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.

Study on Strength and Durability Properties of Bacterial Concrete

The primary thought of this review is to assess the strength and durability properties of high strength concrete specimens by replacing cement with bacteria for healing cracks. Concrete is the most commonly used construction material all around the world. Cracks are formed due to various reasons. The cracks act as a pathway through which water and toxic salts enter. This causes corrosion and also leads to failure of structure. Repair and Rehabilitation works are costly to be done. In order to overcome this, bacteria is induced into the concrete which leads to the process of Microbial Induced Calcium Precipitate (MICP). The cracks heal by self-healing mechanism and results in crack free concrete structure. It also improves the compressive and tensile strength. In this article a new bacterium has been cultured and identified and is used as a self-healing material in M30 Grade concrete.

A Comparative Investigation on Normal and High Strength Concrete Beams under Torsion

In this study, an experimental investigation was done to study the behaviour of Normal Strength Concrete (NSC) and High Strength Concrete (HSC) Plain beams under torsion with the concrete mix of M40 and M100. No mineral admixtures are used to obtain the required strength of concrete. Eight NSC beams and eight HSC beams whose width was varying with 75 mm, 100 mm, and 150 mm; depth varying as 75 mm, 100 mm, 150 mm and 200 mm; and span of the beams varying 600 mm, 800 mm and 1200 mm were casted and cured to stud the effect of torsion. The principle aim of this study was to understand the torsional behaviour of the NSC and HSC beams for rotation, cracking, size effect and torsional strength. A standard torsional loading method was used for conducting the testing of beams. The results obtained were compared with different theories and code equations. It was observed that the torsional strength of the beam increases with the increase in strength of concrete. HSC beams have higher torsional strength than the NSC beams which has the same amount of reinforcement.

Compressive Fatigue Behaviour of High-Strength Concrete and Mortar: Experimental Investigations and Computational Modelling

A high-strength concrete and mortar subjected to compressive fatigue loading were comparatively investigated using experimental and computational techniques. The focus of the investigations was on the influence of the coarse aggregate in high-strength concrete. Accordingly, the fatigue behaviour was analysed experimentally using the macroscopic damage indicators strain, stiffness and acoustic emission hits. The results clearly show differences in the fatigue behaviour between the concrete and the mortar, especially at the lower stress level investigated. The basalt coarse aggregate here improves the fatigue behaviour of the concrete. Indication of a negative effect can be seen at the higher stress level. A finite element approach with a gradient-enhanced equivalent strain-based damage model combined with a fatigue model was used for the computational simulation of the fatigue behaviour. The damage model includes a differentiation between tension and compression. The fatigue model follows the assumption of the reduction in the material strength based on the accumulated gradient-enhanced equivalent strains. A random distribution of spherically shaped basalt aggregates following a given particle size distribution curve is used for the simulation of concrete. The comparison of the experimentally and computationally determined strain developments of the concrete and mortar shows very good agreement.