DocumentCode :
2503730
Title :
Sensorless control of a vector controlled three-phase induction motor drive using artificial neural network
Author :
Iqbal, Arif ; Khan, M. Rizwan
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol., Roorkee, India
fYear :
2010
fDate :
20-23 Dec. 2010
Firstpage :
1
Lastpage :
5
Abstract :
The sensorless drive system is more versatile due to its small size and low cost. Therefore it is advantageous to use the sensorless system where the speed is estimated by means of a control algorithm instead of measuring. This paper presents a new model reference adaptive system (MRAS) speed observer for high-performance field-oriented control induction motor drives using neural networks. The proposed MRAS speed observer uses the current model as an adaptive model. The neural network has been then designed and trained online by employing a back propagation network (BPN) algorithm. In the estimator design using motor parameters and monitored stator voltages and currents also taking the motor speed as a variable. Performance analysis of speed estimator with the change in motor parameters especially resistances of stator and rotor is presented. Its performance under fault condition is also examined. The estimator was designed and simulated in Matlab/Simulink. Simulation result shows a good performance of speed estimator especially under fault condition.
Keywords :
angular velocity control; backpropagation; control engineering computing; electric machine analysis computing; fault diagnosis; induction motor drives; machine vector control; model reference adaptive control systems; neural nets; observers; sensorless machine control; BPN algorithm; MRAS speed observer; Matlab-Simulink; artificial neural network; backpropagation network algorithm; high-performance field-oriented control induction motor drives; model reference adaptive system; monitored stator voltages; motor parameters; sensorless control; sensorless drive system; speed estimator design; vector controlled three-phase induction motor drive; Adaptation model; Artificial neural networks; Induction motors; Mathematical model; Resistance; Rotors; Transient analysis; Artificial neural networks (ANNs); Induction motor; Sensorless speed control; Vector control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Power Electronics, Drives and Energy Systems (PEDES) & 2010 Power India, 2010 Joint International Conference on
Conference_Location :
New Delhi
Print_ISBN :
978-1-4244-7782-1
Type :
conf
DOI :
10.1109/PEDES.2010.5712474
Filename :
5712474
Link To Document :
بازگشت