Prediction of FRUHPSCC mechanical property using developed hybrid neural networks

Abstract

This study focuses on the production of durable and high-quality concrete that aligns with the United Nations Sustainable Development Goals (SDGs). Specifically, it aims to fulfill SDG 9 (Industry, Innovation, and Infrastructure) and SDG 11 (Sustainable Cities and Communities). However, producing fiber-reinforced ultra-high performance self-compacting concrete (FRUHPSCC) presents a challenge in achieving the desired mechanical properties. As a result, constructing numerous trial samples increases costs and time. To address this issue, an Artificial Neural Network (ANN) can accurately predict the FRUHPSCC's mechanical properties. The study utilized garnet and basalt aggregates, nanosilica, steel fiber, and other components to make FRUHPSCC and tested its compressive and tensile strengths and microstructure. By utilizing a dataset of experimental results, five types of ANN were developed with different training algorithms, and five hybridized types of ANN employing the Grasshopper Optimization Algorithm (GOA) predicted the compressive strength of this type of concrete. The results indicated that their predictions were highly accurate, and the hybridization of ANNs with GOA increased prediction accuracy further. Notably, the network combining trainlm and GOA produced the highest prediction accuracy, showing that ANNs can predict FRUHPSCC's compressive strength accurately while reducing production costs and time.