Faster Thermal Profiling of a Lunar Rover with Machine Learning Adapted Finite Difference Model

2026-05-26

AI Summary

This work addresses the challenge of high-fidelity thermal modeling for lunar rovers operating under extreme thermal environments, where large temperature gradients, radiative heat transfer, and complex surface conditions hinder accurate simulation. To overcome this, the authors propose an adaptive coarse-grid thermal simulation framework that synergistically integrates physics-informed machine learning with numerical solvers. Specifically, the method combines a transferable neural network with a differentiable finite difference solver to dynamically refine mesh resolution and reconstruct high-resolution temperature fields while enforcing physical consistency. Evaluated against conventional coarse-grid models and purely data-driven artificial neural networks, the proposed approach improves prediction accuracy by 50% and 39%, respectively, while achieving a computational speedup of threefold compared to high-fidelity simulations—effectively balancing efficiency and accuracy.

Abstract

Autonomous space systems operating in extreme thermal environments require accurate and efficient thermal modeling to support both pre-mission system design and onboard autonomy. For lunar rovers, large temperature gradients, radiative heat transfer, and variable surface conditions make reliable thermal prediction especially challenging. High-fidelity physics-based simulations provide accurate results but are computationally expensive, while simplified models and lookup-table approach often lack sufficient accuracy. Physics-informed machine learning (PIML) offers a promising alternative by combining data-driven models with embedded physical knowledge. This paper presents a PIML framework for thermal analysis of a simplified lunar rover with internal heat sources, where machine learning enables environment-adaptive coarse meshing. The proposed architecture integrates a transfer neural network (TNN) that adaptively determines 3D finite-difference nodalization based on thermal loads and initial conditions, enabling more accurate coarse-mesh calculations. A differentiable finite-difference thermal simulator is embedded within the framework to enforce physical consistency and support efficient training, while an upscaling layer reconstructs high-resolution temperature fields from the coarse-grid solution. The proposed PIML approach is evaluated against high-fidelity fine-mesh simulations, low-fidelity fixed coarse-mesh models, and a purely data-driven artificial neural network (ANN). Results show that the PIML framework improves prediction accuracy by 50% and 39% relative to the coarse-mesh physics model and ANN model, respectively, while maintaining physically consistent thermal distributions. Computationally, the framework is also 3x faster than high-fidelity simulations, demonstrating an effective balance between accuracy and efficiency for thermal modeling of lunar rover systems.

Problem

• thermal modeling
• lunar rover
• extreme thermal environments
• computational efficiency
• prediction accuracy

Innovation

• Physics-informed machine learning
• adaptive meshing
• differentiable simulator
• thermal modeling
• lunar rover