ADRC Load Side Speed Controller Parameters Adjustment Based on a Neural Model Applied for a Nonlinear Two-Mass Drive System

The paper is focused on improvements to the conventional speed controller based on Active Disturbance Rejection Control (ADRC) applied for a two-mass electric drive system. The described ADRC structure is based on load-side speed measurement. The paper compares the base structure dynamics with the overall system behavior when plant parameters are changed. The proposed ADRC algorithm extension performs soft controller parameters adjustment to improve the dynamics and plant response. The presented approach accomplishes adaptation capabilities with the use of a Radial Function Neural Network (RBFNN). The article compares the dynamic response of the plant controlled by the conventional ADRC algorithm and the designed neural adaptation extension through the conducted experimental tests.