Abstract
Aiming at life-cycle condition monitoring of high-strength bolt connections, a physics-guided deep learning framework integrating supervised and unsupervised learning was developed to diagnose manifold damage mechanisms and identify different loading stages using acoustic emission (AE) data. For data preprocessing, empirical wavelet transform (EWT) was introduced to provide adaptive and compact time–frequency representations of AE signals where diverse damage mechanisms behaved with various energy distributions. A convolutional neural network (CNN) model was first built to extract damage-related features from multiscale EWT matrices of AE data labeled by the loading stages I, II-III, and IV that were redefined according to their dominant damage mechanisms. Stage I (static friction) could be identified directly, which was characterized by the distinct damage mechanism of plastic deformation of asperities. After that, Gaussian mixture model (GMM) was applied to cluster the extracted feature vectors of AE data induced by multiple damage mechanisms overlapped among stages II (sliding), III (confined), and IV (failure). With the help of Bayesian information criterion (BIC), three damage mechanisms were recognized, including abrasive wear of asperities, adhesive wear of asperities, and plastic deformation and cracking of screw, which were validated by their EWT components. Finally, based on the proportions of AE data corresponding to diverse damage mechanisms, the rules were established for identifying the four loading stages of high-strength bolt connections. Experimental results demonstrated that the three-class CNN model with data labeled by the redefined loading stages achieved a higher accuracy than the four-class CNN model with data straightforwardly labeled by the original loading stages. Not only the critical damage states of static friction failure (looseness) and shear failure, but the four loading stages of high-strength bolt connections and their overlapped damage mechanisms were successfully identified by the physics-guided CNN-GMM framework.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.