Simulation-based design using variable fidelity optimization

TL;DR: A modified variable complexity modeling (MVCM) framework that uses a neural network to replace the Taylor series after several warm-up iterations to enhance the optimal RJA configuration compared with low-fidelity analysis results.

TL;DR: A difference mapping method using least square support vector regression is developed in this work, as a special metamodelling methodology that includes variable-fidelity data, to replace the computationally expensive computer codes.

TL;DR: A multi-fidelity M&S methodology for enhancing simulation speed while minimizing accuracy loss and maximizing model reusability, in the M &S-based analysis is proposed.

TL;DR: An approach already applied to fixed wing aircraft is now ported to the helicopter rotor blade optimization, a surrogate based optimization process including variable-fidelity methods, which proves to be highly beneficial and the need to perform multi-objective optimizations for rotor blade design is highlighted.