摘要
开关磁阻电机具有结构简单、工作可靠、效率高和成本较低等优点,在很多领域都显示出强大的竞争力,但是位置传感器的存在不仅削弱了开关磁阻电机结构简单的优势,而且降低了系统高速运行的可靠性,增加了成本。针对这一问题,提出了基于支持向量机的开关磁阻电机转子位置估计新方法。该方法针对开关磁阻电机的非线性,利用支持向量机泛化能力强以及能够较好地解决小样本学习问题的特点,通过离线学习的方法形成一个理想的支持向量机结构来实现电机电流、磁链与转子位置之间的非线性映射,实现开关磁阻电机的转子位置估计。仿真及实验结果表明,该方法能够实现电机转子位置的准确估计,进而实现开关磁阻电机的无位置传感器控制。
Switched reluctance motor （SRM） with simple construction, high reliability, high efficiency and low cost, has shown its strong competition in many fields. However, mechanical position sensors increase the cost, complexity and potential unreliability at high speed. This paper presents an approach of rotor position estimation for switched reluctance motor based on support vector machine （SVM） . For the nonlinear character of SRM, this approach takes advantage of SVM with better solution for small-sample learning problem and good generalization ability. Through the off-line learning, a better support vector machine structure in which phase currents and phase flux linkages are inputs and the corresponding rotor position is the output, is built to form an efficient nonlinear mapping, so that, it can facilitate the rotor position estimation. The simulation and experimental results show that this method can achieve correct rotor position estimation, and thus the sensorless control of SRM is realized.
出处
《电工技术学报》
EI
CSCD
北大核心
2007年第10期12-17,共6页
Transactions of China Electrotechnical Society
基金
天津市应用基础研究计划资助项目(06YFJMJC01900)
关键词
开关磁阻电机
转子位置估计
支持向量机
序列最小优化算法
Switched reluctance motor, rotor position estimation, support vector machine, sequential minimal optimization algorithm
