Utilization of neural networks for simulation of vehicle induced flow in tunnel systems

---

Tezin Türü: Doktora

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Makina Mühendisliği Bölümü, Türkiye

Tezin Onay Tarihi: 2012

Öğrenci: GENCER KOÇ

Danışman: CÜNEYT SERT

Özet:

Air velocities induced by underground vehicles in complex metro systems are obtained using artificial neural networks. Complex tunnel shaft-systems with any number of tunnels and shafts and with most of the practically possible geometries encountered in underground structures can be simulated with the proposed method. A single neural network, of type feed-forward back propagation, with a single hidden layer is trained for modelling a single tunnel segment. Train and tunnel parameters that have influence on the vehicle induced flow characteristics are used together to obtain non-dimensional input and target parameters. First input parameter is the major head loss coefficient of tunnel, (L/D)_Tunnel. Blockage ratio A_Train/A_Tunnel and train aspect ratio (D/L)_Train are selected to be non-dimensional input parameters to represent the system geometry. As the final input parameter, skin friction coefficient of the train, f_Train drag coefficient of the train, C_D; frontal area of the train, A_Train and lateral area of the train, A_Lateral are combined into a single overall drag coefficient based on the train frontal area. Non-dimensional V_Air/V_Train speed ratio is selected to be the target parameter. Using maximum air velocity predicted by the trained neural network together with non dimensional system parameters and time, an additional neural network is trained for predicting the deceleration of air in case of train stoppage within the tunnel system and departure of the train from the system. A simulation tool for predicting time dependent velocity profile of air in metro systems is developed with the trained neural networks.