A hierarchical genetic algorithm based RBF neural network approach for modelling of electrohydraulic system

The paper presents an approach to model the electrohydraulic system of a certain mine-sweeping weapon using the radial basis function (RBF) neural networks. In order to obtain accurate and simple RBF neural networks efficiently, a hierarchical genetic algorithm (HGA) is used to train the neural networks, in which the number of hidden units and the parameters of centers are optimized by the HGA simultaneously. The spread factors and the weights of the neural networks are calculated by the linear algebra methods for relieving computational burden. The proposed algorithm is applied to the modelling of the electrohydraulic system, and the results clearly indicate that the obtained RBF neural network can model the hydraulic system satisfactorily. The comparison results also show that the proposed algorithm performs better than the traditional methods.