INTELLIGENT METHOD OF DYNAMIC CONTROL FOR A CLASS OF STOCHASTIC NONLINEAR SYSTEMS
Annotatsiya
The paper considered the problems of researching the stabilisation system and backstepping control of stochastic nonlinear systems. The characteristics of stochastic nonlinear dynamic control systems are random signals with normal lawful distribution, which significantly complicates task control. In stochastic control, it is necessary to determine the trajectories of the control variables in order to achieve the desired control objective at minimum cost. Since the mathematical equations of stochastic nonlinear systems are not always constant, not every model-based controller can be accurate. Therefore, in this work, a neuro-fuzzy network is used to evaluate the parameters of the control system with backstepping, which allows us to overcome the difficulties associated with the inaccuracy of the mathematical model of the system. This paper proposes to use a combination of the hybrid application of fuzzy neural network and backstepping control method to control nonlinear plants for analytical support of the control system stability. A comparative analysis of the proposed method with a neural network control system using a radial basis function for solving the assigned task is implemented. The analysis of the results shows that the proposed method is highly effective and can be used for any class system under consideration.