Data-Driven Full-Field Prediction of Rotorcraft Fuselage Using Measurable Acceleration Response

This paper presents a study aimed at predicting the full-field acceleration response of a rotorcraft fuselage. The prediction was achieved from the acceleration response observed at a limited sensor location on the rotorcraft. Moreover, the prediction was realized through a framework that used a data-driven model order reduction and long-short-term memory artificial neural network. To validate the performance of the proposed framework, a rotor/fuselage one-way coupled analysis was performed by considering a fuselage with a utility helicopter configuration and a platform rotorcraft. As a result, the efficiency and accuracy of the full-field prediction performance were confirmed by comparing with the finite element solutions.