Abstract
In this study, two different methods of data mining are used to develop new formulations for predicting the maximum bond strength force of near-surface-mounted fiber-reinforced polymer (FRP) systems in concrete. The advantages of each method are employed to find the most important parameters in estimating the maximum bond strength. A comprehensive database is used to develop new formulations for the maximum bond strength. Several effective parameters like geometrical and mechanical properties of the FRP, geometrical properties of the groove, bonded length, and concrete strength are involved in prediction of the maximum bond strength. The multivariate adaptive regression splines algorithm is implemented to accomplish sensitivity analysis. The results indicate that the geometry and mechanical properties of the FRP are the most important parameters. Alternatively, the M5′ algorithm as a rule-based method is employed to develop a more practical and simple model for estimating the maximum bond strength. Comparison of the developed models and the most common design codes demonstrates the superiority of the models in terms of the accuracy. Furthermore, the safety analysis based on demerit points classification scale also confirms the reliability of the proposed formulations.
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: Iranian Journal of Science and Technology, Transactions of Civil Engineering
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.
