Search

In this paper, a switching periodic adaptive control approach is proposed for a class of nonlinear systems with periodic parametric uncertainties whose period and bound are not known. A fully saturated periodic adaptation law is utilized to estimate the unknown parameter vector. A logic switching based algorithm is provided to tune the unknown period and bound of the parameter vector online. By virtue of Lyapunov energy function, asymptotic convergence can be ensured for the tracking error and all the signals in the system is guaranteed bounded. A simulation to a one-link robotic manipulator is carried out to demonstrate the effectiveness of the switching learning control algorithm.

This paper mainly aims at reducing relative learning complexity of subnets originate from “be Expert in Multiple aspects and Good at Many” (EMGM) modular neural network (MNN). Firstly, subnet learning algorithm which has a pure sequential execution style is built and convergence analysis is given. Secondly, in EMGM MNN system, an equivalent learning condition, which satisfies the criterion needed for the efficient training algorithm designed before, is founded for every subnet. Three identification problems have been involved to test the effectiveness and efficiency of the new framework in dealing with low dimension data. Both theoretical and experimental results show the new framework will reduce relative learning complexity of every subnet. The experiment result also shows new framework can achieve comparable generalization capability with original one. Furthermore, Bias Variance analysis shows maximum ability of generalization performance improvement of EMGM MNN may exist and the improvement comes from the improvement of bias estimation accuracy.