Open AccessSensorless Speed/Torque Control of DC Machine Using Artificial Neural Network Technique
Author(s) -
Rakan Khalil Antar,
Ahmed A. Allu
Publication year - 2016
Publication title -
mağallaẗ tikrīt li-l-ʻulūm al-handasiyyaẗ/tikrit journal of engineering sciences
Language(s) - English
Resource type - Journals
eISSN - 2312-7589
pISSN - 1813-162X
DOI - 10.25130/tjes.23.3.06
Subject(s) - control theory (sociology) , chopper , dc motor , torque , electronic speed control , engineering , mras , artificial neural network , direct torque control , matlab , computer science , control engineering , vector control , voltage , induction motor , electrical engineering , control (management) , artificial intelligence , physics , thermodynamics , operating system
In this paper, Artificial Neural Network (ANN) technique is implemented to improve speed and torque control of a separately excited DC machine drive. The speed and torque sensorless scheme based on ANN is estimated adaptively. The proposed controller is designed to estimate rotor speed and mechanical load torque as a Model Reference Adaptive System (MRAS) method for DC machine. The DC drive system consists of four quadrant DC/DC chopper with MOSFET transistors, ANN, logic gates and routing circuits. The DC drive circuit is designed, evaluated and modeled by Matlab/Simulink in the forward and reverse operation modes as a motor and generator, respectively. The DC drive system is simulated at different speed values (±1200 rpm) and mechanical torque (±7 N.m) in steady state and dynamic conditions. The simulation results illustrate the effectiveness of the proposed controller without speed or torque sensors.