Parameter Identification of Lorenz System Using RBF Neural Networks with Time-Varying Learning Algorithm

A hybrid evolutionary algorithm is proposed to identify parameters for Lorenz chaotic system. In the proposed algorithm, time-varying learning algorithm based on annealing robust concept (ARTVLA) is adopted to optimize a radial basis function neural network (RBFNN) for parameter identification of Lorenz system. In the ARTVLA, the determination of the learning rate would be an important work for the trade-off between stability and speed of convergence. A computationally efficient optimization method, particle swami optimization (PSO) method, is adopted to simultaneously find a set of promising learning rates and optimal parameters of RBFNNs. The proposed RBFNN (ARTVLA-RBFNN) has good performance for identifying parameters of Lorenz system. Simulation results are illustrated the effectiveness and feasibility of the proposed ARTVLA-RBFNN.