An easy way to comply with the conference paper formatting requirements is to use this document as a template and simply type your text into it. The increase in the performance of internal combustion engines for diesel engines has driven to follow alternative ways in order to improve the flow characteristics. This paper presents the computational fluid dynamics (CFD) modeling to study the effect of intake flow condition on the swirl ratio and volumetirc efficiency of a direct injection (DI) diesel engine. A single cylinder direct injection diesel engine with two directed intake ports whose outlet is tangential to the wall of the cylinder has been considered. The numerical results from this geometry are validated with the experimental results and published in the literature. In order to enhance the swirl ratio, intake flow in different components are adjusted instead of modifying the intake manifold shape and profile. The experiments are designed by full factorial approach for 3 variables (three components of intake velocity) to study the turbulent flows in a computational way and accomplished using OpenFOAM software. The induced swirl and tumble at the end of compression stroke are also computed and visualized. Numerous computations have been performed in this work during maximum intake valve lift and closed exhaust valve positions. To estimate the reliable data for predicted results, machine learning techniques such as artificial neural network is employed. Information is gathered for different combinations of intake velocity on swirl ratio and volumetric efficiency. Genetic algorithm is applied to fund the fittest data-set for several generations thereby the best optimal flow components are determined. The results from design of experiments approach and neural network techniques are compared.