Application of adaptive neural controller for drive with elastic shaft and variable moment of inertia

In the paper an application of adaptive neural controller for electrical drive with elastic coupling between motor and the driven mechanism with variable moment of inertia is presented. Due to presence of several mechanical resonances (since it is a multi-mass system) at higher frequencies, a suitably tuned speed filter is applied to the feedback loop in order to damp the selected resonance frequencies. This approach allows to improve the control properties. The speed controller is designed as a neural controller, which allows to remain properties of the control process irrespective of the variable moment of inertia. The collected results of simulation and experiment confirm the proper operation of the control system.