Surrogated finite element models using machine learning

Publication Date


Document Type

Conference Proceeding

Publication Title

AIAA Scitech 2021 Forum



First Page


Last Page



Current maintenance intervals of mechanical systems are scheduled a priori based on the life of the system, resulting in expensive maintenance scheduling, and often undermining the safety of passengers. This problem is particularly relevant in the development of autonomous vehicles, especially in the concept of urban air mobility. The actual usage of the vehicle will be used to predict stresses in the structure and therefore to define maintenance scheduling. Machine learning algorithms, specifically the Random Forest algorithm, can be used to create surrogate finite element models that map a reduced set of data coming from real-time measurements of a structure into a detailed/high-fidelity finite element analysis model of the same system. As a result, the FEA-based machine learning approach directly estimates the dynamic response over the entire system during operations, thus improving the ability to define ad-hoc, safe and efficient maintenance procedures. The predictive performance of random forest algorithm is presented for direct estimation of the acceleration distribution over a beam structure.


Aerospace Engineering; Aviation and Technology