AUTOMATIC REGULATOR FOR NON-STATIONARY OBJECTS WITH AN INCREASED RANGE OF NORMAL OPERATION

Abstract

Many objects automatic control unsteady. This is manifested in the change of their parameters. Therefore, periodically adjust the required parameters of the controller. This work is usually carried out rarely. For a long time, regulators are working with is not the optimal settings. The consequence of this is the low quality of many industrial control systems. The solution problem is the use of robust controllers. Explores the possibility of increasing the survivability of automatic control systems by expanding the area of their normal work. This is achieved by using an artificial neural network simple structure. The method is based on the cooperative effect of neural structures. In this block diagram of the controller is very simple. Such control effectively compensates the coordinate perturbations if they act on the control channel.