Abstract: In this study, a semi-cylinder obstacle placed in a
channel is handled to determine the effect of flow and heat transfer
around the obstacle. Both faces of the semi-cylinder are used in the
numerical analysis. First, the front face of the semi-cylinder is stated
perpendicular to flow, than the rear face is placed. The study is
carried out numerically, by using commercial software ANSYS 11.0.
The well-known κ-ε model is applied as the turbulence model.
Reynolds number is in the range of 104 to 105 and air is assumed as
the flowing fluid. The results showed that, heat transfer increased
approximately 15 % in the front faze case, while it enhanced up to 28
% in the rear face case.
Abstract: The purpose of this study is mainly to predict collision
frequency on the horizontal tangents combined with vertical curves
using artificial neural network methods. The proposed ANN models
are compared with existing regression models. First, the variables
that affect collision frequency were investigated. It was found that
only the annual average daily traffic, section length, access density,
the rate of vertical curvature, smaller curve radius before and after
the tangent were statistically significant according to related
combinations. Second, three statistical models (negative binomial,
zero inflated Poisson and zero inflated negative binomial) were
developed using the significant variables for three alignment
combinations. Third, ANN models are developed by applying the
same variables for each combination. The results clearly show that
the ANN models have the lowest mean square error value than those
of the statistical models. Similarly, the AIC values of the ANN
models are smaller to those of the regression models for all the
combinations. Consequently, the ANN models have better statistical
performances than statistical models for estimating collision
frequency. The ANN models presented in this paper are
recommended for evaluating the safety impacts 3D alignment
elements on horizontal tangents.