改进型SVM在轴向磁轴承转子位移自检测中的应用  

Application of Improved SVM in Self-Sensing of Rotor Displacement in Axial Active Magnetic Bearing

作　　者：陶涛[1,2] 马小燕 花良浩[1] TAO Tao;MA Xiaoyan;HUA Lianghao(Yangzhou Polytechnic Institute,Yangzhou 225127,China;Yangzhou Information and Automation Engineering Technology Research Center,Yangzhou 225127,China)

机构地区：[1]扬州工业职业技术学院,江苏扬州225127 [2]扬州市信息与自动化工程技术研究中心,江苏扬州225127

出　　处：《电机与控制应用》2018年第10期106-112,共7页Electric machines & control application

基　　金：国家自然科学基金项目(51575244);江苏省"青蓝工程"项目(2017);江苏省高水平骨干专业建设项目(苏教高[2017]17号);扬州市科技计划项目(YZ2018072;SCX2017020022;YZ2018147)

摘　　要：磁轴承采用位移自检测技术能够减少磁轴承体积、降低成本和提高可靠性。提出了一种基于混合核函数最小二乘支持向量机(LS-SVM)预测模型的磁轴承自检测技术。介绍了轴向主动磁轴承的工作原理并推导了其悬浮力的数学模型;在混合核函数LS-SVM回归原理的基础上,建立了控制线圈电流与转子位移之间的非线性预测模型,并优化了LS-SVM参数,实现了无位移传感器控制。构建了轴向主动磁轴承系统自检测仿真模型,针对所提自检测方法进行了仿真研究,仿真结果表明该模型能够准确预测转子轴向位移。进一步的试验结果表明,该方法具有良好的轴向位移自检测性能,实现了轴向主动磁轴承无位移传感器下稳定悬浮运行。The self-sensing magnetic bearing could reduce the cost and the axial size of the magnetic bearing and increase its reliability.A self-sensing control method based on mixed-kernel least squares support vector machine(LS-SVM)forecasting model was proposed for an axial active magnetic bearing(AAMB).The principle and mathematical model of the active magnetic bearing were introduced;based on the principle of the mixed-kernel LS-SVM,the nonlinear forecasting model between the current and the displacement which realized the displacement self-sensing control was built through parameter optimization.The control system of the AAMB with self-sensing was constructed.The simulation results showed that the prediction model could accurately detect the rotor axial displacement.Further experimental results also showed that the method had a good ability of axial displacement self-sensing.The AAMB could realize stable suspension operation without displacement sensors.

关 键 词：轴向主动磁轴承 轴向位移 自检测 预测模型 

分 类 号：TM301.2[电气工程—电机]