论文信息 - Study on RBF NN based on improved differential evolution

Study on RBF NN based on improved differential evolution

A novel method of nonlinear system modeling using radial basis function neural network based on improved differential evolution algorithm is proposed. Differential evolution algorithm is presented to in order to improve modeling capability. Local operator and optimization selection strategy is presented to improve the searching speed and the local searching capability of genetic algorithm. According to the characteristics of radial basis function neural network and differential evolution algorithm, radial basis function neural network and differential evolution algorithm are associated to improve modeling precision. The simulation results show the effectiveness of this method.

Wang Fuli | Jia Mingxing | He Dakuo

[1] Yonghong Tan,et al. Nonlinear one-step-ahead control using neural networks: Control strategy and stability design , 1996, Autom..

[2] Joos Vandewalle,et al. Efficient identification of RBF neural net models for nonlinear discrete-time multivariable dynamical systems , 1995, Neurocomputing.

[3] Richard D. Braatz,et al. On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[4] Jooyoung Park,et al. Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[5] Haralambos Sarimveis,et al. A new algorithm for developing dynamic radial basis function neural network models based on genetic algorithms , 2002, Comput. Chem. Eng..

[6] Michael A. Henson,et al. Nonlinear model predictive control: current status and future directions , 1998 .

[7] Rainer Storn,et al. Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[8] Mao Zongyuan,et al. The Neura Network Predictive Control of Time-Delay Systems , 2001 .

[9] Kumpati S. Narendra,et al. Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.