Model free adaptive control scheme based on Elman neural network prediction

Model free adaptive control (MFAC) is a typical data-driven control method. This method only uses the input and output data of the system to design the controller and gets rid of the dependence of the controller design on the model. However, this control method is difficult to control large delay and multi disturbance objects. In order to solve these problems, this paper proposes an anti disturbance model free adaptive controller based on Elman neural network prediction, which uses neural network to predict the system output, reduces the calculation amount of the algorithm, and speeds up the convergence speed; in addition, when solving the control variable, the disturbance factor is added to make the controller act in advance and improve the anti disturbance ability. This control method is applied to the coordinated control system of drum furnace, which shows the feasibility and effectiveness of this control method.