DeepAI AI Chat
Log In Sign Up

Thermal Neural Networks: Lumped-Parameter Thermal Modeling With State-Space Machine Learning

by   Wilhelm Kirchgässner, et al.

With electric power systems becoming more compact and increasingly powerful, the relevance of thermal stress especially during overload operation is expected to increase ceaselessly. Whenever critical temperatures cannot be measured economically on a sensor base, a thermal model lends itself to estimate those unknown quantities. Thermal models for electric power systems are usually required to be both, real-time capable and of high estimation accuracy. Moreover, ease of implementation and time to production play an increasingly important role. In this work, the thermal neural network (TNN) is introduced, which unifies both, consolidated knowledge in the form of heat-transfer-based lumped-parameter models, and data-driven nonlinear function approximation with supervised machine learning. A quasi-linear parameter-varying system is identified solely from empirical data, where relationships between scheduling variables and system matrices are inferred statistically and automatically. At the same time, a TNN has physically interpretable states through its state-space representation, is end-to-end trainable – similar to deep learning models – with automatic differentiation, and requires no material, geometry, nor expert knowledge for its design. Experiments on an electric motor data set show that a TNN achieves higher temperature estimation accuracies than previous white-/grey- or black-box models with a mean squared error of 3.18 K^2 and a worst-case error of 5.84 K at 64 model parameters.


page 1

page 5

page 6

page 8


Thermal regulation in thin vascular systems: A sensitivity analysis

One of the ways natural and synthetic systems regulate temperature is vi...

On Radiation-Based Thermal Servoing: New Models, Controls and Experiments

In this paper, we introduce a new sensor-based control method that regul...

Uncertainty Propagation of Initial Conditions in Thermal Models

The operation of machine tools often demands a highly accurate knowledge...

Transfer-learning-based Surrogate Model for Thermal Conductivity of Nanofluids

Heat transfer characteristics of nanofluids have been extensively studie...

Imaging with thermal noise induced currents

We use thermal noise induced currents to image the real and imaginary pa...