Damage Assessment of an Aircraft’s Wing Spar Using Gaussian Process Regressors

In this work, the beginning of developing a structural health monitoring (SHM) approach is presented for a representation of an aircraft composite wing spar. Lack of directly available field performance data is mitigated using a high-fidelity finite element model and a probabilistic understanding of the aerodynamic loads under different flight regimes, simulating realizations of the spar’s performance in service. Debonding damage between laminates was included in the model at different locations in the spar, with various damage sizes. Under the expectation of a fiber optic measurement system being used for data collection, the target measurements are uniaxial strain, measured in several paths throughout the spar. Given measured strain, the damage assessment problem is probabilistically formulated by defining local buckling from debonding as the observable damage, which is fundamentally characterized by load-dependent buckling eigenvalues. This FE physical model is highly computationally intensive, so machine learning was used to build a “run time” surrogate model to learn the relationships between inputs – loads and damage conditions, and outputs – strain and buckling eigenvalues. In addition, other surrogate models were created to solve the inverse problem, linking strain data to damage classification (size and location). Finally, the probabilistic frameworks are demonstrated and damage criticality assessment, which is directly related to the buckling load, is performed via Gaussian process regression.