Physics-Informed Neural Networks for Thermophysical Property Retrieval

2025-11-28

AI Summary

Accurate, non-intrusive in-situ estimation of thermal conductivity (k) of existing building envelopes remains challenging due to limitations of conventional methods—including invasiveness, reliance on steady-state conditions, long observation periods, and high environmental sensitivity. Method: This paper proposes an iterative physics-informed neural network (PINN)-based inversion framework that embeds the transient heat conduction equation as a hard physical constraint. It jointly assimilates infrared thermography sequences, finite-volume method (FVM) simulation data, and on-site meteorological measurements to alternately solve the forward heat transfer problem and optimize (k). Contribution/Results: The method eliminates the need for steady-state assumptions and achieves high-accuracy, robust (k) estimation using only short-term (<24 h), non-contact thermal observations. Experimental validation under varying environmental conditions and sampling durations demonstrates a mean absolute error ≤ 4.0851, significantly enhancing the practicality and engineering applicability of on-site thermal performance assessment.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Kernel Methods
• Search and Optimization: Heuristic Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Inverse heat problems refer to the estimation of material thermophysical properties given observed or known heat diffusion behaviour. Inverse heat problems have wide-ranging uses, but a critical application lies in quantifying how building facade renovation reduces thermal transmittance, a key determinant of building energy efficiency. However, solving inverse heat problems with non-invasive data collected in situ is error-prone due to environmental variability or deviations from theoretically assumed conditions. Hence, current methods for measuring thermal conductivity are either invasive, require lengthy observation periods, or are sensitive to environmental and experimental conditions. Here, we present a PINN-based iterative framework to estimate the thermal conductivity k of a wall from a set of thermographs; our framework alternates between estimating the forward heat problem with a PINN for a fixed k, and optimizing k by comparing the thermographs and surface temperatures predicted by the PINN, repeating until the estimated k's convergence. Using both environmental data captured by a weather station and data generated from Finite-Volume-Method software simulations, we accurately predict k across different environmental conditions and data collection sampling times, given the temperature profile of the wall at dawn is close to steady state. Although violating the steady-state assumption impacts the accuracy of k's estimation, we show that our proposed framework still only exhibits a maximum MAE of 4.0851. Our work demonstrates the potential of PINN-based methods for reliable estimation of material properties in situ and under realistic conditions, without lengthy measurement campaigns. Given the lack of research on using machine learning, and more specifically on PINNs, for solving in-situ inverse problems, we expect our work to be a starting point for more research on the topic.

Problem

• Estimating wall thermal conductivity from non-invasive thermograph data
• Solving inverse heat problems with environmental variability challenges
• Developing PINN-based framework for accurate in-situ property measurement

Innovation

• PINN-based iterative framework estimates thermal conductivity
• Alternates between forward heat estimation and parameter optimization
• Uses environmental data and simulations for accurate predictions