Abstract: To improve the dynamics response of the vehicle
passive suspension, a two-terminal mass is suggested to connect in
parallel with the suspension strut. Three performance criteria, tire grip,
ride comfort and suspension deflection, are taken into consideration to
optimize the suspension parameters. However, the three criteria are
conflicting and non-commensurable. For this reason, the Chebyshev
goal programming method is applied to find the best tradeoff among
the three objectives. A simulation case is presented to describe the
multi-objective optimization procedure. For comparison, the
Chebyshev method is also employed to optimize the design of a
conventional passive suspension. The effectiveness of the proposed
design method has been clearly demonstrated by the result. It is also
shown that the suspension with a two-terminal mass in parallel has
better performance in terms of the three objectives.
Abstract: In this paper, Differential Evolution (DE) algorithm, a new promising evolutionary algorithm, is proposed to train Radial Basis Function (RBF) network related to automatic configuration of network architecture. Classification tasks on data sets: Iris, Wine, New-thyroid, and Glass are conducted to measure the performance of neural networks. Compared with a standard RBF training algorithm in Matlab neural network toolbox, DE achieves more rational architecture for RBF networks. The resulting networks hence obtain strong generalization abilities.