SPEED CONTROL OF DC MOTOR BY USING NOVEL NEURAL NETWORK CONFIGURATION

Abstract:This paper uses Artificial Neural Networks (ANNs) in estimating speed and controlling it for a separately excited DC motor. The rotor speed of the dc motor can be made to follow an arbitrarily selected trajectory. The purpose is to achieve accurate trajectory control of the speed, especially when the motor and load parameters are unknown. Such a neural control scheme consists of two parts. One is the neural identifier which is used to estimate the motor speed. The other is the neural controller which is used to generate a control signal for a converter. These two neural networks are trained by Levenberg- Marquardt back-propagation algorithm. ANNs used in this are the standard three layers feed forward neural network with sigmoid activation functions in the input and hidden layers while linear activation function is employed for the output layer. The conventional constant gain feedback controller fails to maintain the performance of the system at acceptable levels under unknown dynamics in load torque. On the other hand, ANNs act as an effective tool to implement the model and adaptive control in a complicated nonlinear system having expansive allocations. The adaptive learning algorithm is formed in such a way that the learning rate is as large as possible while maintaining the stability of the learning process. This simplifies the learning process in terms of computation time, which is of special importance in real-time implementation.
Antsaklis, P. J. (April, 1990). Neural Networks in control systems. IEEE control systems magazine, volume-10 , 3-5. Cajueiro, D. O., & Hemerly, E. M. (December, 2003). Direct Adaptive Control using Feedforward Neural Networks. Revista Control & Automation, Vol.14, No.4 , 348-358.

Chen, S., Billings, S., & Grant, P. (April, 1990). Non-linear system identification using neural networks. IEEE Transactions, volume-51 , 1191-1214. DOURATSOS, I., & BARRY, J. (2007). NEURAL NETWORK BASED MODEL REFERENCE ADAPTIVE. International journal of information and systems sciences, volume-3 , 161-179.

CHOPPER DESIGNED D.C MOTOR OPERATING CONTROL Abstract:The speed of separately excited DC motor can be controlled from below and up to rated speed using chopper as a converter. The chopper firing circuit receives signal from controller and then chopper gives variable voltage to the armature of the motor for achieving desired speed. There are two control loops, one for controlling current and another for speed. The controller used is Proportional-Integral type which removes the delay and provides fast control. Modeling of separately excited DC motor is done. The complete layout of DC drive mechanism is obtained. The designing of current and speed controller is carried out. The optimization of speed controller is done using modulus hugging approach, in order to get stable and fast control of DC motor. After obtaining the complete model of DC drive system, the model is simulated using MATLAB(SIMULINK).The simulation of DC motor drive is done and analyzed under varying speed and varying load torque conditions like rated speed and load torque, half the rated load torque and speed, step speed and load torque and stair case load torque and speed.

[20] Bose B.K., Power electronics and motor drives recent technology advances, Proceedings of the IEEE International Symposium on Industrial Electronics, IEEE, 2002, pp 22-25.

CONTROL AND DESIGNING OF THE DC MOTOR DRIVE USING P-I CONTROLLERS WITH THE HELP OF MATLAB SIMULATION

Abstract:The paper describes the designing of a closed loop model of the dc motor drive for controlling speed. Accuracy and the dynamic responses are better in a closed loop system. In the closed loop system, acceleration and the deceleration of the motor can be controlled according to the requirement. In order to regulate drives automatically, the controlled variables are measured. A tachogenerator is used for this purpose. The output of the tachogenerators is compared with a preset reference voltage. The differences between these two signals are fed as an actuating signal to control the elements of the system. Control amplifiers are used as both comparators and amplifiers. As a small change in the voltage can cause a large change in the motor current and lead to a particular drive control feature. There are two closed paths in the dc control scheme. One is the outer speed control loop and the other is the inner current control loop. Both the loops are controlled with the help of P-I controllers having their own gains and the time constants according to the requirement of the system. The output of the speed P-I controller which is the function of the speed error is used to command for current P-I controller and compared with armature current. The current P-I controller output control the triggering circuit of the converter. The armature current tends to increase to a large value when the motor is accelerating. A current limit can be obtained in this system by limiting the maximum current command voltage. If the motor speed drops below the set point, the resulting error signal causes the gate pulse generator to advance the firing pulses, and increase the rectifier output voltage. Consequently the speed rises to the desired level.

ANN BASED PEAK POWER TRACKING FOR PV SUPPLIED DC MOTORS Abstract:The report presents an application of an Artificial Neural Network(ANN) for the identification of the optimal operating point of a PV supplied separately excited dc motor driving two different load torques. A gradient descent algorithm is used to train the ANN controller for the identification of the maximum power point of the Solar Cell Array (SCA) a gross mechanical energy operation of the combined system. The algorithm is developed based on matching of the SCA to the motor load through a buck-boost power converter so that the combined system can operate at the optimum point. The input parameter to the neural network is solar insulation and the output parameter is the converter chopping ratio corresponding to the maximum power output of the SCA or gross mechanical energy output of the combined PV system. The converter chopping ratios at different solar insulations are obtained from the ANN controller for two different load torques and are compared with computed values. * Appelbaum J. Starting and Steady state characteristics of dc motors powered by solar cell generators,IEEE Trans. on Energy conversion 1, pp 17-24. * Saied M.M Matching of the dc motors to PV generators for max daily gross mechanical energy,IEEE Trans on Energy conversion 3,pp 465-472.

A SLIDING MODE CONTROLLER FOR INDUCTION MOTOR DRIVES Abstract:Induction motors are being applied today to a wider range of applications requiring variable speed. Generally, variable speed drives for Induction Motor require both wide operating range of speed and fast torque response, regardless of any disturbances and uncertainties (like load variation, parameters variation and un-modeled dynamics). This leads to more advanced control methods to meet the real demand. The recent advances in the area of field-oriented control along with the rapid development and cost reduction of power electronics devices and microprocessors have made variable speed induction motor drives an economical alternative for many industrial applications. These AC drives are nowadays replacing their DC counter part and are becoming a major component in todays sophisticated industrial manufacturing and process automation. Advent of high switching frequency PWM inverters has made it possible to apply sophisticated control strategies to AC motor drives operating from variable voltage, variable frequency source. The complexity in there mathematical model and the consequent need for the sophisticated algorithms are being handled by the computational power of low cost microprocessors to digital signal processors (DSPs). In the formulation of any control problem there will typically be discrepancies between the actual plant and the mathematical model developed for controller design. This mismatch may be due to un-modeled dynamics, variation in system parameters or the approximation of complex plant behavior by a straightforward model. The designer must ensure that the resulting controller has the ability to produce required performance levels in practice despite such plant/model mismatches. This has led to an intense interest in the development of robust control methods which seek to solve this problem. One particular approach to robust-control controller design is the so-called sliding mode control methodology. In this dissertation report, a sliding mode controller is designed for an induction motor drive. The gain and band width of the controller is designed considering rotor resistance variation, model in accuracies and load disturbance, to have an ideal speed tracking. The chattering effect is also taken into account. The controller is simulated under various

conditions and a comparative study of the results with that of PI controller has been presented. 1. R.M. Cuzner, R.D. Lorenz, D.W. Novotny, Application of non-linear observers for rotor position detection on an induction motor using machine voltages and currents, IEEE- IAS Annual Meeting Conference Record, October 1990, pp. 416421. 2. Atkinson D. J., P. P. Acarnley and J. W. Finch, Application of estimation technique in vector controlled inductin motor drives, IEE Conference Proceeding, London, July 1990, pp. 358-363