This paper addresses a nonlinear feedback control problem for the chaotic arch microelectro- mechanical system with unknown parameters, immeasurable states and partial state-constraint subjected to the distributed electrostatic actuation. To reflect inherent properties and design controller, the phase diagrams, bifurcation diagram and Poincare section are presented to investigate the nonlinear dynamics. The authors employ a symmetric barrier Lyapunov function to prevent violation of constraint when the arch micro-electro-mechanical system faces some limits. An RBF neural network system integrating with an update law is adopted to estimate unknown function with arbitrarily small error. To eliminate chaotic oscillation, a neuro-adaptive backstepping control scheme fused with an extended state tracking differentiator and an observer is constructed to lower requirements on measured states and precise system model. Besides, introducing an extended state tracking differentiator avoids repeated derivative for the virtual control signal associated with conventional backstepping. Finally, simulation results are presented to illustrate feasibility of the proposed scheme. 相似文献
Stochastic variational inference is an efficient Bayesian inference technology for massive datasets, which approximates posteriors by using noisy gradient estimates. Traditional stochastic variational inference can only be performed in a centralized manner, which limits its applications in a wide range of situations where data is possessed by multiple nodes. Therefore, this paper develops a novel trust-region based stochastic variational inference algorithm for a general class of conjugate-exponential models over distributed and asynchronous networks, where the global parameters are diffused over the network by using the Metropolis rule and the local parameters are updated by using the trust-region method. Besides, a simple rule is introduced to balance the transmission frequencies between neighboring nodes such that the proposed distributed algorithm can be performed in an asynchronous manner. The utility of the proposed algorithm is tested by fitting the Bernoulli model and the Gaussian model to different datasets on a synthetic network, and experimental results demonstrate its effectiveness and advantages over existing works.