Towards Real-Time Pilot-in-the-Loop Simulation of Rotorcraft with Fully-Coupled CFD Solutions of Rotor / Terrain Interactions

Open Access
Oruc, Ilker
Graduate Program:
Aerospace Engineering
Doctor of Philosophy
Document Type:
Date of Defense:
August 02, 2017
Committee Members:
  • Joseph F. Horn, Dissertation Advisor
  • Joseph F. Horn, Committee Chair
  • Edward C. Smith, Committee Member
  • Sven Schmitz, Committee Member
  • Savas Yavuzkurt, Outside Member
  • modeling
  • simulation
  • pilot-in-the-loop
  • rotorcraft
  • terrain
  • ship airwake
  • dynamic interface
  • DI
  • helicopter/ship
  • coupled
  • fully-coupled
  • fully coupled
  • ground effect
  • CFD
  • aerodynamics
  • flight control
  • flight dynamics
  • ship landing
  • ship approach
  • computational
  • fluid
  • dynamics
  • real-time
  • manned
  • sloped
  • partial ground
  • acceleration
  • helicopter simulation
  • high-performance-computing
  • flight simulator
  • MPI
  • helicopter dynamics
  • SFS2
  • MPMD
  • actuator disk
  • ADM
  • ALM
  • simple frigate ship
  • non-linear
  • NLDI
  • UH-60
  • flight performance
  • one-way coupled
  • two-way coupled
  • recirculation
  • coupled simulation
  • coupling interface
  • IGE
  • OGE
  • hover
  • Navier-Stokes
  • Gaussian
This thesis presents the development of computationally efficient coupling of Navier-Stokes CFD with a helicopter flight dynamics model, with the ultimate goal of real-time simulation of fully coupled aerodynamic interactions between rotor flow and the surrounding terrain. A particular focus of the research is on coupled airwake effects in the helicopter / ship dynamic interface. A computationally efficient coupling interface was developed between the helicopter flight dynamics model, GENHEL-PSU and the Navier-Stokes solvers, CRUNCH/CRAFT-CFD using both FORTRAN and C/C++ programming languages. In order to achieve real-time execution speeds, the main rotor was modeled with a simplified actuator disk using unsteady momentum sources, instead of re- solving the full blade geometry in the CFD. All the airframe components, including the fuselage are represented by single aerodynamic control points in the CFD calculations. The rotor downwash influence on the fuselage and empennage are calculated by using the CFD predicted local flow velocities at these aerodynamic control points defined on the helicopter airframe. In the coupled simulations, the flight dynamics model is free to move within a computational domain, where the main rotor forces are translated into source terms in the momentum equations of the Navier-Stokes equations. Simultaneously, the CFD calculates induced velocities those are fed back to the simulation and affect the aerodynamic loads in the flight dynamics. The CFD solver models the inflow, ground effect, and interactional aerodynamics in the flight dynamics simulation, and these calculations can be coupled with solution of the external flow (e.g. ship airwake effects). The developed framework was utilized for various investigations of hovering, forward flight and helicopter/terrain interaction simulations including standard ground effect, partial ground effect, sloped terrain, and acceleration in ground effect; and results compared with different flight and experimental data. In near ground cases, the fully-coupled flight dynamics and CFD simulations predicted roll oscillations due to interactions of the rotor downwash, ground plane, and the feedback controller, which are not predicted by the conventional simulation models. Fully coupled simulations of a helicopter accelerating near ground predicted flow formations similar to the recirculation and ground vortex flow regimes observed in experiments. The predictions of hover power reductions due to ground effect compared well to a recent experimental data and the results showed 22% power reduction for a hover flight z/R=0.55 above ground level. Fully coupled simulations performed for a helicopter hovering over and approaching to a ship flight deck and results compared with the standalone GENHEL-PSU simulations without ship airwake and one-way coupled simulations. The fully-coupled simulations showed higher pilot workload compared to the other two cases. In order to increase the execution speeds of the CFD calculations, several improvements were made on the CFD solver. First, the initial coupling approach File I/O was replaced with a more efficient method called Multiple Program Multiple Data MPI framework, where the two executables communicate with each other by MPI calls. Next, the unstructured solver (CRUNCH CFD), which is 2nd-order accurate in space, was replaced with the faster running structured solver (CRAFT CFD) that is 5th-order accurate in space. Other improvements including a more efficient k-d tree search algorithm and the bounding of the source term search space within a small region of the grid surrounding the rotor were made on the CFD solver. The final improvement was to parallelize the search task with the CFD solver tasks within the solver. To quantify the speed-up of the improvements to the coupling interface described above, a study was performed to demonstrate the speedup achieved from each of the interface improvements. The improvements made on the CFD solver showed more than 40 times speedup from the baseline file I/O and unstructured solver CRUNCH CFD. Using a structured CFD solver with 5th-order spacial accuracy provided the largest reductions in execution times. Disregarding the solver numeric, the total speedup of all of the interface improvements including the MPMD rotor point exchange, k-d tree search algorithm, bounded search space, and paralleled search task, was approximately 231%, more than a factor of 2. All these improvements provided the necessary speedup for approach real-time CFD. For the Pilot-in-the-loop flight dynamics and CFD simulations, a simplified backward facing step was chosen. A study was performed to quantify the grid sensitivity of the helicopter dynamic response and results showed that at least 2 ft grid resolution will be required in the airwake of the ship to capture general coupled airwake effects on the approach. Finally, a network configuration was introduced for the Pilot-in-the-loop CFD simulations and the Pilot-in-the-loop CFD simulation framework was implemented and tested in the PSU Flight Simulation lab bringing coupled CFD into a realistic flight simulation environment. A near-real-time (3x slower than real-time) Pilot-in-the-loop CFD simulation for a simple wake shedding case was demonstrated with 0.38 million structured grid cells running on 352 processors and results are presented.