# Data-driven Power Loss Identification through Physics-Based Thermal Model Backpropagation

arXiv: https://arxiv.org/abs/2504.00133 · HTML: https://mlsanity.com/paper/2504.00133/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 29 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 5 of 5)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [HARDCORE: H-field and power loss estimation for arbitrary waveforms with residual, dilated convolutional neural networks in ferrite cores](https://mlsanity.com/paper/2401.11488/) (2024)
- [Thermal Neural Networks: Lumped-Parameter Thermal Modeling With State-Space Machine Learning](https://mlsanity.com/paper/2103.16323/) (2021)
- [Estimation of Semiconductor Power Losses Through Automatic Thermal Modeling](https://mlsanity.com/paper/2310.19049/) (2023)

## Built on by (most cited first, 2 of 2)

- [Physics-Informed Condition Monitoring of SiC Power Modules](https://mlsanity.com/paper/2608.08363/) (2026)
- [Failure-Mechanism Transferability of Cumulative-Damage Features for Health State Estimation of SiC Power Modules](https://mlsanity.com/paper/2608.08365/) (2026)

## Abstract (arXiv)

Digital twins for power electronics require accurate power losses whose direct measurements are often impractical or impossible in real-world applications. This paper presents a novel hybrid framework that combines physics-based thermal modeling with data-driven techniques to identify and correct power losses accurately using only temperature measurements. Our approach leverages a cascaded architecture where a neural network learns to correct the outputs of a nominal power loss model by backpropagating through a reduced-order thermal model. We explore two neural architectures, a bootstrapped feedforward network, and a recurrent neural network, demonstrating that the bootstrapped feedforward approach achieves superior performance while maintaining computational efficiency for real-time applications. Between the interconnection, we included normalization strategies and physics-guided training loss functions to preserve stability and ensure physical consistency. Experimental results show that our hybrid model reduces both temperature estimation errors (from 7.2+-6.8degC to 0.3+-0.3degC) and power loss prediction errors (from 5.4+-6.6W to 0.2+-0.3W) compared to traditional physics-based approaches, even in the presence of thermal model uncertainties. This methodology allows us to accurately estimate power losses without direct measurements, making it particularly helpful for real-time industrial applications where sensor placement is hindered by cost and physical limitations.