Title :
Extended Luenberger Observer Based on Dynamic Neural Network for Inertia Identification in PMSM Servo System
Author :
Cao, Xianqing ; Bi, Meng
Author_Institution :
Coll. of Inf. Eng., Shenyang Inst. of Chem. Technol., Shenyang, China
Abstract :
A new scheme to estimate the moment of inertia in the motor drive system in very low speed is proposed. The simple speed estimation scheme, which is used in most servo systems for low-speed operation, is sensitivity to variations in machine parameters especially the moment of inertia. To estimate the motor inertia value, an extended Luenberger observer (ELO) is applied. The observer gain matrix can be adjusted on-line based on dynamic neural network. The effectiveness of the proposed ELO is verified by simulation results.
Keywords :
neural nets; permanent magnet motors; servomotors; synchronous motors; PMSM servo system; dynamic neural network; estimation scheme; extended Luenberger observer; inertia identification; moment of inertia; motor drive system; motor inertia value; observer gain matrix; Artificial neural networks; Chemical technology; Least squares approximation; Neural networks; Nonlinear systems; Recurrent neural networks; Sampling methods; Servomechanisms; Servomotors; Torque; dynamic neural network; extended Luenberger observer; inertia estimation; servo system;
Conference_Titel :
Natural Computation, 2009. ICNC '09. Fifth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3736-8
DOI :
10.1109/ICNC.2009.357
