جستجو در تالارهای گفتگو

PREDICTING THE BUCKLING CAPACITY OF STEEL CYLINDRICAL SHELLS WITH RECTANGULAR STRINGERS UNDER AXIAL LOADING BY USING ARTIFICIAL NEURAL NETWORKS Z. Kalantari and M. S. Razzaghi Abstract A parametric study was carried out in order to investigate the buckling capacity of the vertically stiffened cylindrical shells. To this end ANSYS software was used. Cylindrical steel shells with different yield stresses, diameter-to-thickness ratios (D/t) and number of stiffeners were modeled and their buckling capacities were calculated by displacement control nonlinear static analysis. Radial basis function (RBF) neural networks were used to predict the buckling capacity of shells. Herein 70 percent of the results of numerical analyses were used to train the neural network and the remainders were used to test and validate the results of neural networks. Results of this study showed that RBF neural networks are useful tools to predict the buckling capacity of vertically stiffened cylindrical shells. It was also shown that buckling capacities of stiffened shells exponentially vary by distance of adjacent stiffeners (unstiffened length). Keywords Buckling, cylindrical shells, stiffener, Artificial Neural Networks چکیده به منظور بررسی ظرفیت کمانش پوسته های مطالعات پارامتریک پوسته های استوانه ای با سخت کننده های قائم، مطالعات پارامتریک به انجام رسید. برای این منظور از نرم افزار ANSYS استفاده شد. پوسته ای استوانه ای فولادی با تنش جاری شدن، نسبت ارتفاع به قطر و تعداد سخت کننده های گوناگون مدلسازی شدند و ظرفیت کمانش آنها با استفاده از تحلیل استاتیکی غیر ارتجاعی با کنترل تغییر مکان محاسبه شد. به منظور پیش بینی ظرفیت محوری کمانش از شبکه عصبی RBF استفاده شد. برای این منظور هفتاد درصد از نتایج خروجی تحلیل های عددی برای آموزش شبکه استفاده شدند و مابقی برای تست و صحت سنجی نتایج کنار گذاشته شدند. نتایج این پژوهش نشان می دهد، شبکه های عصبی RBF ابزاری مناسب برای پیش بینی ظرفیت کمانش پوسته های استوانه ای با سخت کننده قائم هستند. علاوه بر این نشان داده شد که تغییرات ظرفیت کمانش پوسته ها با فاصله سخت کننده های مجاور (طول مهار نشده) به صورت نمایی تغییر می کند. منبع دانلود 28-8-7.pdf

Comparison Study on Neural Networks in Damage Detection of Steel Truss Bridge Hassan Aghabarati 1 ; Mohsen Tabrizizadeh2 This paper presents the application of three main Artificial Neural Networks (ANNs) in damage detection of steel bridges. This method has the ability to indicate damage in structural elements due to a localized change of stiffness called damage zone. The changes in structural response is used to identify the states of structural damage. To circumvent the difficulty arising from the non-linear nature of the inverse problem, three neural networks, Multi-Layer Perceptron Neural Network (MLPNN), Radial Basis Function Neural Network (RBFNN) and General Regression Neural Network (GRNN) are employed to simulate damage states of steel bridges. It was observed that the performance of all three networks is well and they have good agreement with actual results performed with Finite Element analysis. The efficiency of GRNN in structural identification is so good, although RBFNN has results close to GRNN and MLPNN results are satisfactory. All networks have good results while there is a little damage in structural members. Generally, results would have more error when damages in structural members extend. The engineering importance of the whole exercise can be appreciated once we realize that the measured input at only a few locations in the structure is needed in the identification process using neural networks. منبع دانلود JSEG61313868600.pdf

Artificial Neural Network Modeling of Total Dissolved Solid in the Simineh River, Iran Original Article, D2 NematiS, Naghipour L and Fazeli Fard MH. Journal. Civil Eng. Urban. 4(1): 08-13. 2014 ABSTRACT:This research aims to model Total Dissolved Solid (TDS) values at the Simineh River in northwest Iran by application of Artificial Neural Networks (ANNs) to evaluate existing water quality conditions and also to predict future conditions in this river. The input parameters of the ANNs model are Calcium (Ca), Chloride (Cl), Magnesium (Mg), Sodium (Na), Bicarbonate (HCO3), Sulfate (SO4), and water discharge (Q) from 1993 to 2011. The performance of the ANNs model was assessed in accordance with Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2) between the measured and predicted values. The study also includes an estimation of the relative importance of these variables to determine appropriate input combinations. A method is used in this paper to calculate the relative importance of each input parameters, showing that magnesium and calcium concentrations are the most and least influential parameters, with approximate values of 18 and 12 %, respectively. The ANNs with different numbers of neurons in the hidden layer were constructed, and the model with 14 hidden neurons was selected as the best. Comparisons between the measured and predicted values show that the ANNs model could be successfully applied and provide high accuracy and reliability for water quality parameters forecasting. Keywords:Artificial Neural Networks, Total Dissolved Solid, Simineh River, Relative Importance, Water Quality منبع: [Hidden Content] دانلود: [Hidden Content].,14-02-08-13.pdf J. Civil Eng. Urban.,14-02-08-13.pdf