Artificial Intelligence Approaches for Structural Health Monitoring of Aerospace Structures

Structural health monitoring (SHM) and non-destructive evaluation (NDE) have been a significant research topic to help with damage detection in aerospace structures. SHM and NDE techniques are based on extracting damage sensitive features to determine the criticality of damage and lifetime of a structure. Acoustic emission (AE) signal detection is an important technique in SHM and NDE especially for fatigue crack growth. AE signals for thin aerospace structures consist of ultrasonic guided Lamb waves that propagate through the structure. This thesis focuses on AE signal repeatability, load at which AE signals occur, feature extraction, artificial intelligence and electro-mechanical impedance of a piezoelectric wafer active sensor (PWAS) in response to a crack in thin aerospace structures. The artificial intelligence techniques explored include machine learning model classification and deep learning classical and convolutional neural networks designed to understand the meaning behind each AE signal that comes from a fatigue crack. The goal of this research is to distinguish AE signals from fatigue growing cracks into two categories; crack face rubbing and crack growth. From there, we want to determine the crack length based on the AE signal. With the understanding of the AE signal and artificial techniques created from this research, when applied to industry, we will be able to locate cracks on an aerospace structure and determine whether the structure needs maintenance before it results in catastrophic failure