Adaptive recurrent neuro-fuzzy control of the complex drive system

Abstract

In the paper issues related to the control of the drive system with changeable parameters are presented. The adaptive MRAS-base control structure with a retunable neuro-fuzzy controller is applied. The architecture of the fuzzy sets and recurrent feedbacks are described. The main point of the work is a comparative analysis of the influence of the recurrent feedback on the properties of the control structure. The obtained results have been compared with the classical Mamdani and TSK systems. Selected simulation results are included in the paper as well as some experimental tests that confirm the theoretical investigations.