pith. sign in

arxiv: 2504.00133 · v1 · pith:OTSGBHUUnew · submitted 2025-03-31 · 📡 eess.SY · cs.AI· cs.CC· cs.LG· cs.SY

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

classification 📡 eess.SY cs.AIcs.CCcs.LGcs.SY
keywords powermodellossthermalapplicationslossesmeasurementsnetwork
0
0 comments X
read the original abstract

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{\deg}C to 0.3+-0.3{\deg}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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.