Thermal Simulations for Optimization of Dry Transformers Cooling System

An efficient computational model based on principles of thermo-fluid dynamics is crucial for thermal design and optimization of transformers. In this paper we propose a Thermal/Pressure Network (TPN) model of a dry transformer encapsulated in enclosure with natural or forced cooling. The network model has been validated by Computational Fluid Dynamics (CFD) simulations with ANSYS Fluent and then applied for the computation of real transformers, comparing results to thermal measurements. Finally, the parameterized transformer TPN model has been utilized in an optimization loop in order to improve the cooling system. In this respect, the use of a gradient-free optimization algorithm under a multi-objective frame is recommended to avoid local minima and smooth the dependency on the initial guess.