Using waste tire rubber as a aggregate replacement in the production of concrete can be considered as an effective way for environment and economies. This study presents an approach based on a prediction model using Artificial Neural Networks (ANN) to predict compressive strength of eco-friendly concrete containing waste tire rubber (RC). A data set with nine influencing features including water, cement, supplementary cementitious materials, coarse aggregate, coarse rubber aggregate, fine aggregate, fine rubber aggregate, superplasticizer, age using for training and validating models have been collected from the literature. The output was compressive strength of RC. The combination of root mean square propagation and stochastic gradient descent with momentum method is employed to train the ANN. Using various validation criteria such as coefficient of determination (R2), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), the ANN model was validated and compared with two machine learning (ML) techniques Random Forest (RF) and Multilayer Perceptron (MLP). A Sensitivity analysis also was carried out to validate the robustness and stability of these models. The experimental results showed that the ANN model outperformed in comparing with other models and therefore it can be used as a suitable approach to predict compressive strength of eco-friendly rubber concrete.
Abstract. This article reviews publications investigating accidents at buildings and civil engineering structures. According to the conducted analysis, such publications commonly describe the circum-stances of specific accidents, rather than identify their causes. Classifications of accident causes are often published without disclosing the information sources. No publications have been found on as-sessing the impact of the human factor, including design errors, rolled metal defects, poor-quality manufacturing or installation, as well as violations of the operational rules. In the majority of publica-tions, outdated methods are used for analysing and processing data on accidents. In order to improve the current situation, organizational and methodological measures are proposed. The importance of using the methods of systems analysis and content analysis for searching and processing information is substantiated. It is shown that the main conditions for accident prevention involve strict compliance with reliability requirements at the design, constructional, and operational stages, organization of the maintenance service of structures, their timely inspection, as well as preventive and overhaul repairs. In this regard, the accumulation of statistical data on damages and accidents, grouped according to a unified scientifically-based methodology, appears to be of great importance. It is proposed to create a unified form for data representation on accidents that should be placed on web portals in open access for the purpose of its continuous replenishment.
The behavior of the steel I-beam with plate corrugated webs in conditions of restrained torsion is considered. The problem is solved numerically in the «ANSYS 14.5» software package based on spatial model where finite elements of shell type are used. Results obtained allowed us to calculate geometric characteristics of web beams associated with torsional deformation in order to continue to perform the calculation of these beams on the rod model. Analysis was made using two models of corrugated web I-beams with different corrugation configurations with geometric parameters and giving similar values of metal. A comparative analysis of the stress-strain state of corrugated beams and I-beams with flat web at torsion with bend.
An example of the optimal design of a steel truss with the use of modified Lagrange functions is considered. To solve the problem, it is necessary to select the cross-sectional areas of the truss at a given interval by minimizing its volume, provided that the regulatory requirements for strength and rigidity are met. The external diameters of the sections of the truss elements vary. A detailed algorithm for solving the problem is presented. The algorithm is implemented in the mathematical package MathCAD, which allows you to visually trace the sequence of commands, as well as receive graphs reflecting the state of the problem at each iteration.
The analysis of the current state of issues related to the construction of design models of building structures based on wood. The main software systems are presented, in which the calculation of wooden structures is realized. The need to develop software for timber frame buildings was identified, which would allow an engineer to select sections, check structural units of spatial models of various geometric configurations and take into account the joint work of supporting structures and cladding.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.