Abstract
In order to avoid the debonding failure of FRP-strengthened RC beams, most codes have proposed models of the allowable debonding strain of FRP. However, experimental studies have shown that the incomplete consideration of parameters suggested by the codes leads to low accuracy and greater variability, and it is impossible to guarantee that the strengthened members will not be peeled off. In order to accurately calculate the allowable debonding strain of FRP-strengthened RC beams, a neural network model for predicting allowable debonding strain of FRP-strengthened RC beams was established, and genetic algorithm were introduced to optimize the weights and thresholds of the network. The established model was trained and simulated through experiment data. The results show that the established model has a coefficient of variation of 17%, and compared with the traditional BP neural network and codes, the built model has better accuracy and stronger robustness.
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 callMore From: IOP Conference Series: Earth and Environmental Science
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.
