We generalise Spatial Transformer Networks (STN) by replacing the parametric transformation of a fixed, regular sampling grid with a deformable, statistical shape model which is itself learnt. We call this a Statistical Transformer Network (StaTN). By training a network containing a StaTN end-to-end for a particular task, the network learns the optimal nonrigid alignment of the input data for t...

At Siemens the in-house CFD code UniFlow is used to analyse fluid flow and heat transfer in oilimmersed dry-type transformers, as well transformer components like windings, cores, tank walls, radiators. It can be employed perform steady state transient analyses. This paper describes its physical models numerical solution methods. Moreover, it presents an application a valve winding of HVDC tran...

Solid-state transformers (SSTs) are a promising solution photovoltaic (PV), wind, traction, data center, battery energy storage system (BESS), and fast charging electric vehicle (EV) applications. The traditional SSTs typically three-stage, i.e., hard-switching cascaded multilevel rectifiers inverters with dual active bridge (DAB) converters, which leads to bulky passives, low efficiency, high ...

Transformer fault diagnosis and repair is a complex task that includes many possible types of faults and demands special trained personnel. In this paper, Petri Nets are used for the simulation of transformer fault diagnosis process and the definition of the actions followed to repair the transformer. An oil thermometer and a Buchholz relay are used for transformer fault detection. Simulation r...

Boundary Conduction Mode (BCM) and Discontinuous Conduction Mode (DCM) control strategies are widely used for the flyback micro inverter. For the interleaved flyback micro inverter, the dominant losses with heavy load include the conduction loss of the power MOSFETs and diodes and the loss of the transformer while the dominant losses with light load include the gate driving loss, the turn off l...