关键词: 观测器, 自适应调节规律, 残差信号, B样条模型

Abstract:

This paper considers the state observation problem for bounded dynamic stochastic systems by using B-spline model to approximate output probability density functions. First, a form of residual signal is considered for the output probability density function using square root B-spline neural network model, and the on-line tuning of the observer gain is obtained using Lyapunov analysis. Then a new logarithm B-spline model is presented and the adaptive observer is designed. Finally, two simulated examples are used to demonstrate the proposed algorithms, and desired results have been obtained.

Key words: observer, adaptive updat ing rule, residual signal, B-spline model