P. Bashi Shahabi, H. Niazmand, M.r Modarres Razavi,
Volume 1, Issue 1 (1-2011)
Abstract
Increase of environmental pollution and restricted emission legislations have forced companies to produce automobiles with lower air pollutants. In this respect, discharge of blowby gases into the environment has been prohibited and their recirculation into the combustion chamber is proposed as an alternative solution. In addition, using EGR technique to control and reduce nitrogen oxides in internal combustion engines has been quite effective. An important common feature of these two methods is the fact that improper EGR/blowby distribution leads to the increase in other pollutants and the significant engine power reduction. Therefore, the study of important factors in maldistribution of the injected gases is of great practical importance. Besides the injection position that has significant role on distribution of injected gases, it seems that other parameters such as engine speed, injection velocity and angle may affect the distribution of injected gases. In this numerical study, a new technique is used to determine the effect of these parameters on distribution of injected EGR or blowby gases into the EF7 intake manifold. Numerical calculations are performed for three injection velocities, five injection angles and three different engine speeds. It was found that recirculated gases distribution is slightly influenced by the injection angle and injection velocity, while the engine speed is the most influential factor.
A. Fotouhi, M. Montazeri, M. Jannatipour,
Volume 1, Issue 1 (1-2011)
Abstract
This paper presents the prediction of vehicle's velocity time series using neural networks. For this purpose, driving data is firstly collected in real world traffic conditions in the city of Tehran using advance vehicle location devices installed on private cars. A multi-layer perceptron network is then designed for driving time series forecasting. In addition, the results of this study are compared with the auto regressive (AR) method. The least root mean square error (RMSE) and median absolute percentage error (MDAPE) are utilized as two criteria for evaluation of predictions accuracy. The results demonstrate the effectiveness of the proposed approach for prediction of driving data time series.
