Utilizing Artificial Intelligence to Predict the Superplasticizer Demand of Self-Consolidating Concrete Incorporating Pumice, Slag, and Fly Ash Powders

Alkali−Silica Activity and Inhibition Measures of Concrete Aggregate in Northwest China

The alkali−silica reaction (ASR)-induced expansion of mortar bars containing four types of aggregates originating from different regions in northwest China was studied. The chemical composition, mineral composition, vitreous and amorphous substances, and expansion rates were determined using X-ray fluorescence, X-ray diffraction, polarizing microscope images, and the accelerated mortar bar test (AMBT). The inhibitory effects of fly ash and silica fume on the aggregate activity were evaluated. The binary mortar mixes were produced and tested, containing cement and fly ash or silica fume as the partial cement replacement. The microstructure and composition of the ASR products were analyzed by scanning electron microscope energy dispersive spectroscopy (SEM–EDS). The results show that all four types of aggregates exhibited an alkali activity, and that all expansion rates on the 14th day were higher than the standard of 0.1%. The lowest and highest values were 0.2% and 0.3%, respectively. The primary constituent in the chemical compositions of these aggregates was found to be silica. Polarization microscopy also confirmed that they contained alkali-active cryptolites. Fly ash and silica fume could both inhibit alkali activity expansion and the silica fume exhibited a superior inhibition effect. When the fly ash and silica fume contents were 20% and 10%, respectively, the expansion rates of the mortar bar on the 14th day were all less than 0.03%.

Study on Mechanical Properties of Concrete Using Basalt-Based Recycled Aggregate and Varying Curing Conditions

To replace porous basalt, the mechanical properties of concrete with recycled resources and durability improvement were analyzed in this study. The analysis was based on the quality improvement of recycled aggregate, use of fly ash, and changes in curing conditions. Basalt aggregate (BA) with a 3% water absorption, raw recycled aggregate and basalt (RRA), and improved recycled aggregate and basalt (PRA) were the main experimental variables. As PRA was applied to concrete, the compressive strength was lower than that of the specimen comprising BA in the normal strength region, but the modulus of elasticity (22.9 GPa) was equivalent or higher. The initial drying shrinkage increased because of the use of basalt-based recycled aggregate (B-RA). The drying shrinkage of PRA was similar to that of BA with an average difference of <7% as the age increased. The specimens subjected to steam curing exhibited the lowest drying shrinkage. These results showed that pores in the old paste of recycled aggregate increased freeze−thaw resistance because of the increase in the spacing factor. Although the PRA did not satisfy the quality criteria, the efficient use of recycled aggregate achieved an equivalent or higher performance than that of concrete comprising BA and improved durability.

Rapid Test Method for Evaluating Inhibiting Effectiveness of Supplementary Cementitious Materials on Alkali-Silica Reaction Expansion of Concrete

At present, there are many problems in various tests when judging the alkali activity of aggregates. The most practical engineering concrete prism test (CPT) takes one year, and the concrete suppression method needs two years. The aim of this paper is to discuss inhibiting effectiveness of supplementary cementitious materials (SCMs) on alkali–silica reaction (ASR) expansion of concrete and evaluate this rapid test method. Three kinds of aggregates were selected by chemical analysis, XRD and petrographic analysis. The high alkali–silicic acid activity of three aggregates was determined by accelerated mortar bars, concrete microbars and CPT. The expansion of concrete specimens made of three kinds of aggregates was measured and analyzed by using the method of length measurement. By changing the curing temperature to 40 °C, 60 °C and 80 °C, the test period of CPT is accelerated. It proved that the expansion of CPT is larger at 60 °C and smaller at 40 °C. The inhibition test was also accelerated by adding different proportion of SCMs (fly ash or blast furnace slag) and adjusting the curing temperature to 60 °C and 80 °C. On this basis, the inhibition test was accelerated by changing NaOH solution instead of moist air curing. The test period of the accelerated inhibition test can be effectively shortened from two years to 4 months, The expansion trend of each parameter and specimen is evaluated, the evaluation cycle can be adjusted to 5–6 months. The microscopic reaction characteristics of concrete specimens were investigated by means of SEM. According to each parameter and criterion, the judging standard of concrete rapid test and rapid restraint test is given in this paper.

Application of TLS Method in Digitization of Bridge Infrastructures: A Path to BrIM Development

Over the past years, bridge inspection practices and condition assessments were predicated upon long-established manual and paper-based data collection methods which were generally unsafe, time-consuming, imprecise, and labor-intensive, influenced by the experience of the trained inspectors involved. In recent years, the ability to turn an actual civil infrastructure asset into a detailed and precise digital model using state-of-the-art emerging technologies such as laser scanners has become in demand among structural engineers and managers, especially bridge asset managers. Although advanced remote technologies such as Terrestrial Laser Scanning (TLS) are recently established to overcome these challenges, the research on this subject is still lacking a comprehensive methodology for a reliable TLS-based bridge inspection and a well-detailed Bridge Information Model (BrIM) development. In this regard, the application of BrIM as a shared platform including a geometrical 3D CAD model connected to non-geometrical data can benefit asset managers, and significantly improve bridge management systems. Therefore, this research aims not only to provide a practical methodology for TLS-derived BrIM but also to serve a novel sliced-based approach for bridge geometric Computer-Aided Design (CAD) model extraction. This methodology was further verified and demonstrated via a case study on a cable-stayed bridge called Werrington Bridge, located in New South Wales (NSW), Australia. In this case, the process of extracting a precise 3D CAD model from TLS data using the sliced-based method and a workflow to connect non-geometrical information and develop a BrIM are elaborated. The findings of this research confirm the reliability of using TLS and the sliced-based method, as approaches with millimeter-level geometric accuracy, for bridge inspection subjected to precise 3D model extraction, as well as bridge asset management and BrIM development.

Back-Propagation Neural Network Optimized by K-Fold Cross-Validation for Prediction of Torsional Strength of Reinforced Concrete Beam

Due to the limitation of sample size in predicting the torsional strength of Reinforced Concrete (RC) beams, this paper aims to discuss the feasibility of employing a novel machine learning approach with K-fold cross-validation in a small sample range, which combines the advantages of a Genetic Algorithm (GA) and a Neural Network (NN) to predict the torsional strength of RC beams. This research study not only utilizes the application of a Back Propagation (BP) neural network and the Gene Algorithm-Back Propagation (GA-BP) neural network in the prediction of the torsional strength of the RC beam, but it also investigates neural network parameter optimization, including connection weights and thresholds, using K-fold cross-validation. The root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE) and correlation coefficient (R²) are among the evaluation metrics used to assess the performance of the trained model. To elaborate on the superiority of the proposed network models in predicting the torsional strength of RC beams, a parametric study is conducted by comparing the proposed model to three commonly used empirical formulae from existing design codes. The comparative findings of this research study demonstrate that the performance of the BP neural network is highly similar to that of design codes; however, its accuracy is inadequate. After improving the weights and thresholds by k-fold cross-validation and GA, the prediction of the BP neural network shows higher consistency with the actual measured values. The outcome of this study can be used as a theoretical reference for the optimal design of RC beams in practical applications.

Evaluation of the Performance of a Composite Profile at Elevated Temperatures Using Finite Element and Hybrid Artificial Intelligence Techniques

It is very important to keep structures and constructional elements in service during and after exposure to elevated temperatures. Investigation of the structural behaviour of different components and structures at elevated temperatures is an approach to manipulate the serviceability of the structures during heat exposure. Channel connectors are widely used shear connectors not only for their appealing mechanical properties but also for their workability and cost-effective nature. In this study, a finite element (FE) evaluation was performed on an authentic composite model, and the behaviour of the channel shear connector at elevated temperature was examined. Furthermore, a novel hybrid intelligence algorithm based on a feature-selection trait with the incorporation of particle swarm optimization (PSO) and multi-layer perceptron (MLP) algorithms has been developed to predict the slip response of the channel. The hybrid intelligence algorithm that uses artificial neural networks is performed on derived data from the FE study. Finally, the obtained numerical results are compared with extreme learning machine (ELM) and radial basis function (RBF) results. The MLP-PSO represented dramatically accurate results for slip value prediction at elevated temperatures. The results proved the active presence of the channels, especially to improve the stiffness and loading capacity of the composite beam. Although the height enhances the ductility, stiffness is significantly reduced at elevated temperatures. According to the results, temperature, failure load, the height of connector and concrete block strength are the key governing parameters for composite floor design against high temperatures.

Mechanical Properties of Recycled Aggregate Concretes Containing Silica Fume and Steel Fibres

In this study, the impact of steel fibres and Silica Fume (SF) on the mechanical properties of recycled aggregate concretes made of two different types of Recycled Coarse Aggregates (RCA) sourced from both low- and high-strength concretes were evaluated through conducting 60 compressive strength tests. The RCAs were used as replacement levels of 50% and 100% of Natural Coarse Aggregates (NCA). Hook-end steel fibres and SF were also used in the mixtures at the optimised replacement levels of 1% and 8%, respectively. The results showed that the addition of both types of RCA adversely affected the compressive strength of concrete. However, the incorporation of SF led to compressive strength development in both types of concretes. The most significant improvement in terms of comparable concrete strength and peak strain with ordinary concrete at 28 days was observed in the case of using a combination of steel fibres and SF in both recycled aggregate concretes, especially with RCA sourced from high strength concrete. Although using SF slightly increased the elastic modulus of both recycled aggregate concretes, a substantial improvement in strength was observed due to the reinforcement with steel fibre and the coexistence of steel fibre and SF. Moreover, existing models to predict the elastic modulus of both non-fibrous and fibrous concretes are found to underestimate the elastic modulus values. The incorporation of SF changed the compressive stress-strain curves for both types of RCA. The addition of steel fibre and SF remarkably improved the post-peak ductility of recycled aggregates concretes of both types, with the most significant improvement observed in the case of RCA sourced from a low-strength parent concrete. The existing model to estimate the compressive stress-strain curve for steel fibre-reinforced concrete with natural aggregates was found to reasonably predict the compressive stress-strain behaviour for steel fibres-reinforced concrete with recycled aggregate.