Data-Driven Optical To Thermal Inference in Pool Boiling Using Generative Adversarial Networks

2025-05-01

AI Summary

Direct measurement of transient temperature fields in pool boiling remains challenging, hindering quantitative characterization of multiphase heat transfer. To address this, we propose a data-driven method that inversely infers temperature fields from optical phase-interface images. Our approach introduces, for the first time, conditional generative adversarial networks (cGANs) for thermal field inversion in multiphase flows. We design a simulation-guided training strategy coupled with physics-unconstrained data augmentation to ensure thermodynamic consistency while enhancing generalizability. Furthermore, we integrate high-speed imaging, geometric contour feature extraction, and multi-source simulation data into an end-to-end mapping framework. Experimental and numerical validation demonstrates temperature field reconstruction errors below 6%, significantly improving interpretability and observability of heat transfer processes in complex two-phase systems.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Phase change plays a critical role in thermal management systems, yet quantitative characterization of multiphase heat transfer remains limited by the challenges of measuring temperature fields in chaotic, rapidly evolving flow regimes. While computational methods offer spatiotemporal resolution in idealized cases, replicating complex experimental conditions remains prohibitively difficult. Here, we present a data-driven framework that leverages a conditional generative adversarial network (CGAN) to infer temperature fields from geometric phase contours in a canonical pool boiling configuration where advanced data collection techniques are restricted. Using high-speed imaging data and simulation-informed training, our model demonstrates the ability to reconstruct temperature fields with errors below 6%. We further show that standard data augmentation strategies are effective in enhancing both accuracy and physical plausibility of the predicted maps across both simulation and experimental datasets when precise physical constraints are not applicable. Our results highlight the potential of deep generative models to bridge the gap between observable multiphase phenomena and underlying thermal transport, offering a powerful approach to augment and interpret experimental measurements in complex two-phase systems.

Problem

• Infer temperature fields from phase contours in pool boiling using CGAN
• Overcome limitations in measuring chaotic multiphase heat transfer
• Enhance accuracy of thermal field predictions with data augmentation

Innovation

• Uses CGAN to infer temperature from phase contours
• Combines high-speed imaging with simulation training
• Applies data augmentation to enhance prediction accuracy