A C-HIL based data-driven DC-DC power electronics converter model for system-level studies

We propose to exploit a Controller Hardware-In-
the-Loop (C-HIL) digital twin of power electronics converters
to acquire data for deriving a model that is usable in system-
level studies. An enhanced neural network-based polytopic model
(a black-box model) is used for this purpose. The choice of this
model is motivated by its simplicity and the ability to conceal the
converter’s topology and control algorithm within its structure,
thus ensuring the data privacy of power electronics converter
manufacturers. The capability of the proposed approach to
capture the primary dynamics of converters is demonstrated,
and the approach is validated on an industrial DC-DC power
electronics converter.