Guided wave-hidden Markov model for on-line crack evaluation of a full-scale aircraft

Abstract

Structural Health Monitoring (SHM) has been embraced as an effective method in the aerospace industry. However, one of the main problems hindering SHM for practical usages is the reliable evaluation of damages under in-service conditions that introduce various uncertainties and difficulties for effectively interpreting SHM signals. The Hidden Markov Model (HMM)-based method has been proved to be potential for improving the reliability of damage evaluation under in-service conditions since it can explicitly model the uncertainties during damage state transition and SHM process. Nonetheless, traditional HMM-based damage evaluation methods need sufficient prior data of several discrete damage levels for training. These prior data come from historical experiments or simulations, which may not be sufficient for a new target structure. In this paper, a Guided Wave (GW)-health HMM damage evaluation method with an on-line calibration strategy is proposed to realize quantitative evaluation of damage propagation under time-varying conditions. At the off-line stage, a health HMM is constructed with the prior GW-SHM data collected under the structural healthy state. The likelihood probability of the on-line monitored GW-SHM feature sequence belonging to the prior health HMM is calculated for detecting the damage initiation. A new health-HMM is trained with the health data from the current target structure once the damage is found, replacing the prior health HMM. On this basis, a calibration strategy is conducted to calibrate the likelihood probability to the damage size for quantitative damage evaluation under time-varying conditions in real-time. Finally, the proposed method is validated on the fatigue test of a full-scale aircraft under an actual flight spectrum. The fatigue crack is reliably evaluated, and the maximum error of the evaluated crack length is 0.5 mm.