The Applied Research of Rotor Position Sensorless Detection of Switched Reluctance Motor Based on Genetic RBF Neural Network
Due to the rotor position of switched reluctance motor (SRM) is a highly nonlinear function of stator windings current and flux linkage, so general linear and analytical methods are difficult to achieve precision results, hi the paper, a method is presented that a genetic RBF neural network (RBFNN) is used to rotor position sensorless detection of SRM. Hence, extensive mapping ability of neural network and rapid global convergence of genetic algorithm (GA) are fully developed. The simulation is carried out based on theMatlab7.1.The neural network model is simulated for finding the rotor position at different currents from a suitable measured data for a given SRM. In order to testify the validity and accuracy of the model, a lot of simulation is carried out Results of experiment show that the scheme not only can acquire the rotor position timely and exactly, but also has great robustness and adaptive ability.
SRM GA RBFNN Optimize Simulation
Jun Hang You-rui Huang Lei Shen
Institute of Electrical & Information Engineering Anhui University of Science & Technology Huainan,China
国际会议
南京
英文
139-142
2010-08-26（万方平台首次上网日期，不代表论文的发表时间）