SUBSTANTIATION OF NEUROCONTROLER PARAMETERS FOR THE CONTROL SYSTEM OF THE VIBRATOR DRIVE OF ADAPTIVE VIBRATION TECHNOLOGICAL MACHINES

Abstract

The article proposes and analyzes the structure of the neurocontroller for controlling the vibratory drive of adaptive vibrating technological machines (AVTM), which allows to implement a two-circuit neurocontrol system of energy and technological parameters of AVTM that its each circuit takes into account inertial and dissipative characteristics. By monitoring the phase shift between the frequency of forced oscillations of the AVTM working body and the frequency of cyclic forcing force of the vibrating drive and using predictive model neurocontrol technology to correct the frequency of cyclic forcing force of the vibrating drive, the neurocontroller provides mini resonant operation. The second circuit of neurocontrol provides on the resonant frequency tracking and stabilization of the specific work of the vibration field of AVTM during the vibration cycle using to adjust the amplitude of oscillations of the working body hybrid neuro-PID control system with self-tuning based on neuromodel AVTM system. The proposed design of the neurocontroller to control the vibratory drive of adaptive vibrating technological machines can improve the quality characteristics of the control of dynamic parameters of both electromagnetic and unbalanced vibratory drive. The use of neural network technologies in the design solution allows the introduction of neurocontrol algorithms that change the parameters of the process of vibration processing implemented by AVTM, or change the load mass of the working body AVTM, through the use of predictive model neurocontrol based on the simplex method or quasi-Newtonian algorithm that will optimally choose a strategy for correcting the frequency of cyclic forcing force of the vibrator to ensure and maintain a constant resonant mode of AVTM and at the resonant frequency AVTM will stabilize the specific operation of the neural network PID-controller with self-adjustment on the basis of the direct AVTM neuroemulator.