The DTNN Identification Model of Magnetic Bearing of One Degree of Freedom

摘要

The neural networks DTNN identification model is developed on the basis of the force analysis of magnetic bearing of one degree of freedom, which reflects the nonlinear delay character between input and output system. This network is able to quickly converge in 5 training steps. The mean square error value reduces to 3.495e-006 in 50 steps. Inspection shows that the neural networks DTNN identification model can fit the I/O character of the magnetic bearing of one degree of freedom within a permitted error range. This paper proposes a new approach for modeling magnetic hearing of one degree of freedom. and lays the foundation for the neural networks DT N, identification model of magnetic hearing-rotor system of five degree of freedom.