1. Aerodynamic Drag Force Estimation of a Truck Trailer Model Using Artificial Neural Network
- Author
-
Mehmet Seyhan, Yahya Erkan Akansu, and Mustafa Sarioglu
- Subjects
Drag coefficient ,Engineering ,Offset (computer science) ,Drag force,Artificial neural network,Wind tunnel ,business.industry ,Trailer ,Reynolds number ,Structural engineering ,symbols.namesake ,Drag ,symbols ,Aerodynamic drag ,Zero-lift drag coefficient ,business ,Simulation ,Wind tunnel - Abstract
Prediction of the drag forces acting on truck trailer with/without spoiler is carried out by using artificial neural network (ANN). ANN model data set include the experiments of spoiler positions which have zero level to trailer front corner, -2 mm, -4.5 mm, -9 mm, +4.5 mm and +9 mm offset and truck trailer without spoiler. The experiments were carried out in the wind tunnel for number of ten free stream velocities of 4.6, 6.2, 7.8, 9.4, 11.0, 12.6, 14.2, 15.8, 17.45 and 19.3 m/s which are corresponds to Reynolds numbers range between 1.0x105 and 5.0x105. Mean absolute percentage error (MAPE) is obtained as 2.24% for training, 3.75% for validation and 7.58% for testing in the prediction of the drag forces. Prediction performance of the developed ANN model has very good accuracy. According to drag coefficients results, Reynolds independent for truck trailer model is obtained at Reynolds number between 1.97x105 and 4.89x105. For spoiler position cases, while minimum drag coefficient acting truck trailer with spoiler is seen at – 2mm offset, maximum drag coefficient is seen at -9 mm offset. The maximum drag reduction is 22.6 % at the position of -2 mm spoiler offset in Re = 3.2x105.
- Published
- 2016