Gaussian Process NARX Model for Damage Detection in Composite Aircraft Structures

Samuel da Silva (1) , Luis G. G. Villani (2) , Marc Rébillat (3) , Nazih Mechbal (3)

1 UNESP - Universidade Estadual Paulista Júlio de Mesquita Filho = São Paulo State University
2 UFES - Universidade Federal do Espirito Santo
3 PIMM - Laboratoire Procédés et Ingénierie en Mécanique et Matériaux

This article demonstrates the Gaussian process regression model’s applicability combined with a nonlinear autoregressive exogenous (NARX) framework using experimental data measured with PZTs’ patches bonded in a composite aeronautical structure for concerning a novel structural health monitoring (SHM) strategy. A stiffened carbon-epoxy plate regarding a healthy condition and simulated damage on the center of the bottom part of the stiffener is utilized. Comparing the performance in terms of simulation errors is made to observe if the identified models can represent and predict the waveform with confidence bounds considering the confounding effect produced by noise or possible temperature variations assuming a dataset preprocessed using principal component analysis. The results of the GP-NARX identified model have attested correct classification with a reduced number of false alarms, even with model uncertainties propagation regarding healthy and damaged conditions.

Mots clés: NARX model; Guided wave propagation; composite structures; Nonlinear damage; Stiffener debonding; Propagation of uncertainties; Damage classification; Diagnostic decision support; Diagnostic feature extraction; Prognosis; Structural engineering; Testing methodologies; Wave propagation modeling; Mechanics of Materials; Safety; Risk; Reliability and Quality; Civil and Structural Engineering; Gaussian process; NARX model

Domaines: Matériaux et structures en mécanique [physics.class-ph]; Acoustique [physics.class-ph]

Samuel da Silva, Luis G. G. Villani, Marc Rébillat, Nazih Mechbal. Gaussian Process NARX Model for Damage Detection in Composite Aircraft Structures. Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems, 2021, 5 (1), pp.011007. ⟨10.1115/1.4052956⟩. ⟨hal-03675467⟩