Reconstructing Unobservable Temperature Fields via Simulation-Aided Intelligent Sensing
This work addresses the challenge of real-time thermal monitoring in industrial systems where sensor placement is restricted, offering a practical solution for online monitoring of unobservable states.
The paper proposes a method to generate synthetic datasets via randomized physics-based simulations for training neural networks to reconstruct internal temperature fields from sparse sensors, achieving real-time inference and outperforming Kriging in robustness.
Real-time monitoring of the temperature distribution within components and sub-structures is a challenging topic in many systems due to restrictions on feasible sensor locations. While machine learning (ML) proves a versatile tool in many applications, its adoption for high-resolution thermal monitoring is hindered by the availability of high-quality datasets for training. In this work, we propose a novel approach for generating datasets for industrial applications based on randomized physics-based simulations. We demonstrate the approach in a proof-of-concept hardware setup: A neural network (NN) trained only on such a synthetic dataset, is used to reconstruct the internal temperature field from sparse sensors embedded in the hardware. The NN-based reconstructions do not only outperform Kriging in robustness but also enable real-time inference, making the method suitable for online monitoring of otherwise unobservable thermal states.