جستجوی مقالات مرتبط با کلیدواژه "سیستم استنتاج فازی" در نشریات گروه "مکانیک"

Pressing molds are widely used in the industry due to the high speed of parts production. Due to the very low clearance between the mandrel and the matrix and having complex shapes, the production of these molds is very expensive and costly.  The hardness of the mold and subsequently their fatigue life should be high. One of the processes that has the ability to create surfaces with high dimensional accuracy and complex shapes is the wirecut process. In this research, in order to improve the performance and increase the life of cutting dies, the hardness of Mo40 steel is optimized. For this purpose, based on the method of the response procedure, the design of the experiment has been designed for the three parameters of wire feed speed, wire tension and generator power. Next, the obtained data are clustered and then fuzzy rules with three inputs (wire speed, tension and power) and output (hardness) are extracted. The obtained rules were entered in the toolbox of fuzzy inference systems of MATLAB software. Based on the defined fuzzy inference system, it is possible to predict the hardness based on the parameters of wire speed, wire tension and generator power. In the next phase, based on this system and within the range of available variables, the optimal value of hardness and corresponding variables were extracted. In the final phase, these values ​​were experimentally tested and their agreement with the obtained value was observed.

The aerodynamic coefficients of airfoils are usually calculated through numerical and experimental methods causing time and cost consuming as well as depending on the airfoil surface cover. The estimation of aerodynamic coefficients of fabric covered airfoil through fuzzy logic, neural network and fuzzy-neural methods is the innovation of this research in order to determine a low-cost and fast method for optimal design as well as determining the aerodynamic coefficients of airfoils of vehicles having membrane wings. In the models, subsonic velocity was considered. Reynolds number and angle of attack were assumed as input and the values of lift and drag coefficients were assumed as output. Estimations were made on NACA2418 airfoil data, after which the final error of each method was compared. The mean squared error of lift and drag coefficients were 0.8023 and 4.3451e-04 for fuzzy model 0.0012 and 7.5767e-6 for neural network and 0.0697 and 0.0076 for network-fuzzy inference model respectively. The obtained results indicated good fitting of three studied models and best fitting for neural network model, which confirmed by the lift coefficients obtained from experimental tests done for validation.

In this study, a fuzzy inference system based on look up table was used for modeling and predicting the diffusion coefficient of benzoic acid in the water based γ-Alumina and Silica nanofluids. Due to evaluate the designed fuzzy system, Nanofluids Diffusion coefficients of benzoic acid at constant temperature of 20 ◦C were measured with using a simple and inexpensive technique. The results revealed that the designed fuzzy system could accurately mimic the diffusional mass transfer in nanofluids. The deviation between fuzzy model and experiments for γ-Alumina and Silica nanofluids were about 0.939 and 0.997, respectively. The measurements showed that nanoparticles at low concentration did not have a significant effect on benzoic acid diffusion in nanofluids relative to that in pure water. But diffusion in silica nanofluids strongly reduced at high concentration of nanoparticles, as in volume fraction of 0.8% diffusion coefficient decreased up to 35% relative to that in base fluid. Such factors as the type of tests to determine the diffusion coefficient in nanofluids, nanoparticles concentration and type, could strongly influence of diffusional mass transfer in nanofluids.

The purpose of this research is to perform experimental study and modeling of the plastic deformation of rectangular plates under the low rate impact loading by drop hammer system. In experimental section, some experiments were conducted on rectangular plates with different levels of energy in order to survey the mechanical behavior of steel and aluminum plates according to applied load. The modeling section consists of presenting an explicit function for experimental data by singular value decomposition (SVD) based on non-dimensional parameters and also multi-objective modeling and design of adaptive neuro-fuzzy inference system (ANFIS) by genetic algorithm. Generally, the aim of modeling is a reliable and satisfactory prediction of deflection – thickness ratio of plates under impact loads. A comparison between modeling results and experimental data is done in order to validate the results. The investigation of training and prediction data errors which has been based on root-mean-square error (RMSE) and coefficient of determination (R2) shows that the obtained results of the optimal design of ANFIS is closer to experimental results than mathematical modeling by SVD, with the exception that a mathematical function based on experimental data is presented by SVD method. Therefore, using these presented models for deflection-thickness ratio of plate under impact loading is desirable.