Engineers always look for new methods to speed-up the aircraft design process. Aerody- namic analysis are often the most costly in terms of computational time. Machine learning techniques as surrogate modeling are more and more used in this domain, as well as for optimisation workflows.CEASIOMpy is an open source conceptual aircraft design software written in Python and using the CPACS standard, an XML data definition for aircraft. CEASIOMpy includes modules which cover several of the main aircraft design disciplines. These modules can be connected and executed in an order defined by the user depending on his needs. CEA- SIOMpy includes aircraft geometry CAD, Weight & Balance estimation, aerodynamics (Vor- tex Lattice Methods and SU2), and stability analysis modules. The aerodynamic modules of CEASIOMpy are being used and further developed in the framework of the H2020 project AGILE4.0 in collaboration with other European partners in order to run Multidisciplinary Design Analysis and Optimization (MDAO) on aircraft design cases.Surrogate modeling was implemented in CEASIOMpy using the SMT libraries. First, a few high fidelity Euler calculation are performed for different flight state parameters (angle of attack, Mach number and altitudes), then these results are used to train a surrogate model that can be used to generate a more complete aerodynamics database or replace costly aerodynamic calculations in an optimisation workflow.In this paper we will describe the different parameters that are used to create and employ surrogate models efficiently in CEASIOMpy. Accuracy testing will be performed on different test cases. We will also evaluate the possibility to add geometry parameters (such as wing span, fuselage length, etc.) in a surrogate model to make it suitable for a real optimisation workflow.

The work presented in this report has been performed in the framework of the AGILE 4.0 project (Towards Cyber-physical Collaborative Aircraft Development) and has received funding from the European Union Horizon 2020 Programme under grant agreement nr 815122.