Gonzalez-Olvera Marcos A, Tang Yu
College of Science and Technology, Autonomous University of Mexico City, Mexico City, Mexico.
IEEE Trans Neural Netw. 2010 Apr;21(4):672-9. doi: 10.1109/TNN.2010.2041068. Epub 2010 Feb 17.
This brief presents a structure for black-box identification based on continuous-time recurrent neurofuzzy networks for a class of dynamic nonlinear systems. The proposed network catches the dynamics of a system by generating its own states, using only input and output measurements of the system. The training algorithm is based on adaptive observer theory, the stability of the network, the convergence of the training algorithm, and the ultimate bound on the identification error as well as the parameter error are established. Experimental results are included to illustrate the effectiveness of the proposed method.
本简报提出了一种基于连续时间递归神经模糊网络的黑箱识别结构，用于一类动态非线性系统。所提出的网络通过生成自身状态来捕捉系统的动态，仅使用系统的输入和输出测量值。训练算法基于自适应观测器理论，建立了网络的稳定性、训练算法的收敛性以及识别误差和参数误差的最终界。还包含实验结果以说明所提方法的有效性。
