Prof. John Ekaterinaris
Embry-Riddle Aeronautical University - Daytona Beach, Florida, USA

Title: Machine Learning-based Surrogate Modeling Approaches for Fixed-wing and Rotary Wing Store Separation

Abstract: In pursuit of deriving a limited expense store trajectory prediction model, this work investigates the application of two data-driven surrogate modeling approaches for the prediction of surface pressure and shear stress distributions of a store separating under supersonic conditions. Through the use of computational fluid dynamics (CFD), store separation simulations at three supersonic Mach numbers were carried out, M = 1.2, 1.4, and 1.6, for fixed-wing store separation. Pressure and shear stress distributions were recorded and used to construct a proper orthogonal decomposition (POD) and convolutional neural network (CNN) based surrogate model such that predictions of store load distributions could be obtained under new operating conditions. Load predictions are then integrated and coupled with the equations of motion to predict store trajectories at intermediate Mach numbers of M = 1.3 and M = 1.5. Results demonstrated that both the CNN and POD-based surrogate models were proven capable of providing both high fidelity distributed load and trajectory predictions at a greatly reduced computational expense. Computational run times for a single trajectory prediction simulation at a very reduced cost. The same approach was then used in the more computationally intensive case of store separation from a helicopter in hover do demonstrate that very significant reduction of computational time can be achieved. The resulting reduced order models can be utilized for multiparameter store trajectory optimization studies of store separation from helicopter in hover.

BIO: Dr. John A. Ekaterinaris received his B.S. in Electrical and Mechanical Engineering from the Aristotle University of Thessaloniki in Greece in Oct. 1977. Started graduate studies in the US in 1981 and revived his M.Sc. in Mechanical Engineering in 1982 and his Ph.D. from the School of Aerospace Engineering in 1987, both at the Georgia Institute of Technology, Atlanta GA.

Between 1987 – 1995, was faculty at the Naval Postgraduate Scholl at Monterey CA and preformed his research at NASA–Ames at Moffett Field CA through the Navy/NASA joint institute of Aeronautics. He took a position at RISOE/DTU in Denmark between 1995 – 1997 where he worked on wind energy. He returned to CA and worked at Nielsen Engineering and Research (NEAR) between 1997 – 2000, while at the same time consulted with Boeing and other High Tech companies in the bay area.

In Oct. 2000 he took the Research Director position at FORTH/IACM, where he remained until 2005. In Sept. 2005 he joined the faculty of Mechanical and Aerospace Engineering at the University of Patras. He joined the faculty of Embry-Riddle Aeronautical University in August 2012 where he is currently teaching and performing research.

His interests are computational mechanics (including aerodynamics, magnetogasdynamics, electromagnetics, aeroacoustics, flow transition, turbulence research, and flow structure interaction), development and applications of high order methods for PDEs, multiscale phenomena, stochastic PDE’s, and biomechanics and more recently machine learning and uncertainty quantification. He is author of over 80 journal papers. He has been member American Institute of Aeronautics and Astronautics (AIAA), where he served as member at the Flight Mechanics and Fluid Dynamics Technical Committees, and AIAA associate fellow.

He performed funded research thought the offices of AFOSR and ARO, the European Space Agency (ESA), and through the EU framework programs. He has been associate editor of the Journal Progress in Aerospace Science (JPAS) and editor in chief of the Journal Aerospace Science and Technology (AESCTE).