Compressive Behavior and Analytical Model of Ultra-Early Strength Concrete-Filled FRP Tube With Zero Curing Time

Fiber-reinforced polymer (FRP) has been widely used in civil engineering due to its light weight, high strength, convenient construction, and strong corrosion resistance. One of the important applications of FRP composites is the concrete-filled FRP tube (CFFT), which can greatly improve the compressive strength and ductility of concrete as well as facilitate construction. In this article, the compressive performances of a normal concrete-filled FRP tube (N-CFFT) column with 5-hour curing time and an ultra-early strength concrete-filled FRP tube (UES–CFFT) column with zero curing time were studied by considering the characteristics of rapid early strength improvement of ultra-early strength concrete and the confinement effect of the FRP tube. Monotonic axial compression tests were carried out on 3 empty FRP tubes (FTs) without an internal filler and 6 CFFT (3 N-CFFTs and 3 UES-CFFTs) specimens. All specimens were cylinders of 200 mm in diameter and 600 mm in height, confined by glass fiber–reinforced polymer (GFRP). Test results indicated that the compressive bearing capacity of the specimens increased significantly by adopting the ultra-early strength concrete as the core concrete of the CFFT, although the curing time was zero. It was also shown that the compressive behavior of the UES–CFFT specimens with zero curing time increased significantly than that of the N-CFFT specimens with 5-hour curing time because the former was able to achieve rapid strength enhancement in a very short time than the latter. The ultimate compressive strength of UES–CFFT specimens with zero curing time reached 78.3 MPa, which was 66.2 and 97.2% higher than that of N-CFFT with 5-hour curing time and FT specimens, respectively. In addition, a simple confinement model to predict the strength of UES–CFFT with zero curing time in ultimate condition was introduced. Compared with the existing models, the proposed model could predict the ultimate strength of UES–CFFT specimens with zero curing time with better accuracy.

Mechanical Performance Prediction for Sustainable High-Strength Concrete Using Bio-Inspired Neural Network

High-strength concrete (HSC) is a functional material possessing superior mechanical performance and considerable durability, which has been widely used in long-span bridges and high-rise buildings. Unconfined compressive strength (UCS) is one of the most crucial parameters for evaluating HSC performance. Previously, the mix design of HSC is based on the laboratory test results which is time and money consuming. Nowadays, the UCS can be predicted based on the existing database to guide the mix design with the development of machine learning (ML) such as back-propagation neural network (BPNN). However, the BPNN’s hyperparameters (the number of hidden layers, the number of neurons in each layer), which is commonly adjusted by the traditional trial and error method, usually influence the prediction accuracy. Therefore, in this study, BPNN is utilised to predict the UCS of HSC with the hyperparameters tuned by a bio-inspired beetle antennae search (BAS) algorithm. The database is established based on the results of 324 HSC samples from previous literature. The established BAS-BPNN model possesses excellent prediction reliability and accuracy as shown in the high correlation coefficient (R = 0.9893) and low Root-mean-square error (RMSE = 1.5158 MPa). By introducing the BAS algorithm, the prediction process can be totally automatical since the optimal hyperparameters of BPNN are obtained automatically. The established BPNN model has the benefit of being applied in practice to support the HSC mix design. In addition, sensitivity analysis is conducted to investigate the significance of input variables. Cement content is proved to influence the UCS most significantly while superplasticizer content has the least significance. However, owing to the dataset limitation and limited performance of ML models which affect the UCS prediction accuracy, further data collection and model update must be implemented.