Active Disturbance Rejection Control of Bearingless Permanent Magnet Synchronous Motor Based on Genetic Algorithm and Neural Network Parameters Dynamic Adjustment Method

In order to solve the problem of poor control performance, caused by fixed parameters active disturbance rejection (ADRC) in bearingless permanent magnet synchronous motors (BPMSM), a dynamic adjustment method ADRC, based on genetic algorithm and back-propagation neural network (GA-BPNN), is proposed. Firstly, ADRC models motor-side suspension-side are established, according motor speed formula suspension force formula. Secondly, BPNN used dynamically adjust operation processes deduced, chain rule. Thirdly, avoid getting out control, convergence failure BPNN, GA floating point coding optimize initial value BPNN. Finally, these methods integrated form BPMSM system, GA-BPNN-ADRC, effectiveness verified an experimental platform. The results, show that proposed reduces probability system from 35.61% 0%, anti-interference ability performance displacement significantly improved.