標題: Runge-Kutta neural network for identification of dynamical systems in high accuracy
作者: Wang, YJ
Lin, CT
電控工程研究所
Institute of Electrical and Control Engineering
關鍵字: contraction mapping;gradient descent;nonlinear recursive least square;radial-basis function;Runge-Kutta method;Vander Pol's equation
公開日期: 1-三月-1998
摘要: This paper proposes the Runge-Kutta neural networks (RKNN's) for identification of unknown dynamical systems described by ordinary differential equations (i.e., ordinary differential equation or ODE systems) in high accuracy. These networks are constructed according to the Runge-Kutta approximation method. The main attraction of the RKNN's is that they precisely estimate the changing rates of system states (i.e., the right-hand side of the ODE (x) over dot = f(x)) directly in their subnetworks based on the space-domain interpolation within one sampling interval such that they can do long-term prediction of system state trajectories. We show theoretically the superior generalization and long-term prediction capability of the RKNN's over the normal neural networks. Two types of learning algorithms are investigated for the RKNN's, gradient-and nonlinear recursive least-squares-based algorithms. Convergence analysis of the learning algorithms is done theoretically, Computer simulations demonstrate the proved properties of the RKNN's.
URI: http://dx.doi.org/10.1109/72.661124
http://hdl.handle.net/11536/32735
ISSN: 1045-9227
DOI: 10.1109/72.661124
期刊: IEEE TRANSACTIONS ON NEURAL NETWORKS
Volume: 9
Issue: 2
起始頁: 294
結束頁: 307
顯示於類別:期刊論文


文件中的檔案:

  1. 000072350000006.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。