods.

INTERNATIONAL JOURNAL OF THERMAL SCIENCES (2023)

Article Thermodynamics

Machine learning based prediction of heat transfer deterioration of supercritical fluid in upward vertical tubes

Runfeng Xiao et al.

Summary: The heat transfer deterioration (HTD) of supercritical fluids is crucial for the safe operation of power systems. Current criteria for HTD face difficulties in identifying the working conditions of supercritical fluids. This paper proposes a new definition of HTD and a machine learning-based method to predict HTD in upward vertical tubes with supercritical water and CO2. Eight criteria for HTD were compared and analyzed based on two traditional definitions and the proposed new one. Results showed that the discontinuity of experimental data leads to missing HTD points. Traditional methods achieved accuracy ranging from 55% to 82%. The machine learning-based method demonstrated high prediction accuracy of up to 95% for all three definitions of HTD. The proposed definition and the machine learning method can improve the identification and prediction of HTD in supercritical fluids.

APPLIED THERMAL ENGINEERING (2023)

Article Engineering, Mechanical

A novel defect-based fatigue damage model coupled with an optimized neural network for high-cycle fatigue analysis of casting alloys with surface defect

Tongzhou Gao et al.

Summary: A novel defect-based fatigue damage model combined with an optimized neural network is proposed for predicting the high-cycle fatigue. The defect-based fatigue damage evolution equation is derived based on parametric studies and continuum damage mechanics, followed by numerical simulation and fatigue damage computation validation. Additional computations are performed to obtain reliable fatigue data and establish a database, and the architecture of the optimized neural network is established to verify the predicted results using experimental fatigue data. The proposed methodology is effective for fatigue analysis of casting alloys with surface defects.

INTERNATIONAL JOURNAL OF FATIGUE (2023)

Article Thermodynamics

A fast inversion approach for the identification of highly transient surface heat flux based on the generative adversarial network

Jiang-hang Gu et al.

Summary: This study proposes an operator-learning method for solving complex three-dimensional transient nonlinear inverse heat transfer problems. The FluxNet adversarial network, consisting of a discrete wavelet transform layer, a generator, and a discriminator, is constructed to significantly improve computational efficiency, achieving sub-second speed for the first time. By utilizing adversarial training, the generator and discriminator gain a deeper understanding of data distribution, making the proposed method superior in dealing with highly transient experimental data and micro-nano porous structured geometry. With the developed sub-second light-weight numerical solver with operator learning, the development of advanced real-time soft sensor techniques for a class of 3D transient inverse heat transfer problems in practical engineering applications becomes possible.

APPLIED THERMAL ENGINEERING (2023)

Article Thermodynamics

Estimating thermal properties of phase change material from heat flux measurements

Elodie Courtois et al.

Summary: Inverse analysis is used to estimate the thermal properties of phase change material (PCM) as a function of temperature. The study involves a two-part sequential work to estimate the thermal properties in solid and liquid states and characterize phase change. Experimental setup was used to collect data, which showed good agreement with results obtained from DSC facilities. The well-designed experiment and reliable measurements contribute to addressing the important estimation problem.

INTERNATIONAL JOURNAL OF THERMAL SCIENCES (2022)

Article Computer Science, Interdisciplinary Applications

Solving Inverse Heat Transfer Problems Without Surrogate Models: A Fast, Data-Sparse, Physics Informed Neural Network Approach

Vivek Oommen et al.

Summary: Physics informed neural networks have gained attention for effectively solving partial differential equations by injecting physics laws as regularization into the neural network model. This study aims to investigate the effectiveness of this approach in solving inverse problems and compares it with conventional machine learning methods. It shows that physics informed neural networks can solve inverse heat transfer problems without using surrogate models, contributing to a more robust solution.

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING (2022)

Review Computer Science, Artificial Intelligence

AutoML: state of the art with a focus on anomaly detection, challenges, and research directions

Maroua Bahri et al.

Summary: The past decade has witnessed rapid development in machine learning research, but the performance of multiple algorithms is sensitive to factors such as hyper-parameter tuning and data cleaning, requiring significant human effort to achieve good results. Automated machine learning (autoML) aims to make machine learning algorithms more accessible and reliable, with most research efforts focusing on supervised learning and few proposals for unsupervised learning.

INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS (2022)

Article Automation & Control Systems

Privacy-Preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach

Yang Li et al.

Summary: This article proposes a novel federated deep generative learning framework, Fed-LSGAN, for generating high-quality scenarios in power systems with high-penetration renewables. The framework integrates federated learning and least square generative adversarial networks (LSGANs) to achieve privacy-preserving scenario generation and improve generation quality using the least squares loss function.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Article Thermodynamics

Inverse method for simultaneously estimating temperature-dependent solid- and liquid-phase thermal conductivities during phase transition

Tian Zhou et al.

Summary: This study proposes a novel inverse method to simultaneously estimate the temperature-dependent solid and liquid phase thermal conductivities of phase change materials (PCMs). The theoretical issues such as parameter sensitivity, discretization schemes, and estimation algorithms are clarified. The Monte Carlo method is used to verify the discretization schemes and the results show high sensitivity coefficients for both solid and liquid thermal conductivities. The estimation algorithm results are strongly influenced by temperature measurement position, measurement time, boundary conditions, and the discrete scheme of the mathematical model. The proposed algorithms provide accurate and reliable estimates of temperature-dependent thermal conductivities for solid and liquid phases of PCMs.

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER (2022)

Article Thermodynamics

A deep learning method for estimating thermal boundary condition parameters in transient inverse heat transfer problem

Feiding Zhu et al.

Summary: This study proposed a simple method based on deep learning to estimate thermal boundary condition parameters in the transient inverse heat transfer problem. By combining convolutional neural network (CNN) and long short-term memory networks (LSTM), real-time prediction of multiple time-varying parameters can be achieved. Experimental results showed that the proposed model outperformed standalone models in estimating multiple time-varying parameters.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2022)

Article Thermodynamics

Thermal conductivity evolution of a compressed expanded natural graphite-Phase change material composite after thermal cycling

Mariam Jadal et al.

Summary: This study measures the thermal conductivity of CENG-PCM using two methods and conducts a 1500 thermal cycling test. The results show that there is little change in thermal conductivity after aging cycles, despite the presence of cracks on the surface of the composite. DSC analysis also reveals that the latent heat remains almost unchanged after thermal cycling.

THERMAL SCIENCE AND ENGINEERING PROGRESS (2022)

Article Thermodynamics

Identification of the effective heat capacity-temperature relationship and the phase change hysteresis in PCMs by means of an inverse heat transfer problem solved with metaheuristic methods

Martin Zalesak et al.

Summary: Two metaheuristic optimization methods were employed to solve an inverse heat transfer problem involving a phase change material, identifying the relationship between effective heat capacity and temperature during melting and solidification. The study revealed significant asymmetry between the melting and solidification processes of PCMs, suggesting the existence of phase change hysteresis. The calculation procedure developed for the inverse problem proved robust and accurate, although slightly lower accuracy was observed in experimental data compared to pre-simulated data.

APPLIED THERMAL ENGINEERING (2021)

Review Computer Science, Artificial Intelligence

Machine Learning for industrial applications: A comprehensive literature review

Massimo Bertolini et al.

Summary: Machine Learning (ML) as a branch of artificial intelligence has made significant progress in recent years, especially in industrial applications, showing great potential, and the number of related research and published papers is continuously increasing. Researchers have found that production planning and control, as well as defect analysis, will become the main directions for the future pervasive application of machine learning in operation management.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Article Thermodynamics

Mathematical modelling of heat transmission in the temperature history apparatus by using inverse method to evaluate the latent heat of high temperature PCMs

Ehsan Omaraa et al.

Summary: High temperature PCMs are proposed for thermal energy storage in concentrated solar power plants, but the T-history method's original equations may not be applicable for estimating latent heat. A one-dimensional heat transfer mathematical model with an inverse method can overcome this limitation.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2021)

Article Thermodynamics

A data driven deep neural network model for predicting boiling heat transfer in helical coils under high gravity

Xing Liang et al.

Summary: A deep artificial neural network model was proposed to predict boiling heat transfer in helical coils under high gravity conditions, demonstrating excellent performance in accurately predicting the characteristics of the coils. Through the utilization of deep learning, the model successfully predicted heat transfer performance and achieved outstanding results, showing the potential of deep learning in predicting complex systems.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2021)

Article Thermodynamics

Analytical modelling of PCM supercooling including recalescence for complete and partial heating/cooling cycles

Maxime Thonon et al.

Summary: This study aims to analytically model the thermal behavior of a PCM experiencing supercooling and phase change hysteresis, for both complete and partial phase change cycles. The developed method relies on a heat source term to model the recalescence process during solidification.

APPLIED THERMAL ENGINEERING (2021)

Article Thermodynamics

Fast estimation of the enthalpy-temperature function of Phase Change Materials

Jean-Luc Dauvergne et al.

Summary: This paper introduces a method for rapidly estimating the enthalpy-temperature function of Phase Change Materials (PCMs) using a simple experimental setup and reliable mathematical algorithm. The accuracy of the method was validated using distilled water as a reference PCM, showing good results. Additionally, the method was proven effective for PCMs undergoing progressive melting.

EXPERIMENTAL THERMAL AND FLUID SCIENCE (2021)

Article Energy & Fuels

Inverse method to describe crystallization of undercooled water in cold storage tank

M. A. BEN TAHER et al.

Summary: This study developed a physical model to describe the thermal performance of a cylindrical tank filled with spherical water capsules during storage, using an inverse method and a genetic algorithm to evaluate the heat flux exchanged between the heat transfer fluid and the capsules. The numerical results showed good agreement with experimental data, and the influence of HTF flowrate on the shape of the released heat flux was analyzed and discussed.

JOURNAL OF ENERGY STORAGE (2021)

Article Thermodynamics

A new damping strategy of Levenberg-Marquardt algorithm with a fuzzy method for inverse heat transfer problem parameter estimation

Ramin Sajedi et al.

Summary: In this paper, a new method combining fuzzy logic with the classical LM algorithm significantly improves the convergence speed and stability of solutions for inverse problems with different noisy temperatures. The robustness of the new method is comparable to the LM algorithm.

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER (2021)

Article Thermodynamics

Status, Challenges, and Potential for Machine Learning in Understanding and Applying Heat Transfer Phenomena

Matthew T. Hughes et al.

Summary: This study reviews the past and present efforts in using machine learning techniques in the field of heat transfer, discussing the appropriateness of different data-driven ML models in heat transfer problems, and identifies the imminent opportunities and challenges that the heat transfer community faces.

JOURNAL OF HEAT TRANSFER-TRANSACTIONS OF THE ASME (2021)

Article Green & Sustainable Science & Technology

Application of New Artificial Neural Network to Predict Heat Transfer and Thermal Performance of a Solar Air-Heater Tube

Suvanjan Bhattacharyya et al.

Summary: In this study, the heat transfer and thermal performance of solar air-heater tubes with helical corrugation were predicted using a machine learning regression technique. A statistical analysis of heat transfer was conducted by developing an artificial neural network-based machine learning model, which showed high prediction accuracies. The models based on experimental data features provide accurate estimation of experimental output, reducing the time and cost of experiments.

SUSTAINABILITY (2021)

Article Materials Science, Multidisciplinary

A physics-informed deep learning method for solving direct and inverse heat conduction problems of materials

Zhili He et al.

Summary: A novel data-driven framework based on PINNs is proposed for direct analysis and parameter inversion of heat conduction problems, showing satisfactory accuracy and the potential to replace finite element modeling to some extent through case studies on wood and steel. The framework can effectively address both direct and inverse heat conduction problems and has broad application prospects in materials science.

MATERIALS TODAY COMMUNICATIONS (2021)

Article Engineering, Multidisciplinary

Verification of sequential function specification method with intermittent spray cooling

Xiao Zhao et al.

INVERSE PROBLEMS IN SCIENCE AND ENGINEERING (2020)

Article Thermodynamics

Non-linear Non-Iterative transient inverse conjugate heat transfer method applied to microelectronics

D. G. Cuadrado et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2020)

Article Engineering, Multidisciplinary

Data-driven inverse modelling through neural network (deep learning) and computational heat transfer

Hamid Reza Tamaddon-Jahromi et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

Article Energy & Fuels

Towards a better analytical modelling of the thermodynamic behaviour of phase change materials

Maxime Thonon et al.

JOURNAL OF ENERGY STORAGE (2020)

Article Thermodynamics

A novel comparative approach on inverse heat transfer analysis of an experimental setup of an extended surface

Meenal Singhal et al.

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER (2020)

Article Thermodynamics

An inverse approach for the interfacial heat transfer parameters in alloys solidification

Edilma P. Oliveira et al.

APPLIED THERMAL ENGINEERING (2019)

Article Thermodynamics

Improved prediction of oscillatory heat transfer coefficient for a thermoacoustic heat exchanger using modified adaptive neuro-fuzzy inference system

Mohamed Abd Elaziz et al.

INTERNATIONAL JOURNAL OF REFRIGERATION-REVUE INTERNATIONALE DU FROID (2019)

Article Thermodynamics

Quantitative identification of three-dimensional subsurface defect based on the fuzzy inference of thermal process

Kun Wang et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2019)

Article Chemistry, Multidisciplinary

Efficient Characterization of Macroscopic Composite Cement Mortars with Various Contents of Phase Change Material

Laurent Zalewski et al.

APPLIED SCIENCES-BASEL (2019)

Article Thermodynamics

Inverse method to estimate air flow rate during free cooling using PCM-air heat exchanger

A. Ousegui et al.

APPLIED THERMAL ENGINEERING (2019)

Article Thermodynamics

Assessment of PCM-container interfacial heat transfer using a hot/cold probe technique

R. Sudheer et al.

HEAT TRANSFER-ASIAN RESEARCH (2019)

Article Thermodynamics

A multiple model adaptive inverse method for nonlinear heat transfer system with temperature-dependent thermophysical properties

Guangjun Wang et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2018)

Article Thermodynamics

Fuzzy logic and bed-to-wall heat transfer in a large-scale CFBC

Jaroslaw Krzywanski et al.

INTERNATIONAL JOURNAL OF NUMERICAL METHODS FOR HEAT & FLUID FLOW (2018)

Article Thermodynamics

Inverse Identification of Temperature-Dependent Thermal Properties Using Improved Krill Herd Algorithm

S. C. Sun et al.

INTERNATIONAL JOURNAL OF THERMOPHYSICS (2018)

Article Thermodynamics

A double decentralized fuzzy inference method for estimating the time and space-dependent thermal boundary condition

Guangjun Wang et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2017)

Article Computer Science, Interdisciplinary Applications

Salp Swarm Algorithm: A bio-inspired optimizer for engineering design problems

Seyedali Mirjalili et al.

ADVANCES IN ENGINEERING SOFTWARE (2017)

Proceedings Paper Thermodynamics

Inverse heat conduction problem in a phase change memory device

Jean-Luc Battaglia et al.

EUROTHERM SEMINAR NO 108 - NANOSCALE AND MICROSCALE HEAT TRANSFER V (2017)

Article Thermodynamics

Inverse heat transfer prediction of the state of the brick wall of a melting furnace

Mohamed Hafid et al.

APPLIED THERMAL ENGINEERING (2017)

Article Thermodynamics

A decentralized fuzzy inference method for the inverse geometry heat conduction problem

Yanhao Li et al.

APPLIED THERMAL ENGINEERING (2016)

Article Thermodynamics

A general method for solving transient multidimensional inverse heat transfer problems

Piotr Duda

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2016)

Article Thermodynamics

Fuzzy estimation for unknown boundary shape of fluid-solid conjugate heat transfer problem

Hong Chen et al.

INTERNATIONAL JOURNAL OF THERMAL SCIENCES (2016)

Article Thermodynamics

Identification of the Thermophysical Properties of the Soil by Inverse Problem

Salwa Mansour et al.

JOURNAL OF HEAT TRANSFER-TRANSACTIONS OF THE ASME (2016)

Article Thermodynamics

Online heat flux estimation using artificial neural network as a digital filter approach

Hamidreza Najafi et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2015)

Article Engineering, Multidisciplinary

Inverse method implementation to heat transfer coefficient determination over the plate cooled by water spray

Z. Malinowski et al.

INVERSE PROBLEMS IN SCIENCE AND ENGINEERING (2015)

Proceedings Paper Construction & Building Technology

Estimation of the thermal properties of PCMs through inverse modelling

Ylenia Cascone et al.

6TH INTERNATIONAL BUILDING PHYSICS CONFERENCE (IBPC 2015) (2015)

Proceedings Paper Construction & Building Technology

Identification of Thermal Properties and Thermodynamic Model for a Cement Mortar Containing PCM by Using Inverse Method

Pierre Tittelein et al.

6TH INTERNATIONAL BUILDING PHYSICS CONFERENCE (IBPC 2015) (2015)

Article Construction & Building Technology

A simple method for building materials thermophysical properties estimation

R. Derbal et al.

CONSTRUCTION AND BUILDING MATERIALS (2014)

Article Construction & Building Technology

Thermal characterization of homogeneous walls using inverse method

Khaled Chaffar et al.

ENERGY AND BUILDINGS (2014)

Article Thermodynamics

Fuzzy estimation for heat flux distribution at the slab continuous casting mold surface

Hong Chen et al.

INTERNATIONAL JOURNAL OF THERMAL SCIENCES (2014)

Article Mathematics, Applied

Parameter identification in non-isothermal nucleation and growth processes

Dietmar Hoemberg et al.

INVERSE PROBLEMS (2014)

Article Energy & Fuels

A new method to determine thermophysical properties of PCM-concrete brick

Rui Cheng et al.

APPLIED ENERGY (2013)

Article Thermodynamics

A domain decomposition method for the stable analysis of inverse nonlinear transient heat conduction problems

S. Khajehpour et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2013)

Article Mathematics, Applied

Krill herd: A new bio-inspired optimization algorithm

Amir Hossein Gandomi et al.

COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION (2012)

Article Thermodynamics

An artificial intelligence approach to inverse heat transfer modeling of an irradiative dryer

Ali Mirsephai et al.

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER (2012)

Proceedings Paper Thermodynamics

Determination of the enthalpy of phase change materials by inverse method from calorimetric experiments. Applications to pure substances or binary solutions

Stephane Gibout et al.

6TH EUROPEAN THERMAL SCIENCES CONFERENCE (EUROTHERM 2012) (2012)

Article Thermodynamics

A non-parametric method for estimating enthalpy-temperature functions of shape-stabilized phase change materials

Elena Palomo del Barrio et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2011)

Article Thermodynamics

Identification of the heat transfer coefficient in phase change problems

Damian Slota

ARCHIVES OF THERMODYNAMICS (2010)

Article Engineering, Multidisciplinary

Application of the inverse analysis for boundary condition retrieval

A. Ryfa et al.

INVERSE PROBLEMS IN SCIENCE AND ENGINEERING (2009)

Article Mathematics, Applied

An improved quantum-behaved particle swarm optimization algorithm with weighted mean best position

Maolong Xi et al.

APPLIED MATHEMATICS AND COMPUTATION (2008)

Review Computer Science, Theory & Methods

Metaheuristics in combinatorial optimization: Overview and conceptual comparison

C Blum et al.

ACM COMPUTING SURVEYS (2003)

Article Thermodynamics

Identification of phase change fronts by Bezier splines and BEM

I Nowak et al.

INTERNATIONAL JOURNAL OF THERMAL SCIENCES (2002)

Article Engineering, Manufacturing

Inverse modeling of heat transfer with application to solidification and quenching

KN Prabhu et al.

MATERIALS AND MANUFACTURING PROCESSES (2002)