Predicting FRP Plate End Debonding with a Neural Network Model Enhanced by Modified Sparrow Search Algorithm

Abstract

Fiber Reinforced Polymer (FRP) plates are widely used to strengthen structural members, but their potential is limited by plate end debonding failure. Existing models that are developed to address plate end debonding failure considered only few parameters and primarily based on fracture mechanics or shear strength of beams. Following study aims to develop a Back Propagation Neural Network (BPNN) model optimized by a quantum-computations and multi-strategy enhanced Sparrow Search Algorithm (QMESSA) to effectively forecast the plate end debonding load of externally bonded FRP plates. Where the model utilized complex nonlinear relationship between all the prominent governing parameters and the debonding load. Optimization accuracy and generalization is hindered by local minima problem in BPNN. Incorporating QMESSA significantly reduced the local minima problem in BPNN substantiated by an increased testing data sets regression value from 0.82 to 0.98. Reliability analysis showed that the model outperformed the existing international codes and shear-based model in terms of accuracy and stability. Results from the correlation analysis of parameters revealed that the web reinforcement ratio is the most influential parameter for debonding prediction. Therefore, QMESSA optimized BPNN model can be used as an effective tool for designing FRP to prevent FRP plate end debonding.