Naci Caglar

Development of artificial neural network for prediction of salt recovery by nanofiltration from textile industry wastewaters

This paper presents the use of artificial neural network (ANN) to develop a model for predicting rejection rate (R o) of single salt (NaCl) by nanofiltration based on experimental data-sets. The re...

A simple formulation for effective flexural stiffness of circular reinforced concrete columns

Abstract Concrete cracking reduces flexural and shear stiffness of reinforced concrete (RC) members. Therefore analyzing RC structures without considering the cracking effect may not represent actual behavior. Effective flexural stiffness resulting from concrete cracking depends on some important parameters such as confinement, axial load level, section dimensions and material properties of concrete and reinforcing steel. In this study, a simple formula as a securer, quicker and more robust is proposed to determine the effective flexural stiffness of cracked sections of circular RC columns. This formula is generated by genetic programming (GP). The generalization capabilities of the explicit formulations are compared by cross sectional analysis results and confirmed on a 3-D building model. Moreover the results from GP based formulation are compared with EC-8 and TEC-2007. It is demonstrated that the GP based model is highly successful to determine the effective flexural stiffness of circular RC columns.

Design of a Short Tensile Coupon for Fiber Reinforced Plastic Using Artificial Neural Networks

The measurement of the mechanical properties of Fibre Reinforced Plastic (FRP) material is necessary for numerical structural analysis and design. The mechanical properties of the FRP materials may be determined by specific coupon test methods or by analytical calculation. However, pultruded or moulded FRP components may not possess the dimensions to permit the extraction of standard length coupons. The shape of the short tensile coupon has been established to circumvent this limitation using a Finite Element (FE) representation and Artificial Neural Network (ANN) including the effect of gripping length, coupon shape, width, length and thickness. The FE results have been used for the learning and testing sets of the ANN. The Multi-Layer Perceptron (MLP) has been employed in the modelling of the ANN. The MLP model has been trained using the Scaled Conjugate Gradient Algorithm (SCGA) and tested. The ANN results show that the correlation between targets and outputs are consistent. K e y w o r d s : Fibre reinforced plastic, mechanical properties, numerical analysis, tensile coupon, artificial neural network, scaled conjugate gradient algorithm.