Synthesized NN Predictive Controller for the three-mass electromechanical system. For the control object presented the algorithm of the neuro controller synthesis; determined parameters of the neuro controller that are most critical for the control performance; optimal values of the parameters are found. Modelling of the neuro control is performed. It is shown that the synthesized neuro controller supplies high dynamic performance of the system.
neural network technologies, neural network control system, three-mass electromechanical system, neuroregulator with foresight NN Predictive Controller