Title :
EHM Based Neural Model for Hysteresis
Author :
Ma, Lianwei ; Tan, Yonghong
Author_Institution :
Dept. of Autom., Shanghai Jiaotong Univ.
Abstract :
This paper proposes a neural model for hysteresis. A method of continuous transformation is used to construct an elementary hysteresis model (EHM), which implements a one-to-one mapping between the input space and the output space of the hysteresis. The output of the EHM is used as one of the input signals of the neural network (NN) to approximate the behavior of hysteresis. A parabolic factor is introduced to improve the modeling performance for the major and minor loops of the hysteresis
Keywords :
hysteresis; neural nets; transforms; EHM based neural model; continuous transformation; elementary hysteresis model; neural network; one-to-one mapping; parabolic factor; Degradation; Intelligent systems; Magnetic hysteresis; Magnetic levitation; Neural networks; Neurons; Oscillators; Piezoelectric actuators; System identification; System performance;
Conference_Titel :
Networking, Sensing and Control, 2006. ICNSC '06. Proceedings of the 2006 IEEE International Conference on
Conference_Location :
Ft. Lauderdale, FL
Print_ISBN :
1-4244-0065-1
DOI :
10.1109/ICNSC.2006.1673141
