Abstract
A fatigue damage diagnosis and prognosis approach has been developed based on strain monitoring. The fatigue experiment is conducted on 2024 aluminum specimens with center holes to obtain the strain/crack information. The occurrence of cracks is detected by a thresholding method. A data-driven Gaussian process regression (GPR) algorithm is used to establish the relationship between the crack length and the strain characteristic parameters. A dynamic Bayesian network (DBN) is assembled by combining the GPR algorithm and Paris formula for real-time crack propagation predictions. An experiment has been carried out to illustrate the accuracy of the approach. The results indicate that the threshold method can detect fatigue cracks effectively. The GPR algorithm can accurately identify fatigue crack length and has higher recognition accuracy than other algorithms. The crack propagation prediction error and time consumption of DBN are much smaller than mechanics-based crack growth analysis.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
