Permanent Magnet Toroidal Motor Neural Network Modeling And Position Sensorless Control

Permanent magnet toroidal motor(PMTM)is a new type of permanent magnet synchronous motor,this motor combines planetary worm drive.The special structure design of permanent magnet toroidal motor makes the motor has the advantages of less friction and noise.Permanent magnet toroidal motor can transmit larger torque in smaller space for its special planetary worm mechanism.In this paper,the inductance of permanent magnet toroidal motor is analyzed,the motor is modeled and the sensorless control system of the motor is designed.Based on the analysis of the structure and working principle of permanent magnet toroidal motor,the equivalent coordinate system is established in the direction of planetary wheel rotation.and the self-inductance and mutual inductance of three-phase worm winding are calculated innovatively by using inductance energy method.The expression between the inductance of worm winding and the structural parameters of the motor is obtained,the relationship between the inductance of worm winding and the parameters is analyzed.The mathematical model of permanent magnet toroidal motor is established,and the appropriate parameters for this motor are selected.The motor of Permanent magnet toroidal motor is modeled by using neural network.In order to ensure the control accuracy of permanent magnet toroidal motor,Position Sensorless Control technology is used to control the speed of the motor without increasing the volume of the motor and the complexity of the control system.AS the Model Referchee Adaptive System(MRASAS)is relatively simple,reliable and easy to implement in sensorless control technology,the permanent magnet toroidal motor control based on MRAS is dcsigned,and the corresponding simulation experiments are built under the environment of MATLAB/Simulink,experiments to verify the rationality of the control system design.In view of the low precision and the difficulty of parameters selection for MRAS,a sensorless control system of permanent magnet toroidal motor based on improved sliding mode observer is designed in this paper.The position angle of planetary frame rotor is estimated by arc tangent function method,and the sensorless control system of permanent magnet toroidal motor is realized.The simulation results show that the control accuracy and stability of the sensorless control system are greatly improved,and the improved sliding mode observer control system can reduce the speed jitter of the permanent magnet toroidal motor.