Saved in:
Bibliographic Details
Main Authors: Scarpa, Mattia, Pase, Francesco, Carli, Ruggero, Bruschetta, Mattia, Toso, Franscesco
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.00133
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913785704349696
author Scarpa, Mattia
Pase, Francesco
Carli, Ruggero
Bruschetta, Mattia
Toso, Franscesco
author_facet Scarpa, Mattia
Pase, Francesco
Carli, Ruggero
Bruschetta, Mattia
Toso, Franscesco
contents 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+-6.8°C to 0.3+-0.3°C) 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00133
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data-driven Power Loss Identification through Physics-Based Thermal Model Backpropagation
Scarpa, Mattia
Pase, Francesco
Carli, Ruggero
Bruschetta, Mattia
Toso, Franscesco
Systems and Control
Artificial Intelligence
Computational Complexity
Machine Learning
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+-6.8°C to 0.3+-0.3°C) 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.
title Data-driven Power Loss Identification through Physics-Based Thermal Model Backpropagation
topic Systems and Control
Artificial Intelligence
Computational Complexity
Machine Learning
url https://arxiv.org/abs/2504.00133