Mechanical Property Prediction Model Based on Concrete Microstructure and Its Application in Seismic Reinforcement

Abstract

Seismic reinforcement is a critical aspect of ensuring structural integrity during earthquakes. Concrete, a ubiquitous construction material, plays a vital role in seismic resistance. In this manuscript proposes a Mechanical Property Prediction Model Based on Concrete Microstructure and Its Application in Seismic Reinforcement (MPPB-CAMSR- RICCNN). Initially, the data is collected from the “Concrete Data” information set. Then, the collected information is fed to Get Ready for processing segment. In to Get Ready for processing stage, then, the input data are pre-processed using Multivariate Fast Iterative Filtering (MFIF) is used to clean the data. Then pre-processed output is given to RICCNNthat predicts the mechanical properties of high-performance fiber-reinforced cementations composites (HPFRCC). The weight parameters of RICCNN are optimized using Banyan Tree Growth Optimization (BTGO). The planned MPPB-CAMSR- RICCNN method is implemented and the presentation metrics like Correctness, exactness, compassion, specificity, F1-score, and computational time are appraised. The presentation of suggested technique was executed in the Python structure. The performance of the suggested MPPB-CAMSR- RICCNN approach attains22.5%, 21.5% and 26% higher accuracy, 23.06%, 25.33% and 20.98% higher Precision and 22.12%, 20.33% and 23.98% higher compassion compared with present methods like Predicting Mechanical Properties of HPFRCC by Integrating Micromechanics and Machine Learning (PMHPR-ML), A Predictive Mimicker of Fracture Behavior in Fiber Reinforced Concrete Using Machine Learning (PMFRC-ANN), and Hybrid machine learning-based prediction model for the bond strength of corroded Cr alloy-reinforced coral aggregate concrete (PBSCAC-SVR).By comparing other three existing methods, the proposed MPPB-CAMSR- RICCNN method gives high accuracy models respectively.