This study focuses on using various machine learning (ML) models to evaluate the shear behaviors of ultra-high-performance concrete (UHPC) beams reinforced with glass fiber-reinforced polymer (GFRP) bars. The main objective of the study is to predict the shear strength of UHPC beams reinforced with GFRP bars using ML models. We use four different ML models: support vector machine (SVM), artificial neural network (ANN), random forest (R.F.), and extreme gradient boosting (XGBoost). The experimental database used in the study is acquired from various literature sources and comprises 54 test observations with 11 input features. These input features are likely parameters related to the composition, geometry, and properties of the UHPC beams and GFRP bars. To ensure the ML models' generalizability and scalability, random search methods are utilized to tune the hyperparameters of the algorithms. This tuning process helps improve the performance of the models when predicting the shear strength. The study uses the ACI318M-14 and Eurocode 2 standard building codes to predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams. The ML models' predictions are compared to the results obtained from these building code standards. According to the findings, the XGBoost model demonstrates the highest predictive test performance among the investigated ML models. The study employs the SHAP (SHapley Additive exPlanations) analysis to assess the significance of each input parameter in the ML models' predictive capabilities. A Taylor diagram is used to statistically compare the accuracy of the ML models. This study concludes that ML models, particularly XGBoost, can effectively predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams.

Nanotechnology has emerged as a field with promising applications in building materials. Nanotechnology-based mortars are examples of such building materials that have widespread applications in the construction industry. The main nanomaterials used in mortars include nano-silica, nano-magnesium oxide, nano-alumina, nano-titanium oxide, nano-zinc oxide, nano-clay, and nano-carbon. This review paper presents a summary of the properties and effects of these nanomaterials on cement mortar in terms of its fresh-state and hard-state properties. The fresh-state properties include the setting time, consistency, and workability, while the hard-state properties include mechanical properties such as compressive, flexural, tensile strengths, as well as the elasticity modulus, in addition to durability properties such as water absorption, shrinkage strain, strength loss due to freeze–thaw cycles, and chloride penetration, among others. Different nanomaterials cause different physical and chemical alterations within the microstructures of cement mortar. Therefore, the microstructural characterization and densification of mortar are discussed in detail at varying temperatures. In general, the involvement of nanomaterials in cement mortar influences the fresh-state properties, enhances the mechanical properties, and impacts the durability properties, while reducing the porosity present in the mortar matrix. Cementitious nanomaterials can create a pathway for the easy injection of binding materials into the internal microstructures of a hydration gel to impact the hydration process at different rates, whereas their non-cementitious counterparts can act as fillers. Furthermore, the research gaps and future outlook regarding the application of nanomaterials in mortar are discussed.

Deep convolutional neural networks (CNNs) have shown tremendous success in the detection of objects and vehicles in recent years. However, when using CNNs to identify real-time vehicle detection in a moving context remains difficult. Many obscured and truncated cars, as well as huge vehicle scale fluctuations in traffic photos, provide these issues. To improve the performance of detection findings, we used multiscale feature maps from CNN or input pictures with numerous resolutions to adapt the base network to match different scales. This research presents an enhanced framework depending on Faster R-CNN for rapid vehicle recognition which presents better accuracy and fast processing time. Research results on our custom dataset indicate that our recommended methodology performed better in terms of detection efficiency and processing time, especially in comparison to the earlier age of Faster R-CNN models.

The sugar industry produces a huge quantity of sugar cane bagasse ash in India. Dumping massive quantities of waste in a non-eco-friendly manner is a key concern for developing nations. The main focus of this study is the development of a sustainable geomaterial composite with higher strength capabilities (compressive and flexural). To develop this composite, sugarcane bagasse ash (SA), glass fiber (GF), and blast furnace slag (BF) are used. Ash generated from burning sugar cane in the sugar industry is known as sugar cane bagasse. To check the suitability of this secondary waste for use in civil engineering and to minimize risk to the environment in the development of sustainable growth, a sequence of compressive and flexural strength tests was performed on materials prepared using sugar cane bagasse ash (SA) reinforced by glass fiber (GF) in combination with blast furnace slag (BF) and cement (CEM). The effects of the mix ratios of glass fiber to bagasse ash (0.2%–1.2%), blast furnace slag to the weight of bagasse ash (10%), cement binding to bagasse ash (10%–20%), and water to sugar cane bagasse ash (55%) regarding the flexural strength, compressive strength, density, tangent modulus, stress–strain pattern, and load–deflection curve of the prepared materials were studied. According to the findings, compressive strength achieved a maximum strength of 1055.5 kPa and ranged from 120 to 1055.5 kPa, and the flexural strength achieved a maximum strength of 217 kPa and ranged from 80.1 to 217 kPa at different mix ratio percentages. The value of the initial tangent modulus for the cube specimens ranged between 96 and 636 MPa. For compression specimens with 20% cement, the density decreased from 1320.1 to 1265 kg/m³, and the flexural strength decreased from 1318 to 1259.6 kg/m³. With limitation in lower percentages of C/SA, the specimen cannot sustain its shape even after curing period. In comparing the previous research with the present experimental work, it was observed that the material proposed here is lightweight and can be utilised as a filler substance in weak compressible soils to improve their load-bearing capacity.

This paper was accepted for publication in the journal Composite Structures and the definitive published version is available at http://dx.doi.org/10.1016/j.compstruct.2016.11.049.In plated beam, an adhesive is used primarily to adhere the external plate to the concrete beam to achieve a composite action. Even though some work has been found to indicate that the choice of softer adhesive increased the capacity of beam (MacDonald & Calder, 1982), relatively stiffer adhesives have been largely assumed to provide better strengthening. Largely, due to the fact that adhesive has been widely considered as an insignificant structural component towards the capacity of a composite beam; material capabilities (if not structural) of adhesive have also been ignored for further research towards studying its effects on premature failures (particularly debonding). Under mixed-mode loading, the adoption through discretisation of Cohesive Zone Model as a bulk material (indicative of adhesive component) and to simulate interfacial cracks is shown here to achieve the objectives. The outcomes of the research indicate the critical material properties of adhesive in all directions, such as stiffness, strength and crack energy, play crucial role in controlling the behaviour of modes of failure. Further, based on this study, recommendations have been proposed on the choice of adhesive type at different locations of plated beam so as to capture a failure warning and avoid catastrophic failure