Conventional concrete requires improvements in mechanical properties obtained with various mixtures. But making specific sample garments always takes time and money. In this article, we apply a different type of hybrid algorithm to develop a model that uses machine learning, fuzzy, neural network (NN), and Support Vector Machine (SVM). In this paper, the uncertain random excitation or disturbance are employed to input and identify systematic matrix including damping mass, stiffness, and other nonlinear forms. We developed a solid and systematic solution for the control and robustness design in machine learning based grey wolf optimal controller of modified algorithm for reinforced concrete structures unavailable in the existing literature. The goals of this paper are towards access to adequate, safe and affordable housing and basic services, promotion of inclusive and sustainable urbanization and participation, implementation of sustainable and disaster-resilient buildings, sustainable human settlement planning and manage. Simulation results of linear and nonlinear structures show that the proposed method is able to identify structural parameters and their changes due to damage and unknown excitations. Therefore, the goal is believed to achieved in the near future by the ongoing development of AI and control theory.

In the recent years, modeling of concrete properties based on optimization and prioritization methods has been performed using machine learning techniques including genetic programming, artificial neural networks (ANN), an adaptive neuro-fuzzy inference system, and support vector machines. However, the application of ANN to the task of optimizing the design of reinforced concrete (RC) corbels has been limited in previous studies. In this endeavor, two empirical mathematical models of ANN are developed to calculate the optimal reinforcement ratio and effective depth of RC corbel. More than 1,500 corbel data have been processed utilizing pattern search optimization and used in this computational artificial neural solution. Five model parameters were adopted to formulate simple ANN mathematical models. Parametric analysis was performed to justify the independent parameters of ANN models. This procedure showed the accuracy of ANN models, despite changes in independent parameters. Thus, these variables are successfully integrated into the neural models. The stability and simplicity of the proposed mathematical models of ANN make them suitable for optimizing the design of RC corbels, as these formulas are applicable to predict the optimal reinforcement ratio and edge impact depth, considering the cost factor.

The behavior of the brittle punching shear failure in two-way flat slabs was investigated in this study using experimental and nonlinear finite element analysis approaches. The reinforced concrete slabs were tested under the effect of strengthening carbon fiber reinforced polymer sheets (strengthened and un-strengthened), temperature value (23, 200, 400, and 600 ℃), and the behavior was captured at the material and system levels. Generally, the punching shear performance was significantly worsened upon exposure to the heat-damage effect, where increasing the temperature value increases the resulting cracking intensity. In addition, strengthening the flat slabs improves the overall structural behavior where the ultimate load-carrying capacities, cracking loads, and toughness values are increased. The detailed structural behavior, including the cracking propagation, failure modes, strain values, and displacement profiles at various high temperatures, were captured using the nonlinear finite element analysis. Generally, the resulting improvement is higher for specimens damaged at higher temperatures, with the load-deflection behavior flattening with increased deflection values. Moreover, toughness was improved significantly by strengthening with reduced failure brittleness. Finally, the stiffness-deflection curves at 400 ℃ and 600 ℃ specimens start with a flattened shape but experience a sudden drop in the strengthened ones, revealing that failure occurs compared to specimens at lower temperatures.

This research sought to determine the practically-viable values of strength and thickness for an overlay, along with the big bond's strength and toughness. By achieving this aim, it is ensured that the overlaying system has adequate ductility and, thus, a high resistance to the emergence and propagation of cracking. The paper has also examined the behavior of NLFEA-modeled bridge deck panels made of pre-casted concrete with a complete depth and how the overlay's strength and thickness influenced such a system. The NLFEA-devised deck panel model was put to validation against the experimentally achieved outcomes of credible published research. Twenty models of precast concrete bridge deck panels were devised. The study parameters were the overlay's ratio of overlay thickness-to-thickness of bridge deck slab (t_overlay/t_slab); and the overlay's relative ratio of the strength of overlay-to-strength of deck slab (E_overlay/E_slab). For experimentation purposes, the former ratio was set at the values of 0.00 (no thickness), 0.05, 0.10, 0.15, 0.20, 0.25, 0.30, 0.35, 0.40, 0.45, and 0.50, while the latter ratio was set at 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, and 1.0. The outcomes of this research paper greatly assisted in recommending a set of somewhat useful guidelines to help determine the best overlay's strength and strength suitable to eliminate potential delaminating of the deck's overlay exposed to service load and overload due to AASHTO HS-20 truck and impact loading.

Slab bridge is a structural type with costs similar to those of precast girder bridges. The optimization of their design variables can be a competitive aspect when opting for this type of construction. In this paper, the optimization of the economic cost of the concrete slab deck is considered, where the many functions involved in the design of the structure are taken here as constraints of the optimization problem. On the other hand, the price of the deck can be approached as a linear combination of the quantity of the different materials that are part of it, being the coefficients of that combination the unit prices of each material. In order to find an optimal combination of the design parameters to minimize the deck price, avoiding approximate or manual calculation methods, the use of single-objective optimization metaheuristics is proposed. Four representative algorithms were applied: genetic algorithm, pattern search, variable neighbourhood search, and vapour-liquid equilibrium. The optimization problem was approached as a black box containing all the formulations, relationships, and constraints involved in calculating the cost of the deck. After extensive calculations and comparisons, it is concluded that variable neighbourhood search provide better mean results with minimal data dispersion than the other metaheuristics, and a more stable behavior in the search for an optimal solution, avoiding falling into local solutions.

In this paper, a new simple and effective numerical method is proposed for the nonlinear inelastic time-history analysis of rectangular concrete-filled steel tubular (CFST) frames under dynamic loadings. For this proposed method, a fiber beam-column element is formulated by considering both geometric and material nonlinearities. The geometric nonlinearities are specifically taken into account utilizing the geometric stiffness matrix and stability functions. The element stiffness matrix is assessed based on uniaxial nonlinear hysteretic material models for the steel and concrete fibers on monitored cross-sections along the element length. Furthermore, the residual stress is considered as the initial stress in the steel fibers as well. To solve the differential equation of motion of the structural system subjected to the earthquake loadings, the Newmark's average acceleration method is incorporated with the Newton-Raphson iterative scheme. Five numerical examples of the rectangular CFST column and frames with gradual increasing complexity subjected to four different earthquake loadings are analyzed and compared with results obtained from ABAQUS. The outstanding advantages of the proposed method over ABAQUS in modeling and analyzing are obtained with the highly accurate predicting the dynamic behavior of the rectangular CFST structures and the computational efficiency by using only one element per member.

Recycled powder (RP) has emerged as a promising and viable alternative to traditional cementitious materials for use in concrete. The compressive strength (f_C) of RP mortar has a considerable impact on the mechanical properties of RP concrete. Utilizing machine learning approaches to engineering problems, particularly when estimating the mechanical properties of construction materials, results in outstanding accuracy in forecasting and minimal experimental costs. This study aimed to provide some integrated machine-learning techniques for estimating the f_C of recycled powder mortar (RPM). Initially, relevant literature is consulted to acquire data on the f_C test results of 204 groups of mortars. Subsequently, the Extreme Gradient Boosting (XGB), Random Forest (RF), and Support Vector Regression (SVR) methodologies are used, followed by the optimization of their respective hyperparameters using the Chimp optimization algorithm (ChOA), in order to construct powerful forecasting approaches (XGB^ChOA, RF^ChOA and SVR^ChOA). According to the results, all three models exhibit excellent results in correctly anticipating the f_C. By leveraging these advanced machines learning techniques and optimizing them with ChOA, the authors intended to achieve high accuracy in their predictions, thereby reducing the need for extensive experimental testing and minimizing costs associated with traditional methods of estimating the mechanical properties of construction materials. By accurately predicting the f_C of RPM, these models can significantly reduce the need for extensive physical testing, leading to cost savings in material research and development. While the study mentions the generalization ability of the models, it would be beneficial to assess their performance on independent datasets or in real-world applications to confirm their practical utility. Including external factors or environmental conditions factors in the analysis could enhance the model's accuracy and robustness. The SI results of the models are roughly identical, with a small superiority of XGB^ChOA (SI_Train=0.0334 and SI_Test=0.0567) compared to RF^ChOA, but remarkably better than SVR^ChOA. As it was clear from OBJ that the lowest value of OBJ belonged to XGB^ChOA at 1.2597, followed by RF^ChOA by 1.6792, and then SVR^ChOA equals to 1.3769.

This paper performs a materially nonlinear finite element analysis (FEA) of reinforced concrete (RC) beams with the adoption of a machine learning (ML) based material model. Among the ML-based material models that can compensate for the coarseness in the conventional constitutive material models induced by the limited amount of experimental data and have the flexibility for the supplementation of additional experimental data, the Gaussian process approach is considered to construct the material models of concrete and steel. Despite many benefits including accuracy and reliability, however, the ML-based material model requires a drastic increase in the computational cost and memory consumption. In addition, it is difficult to use in the nonlinear analysis of large complex RC structures composed of numerous members. To address this limitation, optimization, and computing strategies with ML-integrated FEA is designed in this paper. The hardware acceleration is based upon the constitution of a parallelized computing structure, and Python-based FEA process is developed to trace the nonlinear behavior of RC beams. Comparison with experimental data for two representative RC beams is performed to verify the efficiency and reliability of the introduced solution procedures. The obtained results from the developed program show that the introduced solution procedure adopting the hardware acceleration process with the use of the ML-based material models can be used in the nonlinear analysis of large structures composed of numerous RC members.