Apurva Anand

Apurva Anand has a PhD in Aerospace Engineering from Alfred Gessow Rotorcraft Center at University of Maryland College Park. His active areas of research include Machine learning assisted aerodynamic design and optimization of rotor and wind turbine blades. He also works on inverse design frameworks using neural networks, preform uncertainty quantification to predict sensitivities of rotor blades on geometric variations. He has built AGRC Surrogate as a part of his PhD research, which is a neural networks based C81 table generator for rotorcraft airfoils. AGRC Surrogate has also been integrated with optimization algorithms to perform rapid airfoil design without having to do full-order CFD. This brings down the cost of computation from hundreds of core-hours on HPC to seconds on a laptop. AGRC Surrogate is an open source tool available on github.He also works actively on rotor blades optimization with multiple objectives using NSGA algoriths with design and performance constraints. He also worked at Airbus as Flight Physics Engineer, working on certification of A350 family for failure case certification.For his master's thesis, he worked on aerodynamic interaction of nose-mounted propeller aircraft. He studied the installation effect, impact on stall margin, trim and optimum propeller mounting angle for the aircraft.