Control of Induction Motor Using Artificial Neural Network
The main objective of this paper is to design a controller for control of an Induction motor. In this paper, we have proposed v/f control of induction motor using artificial neural network, the network is trained using back propagation algorithm and Leven
- PDF / 2,447,915 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 20 Downloads / 350 Views
Abstract The main objective of this paper is to design a controller for control of an Induction motor. In this paper, we have proposed v/f control of induction motor using artificial neural network, the network is trained using back propagation algorithm and Levenberg–Marquardt learning is used faster computation. The main approach is to keep voltage and frequency ratio constant to obtain constant flux over the entire range of operation and thus to have precise control of the machine. The effectiveness of the controller is demonstrated using MATLAB/Simulink simulation.
Keywords Induction motor v/f control Artificial neural network propagation learning Levenberg–marquardt algorithm
Back
Abbreviations ANN BP PI NN IM VSI PWM EMF RPM
Artificial Neural Network Back Propagation Proportional-Integral Neural Network Induction motor Voltage Source Inverter Pulse Width Modulation Electromagnetic Force Rotation Per Minute
A. Kumar (&) R. Singh C. Singh Mahodi S. Kumar Sahoo VIT University, Vellore, India e-mail: [email protected] R. Singh e-mail: [email protected] C. Singh Mahodi e-mail: [email protected] S. Kumar Sahoo e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2017 S.S. Dash et al. (eds.), Artificial Intelligence and Evolutionary Computations in Engineering Systems, Advances in Intelligent Systems and Computing 517, DOI 10.1007/978-981-10-3174-8_66
791
792
A. Kumar et al.
1 Introduction Induction motors are the most preferred motors for any industrial or domestic purpose applications. For last few years, it was being used in the only applications which require a constant speed because of the expensive or inefficient speed control of the conventional methods. However, advancement in power electronic devices and converter technologies in the past few decades has improved the efficient speed control by varying the supply frequency, which made possible the various forms of adjustable speed induction motor drives. Along with that there has been a quite recognizable improvement in control methods and artificial intelligence which incorporates neural network, fuzzy logic, and genetic algorithm [1–4]. One of the major changes occurred in the context of induction motor control was the invention of field-oriented control (FOC). In this method, determining correctly the orientation of the rotor flux vector is mandatory, rather it leads to the poor response of the drive, but due to its complexity, it is not that feasible [1, 4–6]. Although, direct torque control (DTC) has a very good torque response without any complex orientation transformation and controls the inner loop current but still it possesses some drawbacks, like torque and flux ripple [7–9]. In this paper, scalar control is implemented where the motor is fed with variable frequency signals generated by the PWM control from an inverter where the v/f ratio is maintained constant so that constant torque can be retained over the entire operating range [3, 10]. There are a number of ways to implement scalar control. One
Data Loading...
