研究一类MIMO状态可测的非线性连续系统的激励辨识问题.输入激励信号采用高斯白噪声,均匀采样获得输出状态数据.根据Girsanov定理获得系统参数的渐近无偏估计.数值仿真试验说明了该方法的有效性并发现耦合多变量系统辨识中的NNR现象.最后给出该系统的分步激励辨识算法.
We propose an identification approach for a type of MIMO nonlinear continuous-time systems with observable states using driving signals. The driving signal is Gaussion white noise, the state outputs axe sampled evenly. The maximum likelihood estimates of the model parameters are derived by using the Girsanov theorem. The numerical simulations illustrate the efficiency of the estimates and the NNR phenomenon of coupling multi-variable appears in the numerical simulations. A step-type identification algorithm is suggested at the end.