Elevator With Gearless Permanent Magnet Synchronous Machine Speed Traction Control System Research Based On Neural Network

Permanent Magnet Synchronous Motors (PMSM) are widely applied in different places depending on their several inherent advantages. The low-speed and high-torque PMSM traction system is better than other's when used in elevator control system.The system dynamic performances are affected by the nonlinear friction factors when elevator running in low speed. With deeply research on PMSM vector control, a traction system is proposed in this thesis that based on TMS320F2812 DSP.The nonlinearity characters of PMSM caused by static and dynamic friction are trouble to forecast and avoid, especially with PI regulator. A Neural Network controller based on BP is proposed in order to achieve better conform performances of elevator. The controller has simpler structure and control algorithms and can be realized online easily.In order to prove the effectiveness of the control algorithm, a simulation is made with matlab/simulink. The simulation results show the better robust and the better static and dynamic performance comparing to the PID control. This method has a simple structure and control algorithms, and can be realized online easily.