Designing a Neuro-Sliding Mode Controller for Networked Control Systems with Packet Dropout

This paper addresses control design in networked control system by considering stochastic packetdropouts in the forward path of the control loop. The packet dropouts are modelled by mutuallyindependent stochastic variables satisfying Bernoulli binary distribution. A sliding mode controller isutilized to overcome the adverse influences of stochastic packet dropouts in networked controlsystems. Firstly, to determine the parameters of switching function used in the sliding mode controldesign, an improved genetic algorithm is applied. The proposed improved genetic algorithm provides afast convergence rate and a proper dynamic performance in comparison with conventional geneticalgorithms especially in online control applications. Then, an adaptive neural sliding mode controlbased on radial-basis function neural network approximation is proposed to eliminate chatteringphenomenon in the sliding mode control. A numerical example is given to illustrate the effectivenessof the proposed controller in networked control systems. The results show that the proposed controllerprovides high-performance dynamic characteristics and robustness against plant parameter variationsand external disturbances.