34th Congress of the International Council of the Aeronautical Sciences

04.1 - Aerospace Grade Materials, Structural Analysis, Fatigue and Damage Tolerance

DEVELOPMENT OF A MACHINE LEARNING-BASED STRESS SPECTRUM ESTIMATION TECHNIQUE FOR FATIGUE MONITORING

E.G. Park, South Korea; S.H. Jeong, South Korea; J.Y. Cho, South Korea; J.H. Kim, South Korea

A multiple linear regression model and an artificial neural network regression model were constructed to predict bending moment and strain sensor measurements attached to the aircraft wings, horizontal/vertical tails, and fuselage from flight parameters recorded during flight testing. And the regression performance of the two models was evaluated, and it was found that the ANN was more suitable.


View Paper