Title :
Nonlinear modeling for switched reluctance motor by measuring flux linkage curves
Author :
Cai, Yan ; Yang, Qingxin ; Su, Lihua ; Wen, Yanbin ; You, Yiming
Author_Institution :
Sch. of Electr. Eng. & Autom., Tianjin Polytech. Univ., Tianjin, China
Abstract :
Two kinds of modeling methods are studied based on measuring flux linkage curves for switched reluctance motor (SRM) which the machine geometry is unknowable. A simplified model of SRM is presented for general switched reluctance drive (SRD), which is easy to be built and its accuracy has been improved compared with the quasi-linear model. To get an accurate model, the BP Neural Network (BPNN) nonlinear model of SRM is developed based on Levenberg-Marquardt algorithm by measuring flux linkage characteristics. Compared with measured data of flux linkage and torque, the BPNN model of SRM is proved accurate and meet high performance SRD. Both kinds of the modeling methods are suitable for SRD with different control performance requirement respectively.
Keywords :
backpropagation; machine testing; magnetic flux; neural nets; reluctance motors; BP neural network nonlinear modeling methods; Levenberg-Marquardt algorithm; flux linkage curve measurement; machine geometry; quasi-linear model; switched reluctance drive; switched reluctance motor; Couplings; Geometry; Magnetic analysis; Magnetization; Neural networks; Position measurement; Reluctance machines; Reluctance motors; Solid modeling; Voltage; BP Neural Network; nonlinear model; simplified model; switched reluctance motor (SRM);
Conference_Titel :
Computer Engineering and Technology (ICCET), 2010 2nd International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-6347-3
DOI :
10.1109/ICCET.2010.5486289
