Ultrasonic Motor Drived Two-Axis Motion Control System Based on Neural Network Controller

• Main Authors: Yu-Jui Tien, 田育瑞
• Other Authors: Faa-Jeng Lin
• Format: Others
• Language: zh-TW
• Published: 2001
• Online Access: http://ndltd.ncl.edu.tw/handle/87916235706351699976

碩士 === 中原大學 === 電機工程研究所 === 89 === The subject of this thesis is to develop a two-axis platform controlsystem using rotary ultrasonic motors (USMs). This system can be separated into two parts: one is the driver system, the other is the control system. The driver system uses a parallel-resonant inverter with an energy feedback circuit to drive the USMs of the two-axis platform. The circuit with the feature of energy feedback can reduce the quality factor of the resonant tank and to improve the driving characteristics of the parallel-resonant inverter. Moreover, the exact mathematical model of USM can not be obtained currently and the motor parameters are nonlinear and time-varying due to increase in temperature and changes in motor drive operating conditions, such as driving frequency, source voltage, load torque and static pressure force between stator and rotor of USM. Therefore, intelligent control systems are designed to control the two-axis platform controlled plant. First, the fuzzy neural network (FNN), which combines the capability of fuzzy reasoning in handling uncertain information and the capability of artificial neural network in learning from processes, is adopted. Moreover, based on the control technology of the FNN, the recurrent fuzzy neural network (RFNN) and the wavelet neural network (WNN) are developed individually to control the two-axis platform controlled plant. With the proposed intelligent controllers, the position responses of the movers of the two-axis platform processes the advantage of good transient control performance and robustness to uncertainties for the tracking of periodic reference trajectories. Finally, The effectiveness of the proposed control schemes is verified by some experimental results.