![]() To evaluate its effectiveness, a case study was developed where it was concluded that the designs produced by the application are more efficient than those obtained by commercial tools, thus reducing the computational expense and time used by designers in iterative processes that are carried out in the initial phases project.Įlectronic oscillators are used for the generation of both continuous and discrete signals, playing a fundamental role in today's electronics. The optimization model implemented in OPS Design v2.0 seeks to minimize the number of different profiles and the structure's own weight in order to reduce the construction complexity and the weight per linear meter (costs in quantities of material). This article presents OPS Design v2.0, a computer tool that allows obtaining a preliminary optimal distribution of metallic structural profiles in a Non-Braced Frame System (OMF: Ordinary Moment Frame). The use and development of these techniques has been closely linked to technological advance since, through the use of computer equipment, complex mathematical models can be solved with low cost and time. The optimization of civil structures is a technique whose purpose is to efficiently use the materials that make up the structural systems based on previously established restrictions and objectives. This value indicates that ANN can estimate well. The results showed that the dimensional regression values and the reinforcement ratio were 98.53% and 96.06% respectively. There are 16 empirical formulas for estimating the optimum dimensions and the reinforcement ratios of beam and column. Eight parameters used which consist of earthquake accelarations, soil sites class, joint types, beam spans, number of storey, high of storey, concrete strengths and diameters of the reinforcement. A total of 36 building variations modelling were prepared as the training data for the set up ANN model. This study aims to help engineers shorten the time for trial at the conceptual design stage. ANN is a network based method that allows to get an accurate approach even with the limited information provided. Therefore, an estimation of the optimum dimensions and the reinforcement ratios of beam and column was carried out at the conceptual design stage using the artificial neural network (ANN). On the other hand, to maximize the performance of the building, there are many things that need to be considered. The conceptual design stage is necessary because it is considered as a fundamental input in decision making for maximizing the performance of a building. In addition, their use could be applied both in precast or cast in situ concrete connection design. The main advantage of the proposed ANNs is that they can be easily and effectively adapted to different connection parameters. Those results validate their use as an efficient structural design tool. Comparing the obtained predicted stresses to those of the FEM analyses, the difference is less than 9.16%. A multilayer perceptron combined with a backpropagation algorithm is used in the ANN architecture, and a hyperbolic tangent function is applied as an activation function. The ANN input data are the parameters and nodal stresses obtained from the FEM models. The parameters are: strength of concrete and screws, diameter of screws, plate thickness, and the posttensioning load. The proposed networks are applied to a dry precast concrete connection, which has been modelled by means of the Finite Element Method (FEM). ![]() ![]() In this research, ANNs are used in order to foster the implementation of efficient tools to be used during the early stages of structural design. ![]() Nowadays, Artificial Neural Networks (ANNs) are showing their potential as design tools. A rational and sensible design of both materials and elements results not only in economic benefits and computing time reduction, but also in minimizing the environmental impact. In the built environment, one of the main concerns during the design stage is the selection of adequate structural materials and elements. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |