研究目的
To propose a novel inverse force function using sparse least squares support vector machines (LS-SVMs) to achieve nonlinear modeling for precise motion of a planar switched reluctance motor (PSRM).
研究成果
The proposed inverse force function based on sparse LS-SVMs provides precise phase current commands in the presence of nonlinear magnetic characteristic, achieving much higher dynamic position precision compared to the reported PSRM system. It demonstrates feasibility, validity, and promising industrial applicability.
研究不足
The inverse force function has small training error and testing error except that the estimated phase current is less than 1 A, which may limit its application in scenarios requiring very low phase current commands.
1：Experimental Design and Method Selection:
The methodology involves obtaining training and testing sets from experimental measurement, developing a sparse LS-SVMs regression to model the inverse force function, and testing the function's feasibility.
2：Sample Selection and Data Sources:
Experimental measurement of thrust force versus phase current from 0 to 10 A versus position in a pole pitch is performed to obtain the sample set.
3：List of Experimental Equipment and Materials:
The PSRM system includes the PSRM, dSPACE controller, current drivers, linear optical encoders, PC, and power supply.
4：Experimental Procedures and Operational Workflow:
The inverse force function is applied to the PSRM system with dSPACE controller for trajectory tracking.
5：Data Analysis Methods:
The root-mean-square error of the sparse LS-SVMs is defined to assess the learning and generalization performances.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
