Optimization of a Locomotive Fuel Tank

Abstract

The interaction between fluid and structure in storage tanks filled with fluids has been the interest of many researchers. This interaction which causes the sloshing can be a severe problem in vehicle stability and control. In this paper, fuel tank of the locomotive ER 24 is analyzed and its mass and manufacturing cost are minimized. The fuel tank was assumed to be fully filled with fuel therefore, the greatest forces will be generated. Firstly, the behaviour of fuel and air during braking time is investigated by using a two-phase model. Then, the distribution of pressure on the surface of baffles caused by sloshing is extracted. The fuel tank is modelled and analyzed using finite element method (FEM) considering loading conditions suggested by DIN EN 12663 standard and real boundary conditions.

A multi-objective optimization problem is solved by employing Non-dominated Sorting Genetic Algorithm (NSGA-II) and artificial neural networks. Two multi-layer perceptron networks are used to approximate mass and maximum Von-Mises equivalent stress that later are used in the optimization process. It is shown that compare to the primary design, the optimized fuel tank reduces the mass and manufacturing cost by %39 and %73, respectively, while still provides the safety conditions.