Parameter Identification of the RBF-ARX Model Based on the Hybrid Whale Optimization Algorithm

The radial basis function network-based autoregressive with exogenous input (RBF-ARX) model is the nonlinear model based on state dependence with additional input. This brief discusses the parameter estimation of the model and utilizes it to solve the modeling and control problems of piezoelectric ceramics under pressure fluctuation. The system parameters are identified by the hybrid least squares whale optimization algorithm. Compared with the whale optimization algorithm to optimize the parameters of the RBF-ARX model, the proposed algorithm has a faster convergence rate and can avoid falling into the local optimal. Finally, the example is given to illustrate the optimization effect of the proposed algorithm, and the experimental simulation of piezoelectric ceramics under pressure fluctuation is carried out to verify the effectiveness of the proposed algorithm.