This paper now the modeling and simulation of an adaptive neuro-fuzzy inference method (ANFIS) to control the speed of the switched Reluctance motor .The SRM control is thus a difficult to be in use in the nonlinear use, specially in the control of speed in automobiles. The Neuro-fuzzy system include the advantages of both neural-network and fuzzy system.
This controller is great additional effective than Fuzzy logic and neural network based controller, while it has the ability of self-learning the gain values and adapt correctly to situations, thus gain more flexibility to the controller. A complete simulation, well-designed to the nonlinear model of Switched Reluctance Drive was planned using MATLAB/SIMULINK.
- SR Drive
Fig.1.Block Diagram of ANFIS Controller for SRM Plant
Fig.2: Response of the Speed and Torque Control of SRM using ANFIS with Speed Command 3000 Rpm under no load conditions.
Fig.3: Response of The Speed and Torque Control of SRM using Fuzzy, ANN and ANFIS with Speed command 4000 rpm.
Fig.4: Response of the Speed and Torque Control of SRM using ANFIS with Speed Command 4000 rpm.
Fig.5: Response of the speed control of SRM using FUZZY, ANN and ANFIS with speed Command 3000 RPM under load Conditions
Fig.6: Response of the speed and torque control of SRM using ANFIS with speed Command 3000 RPM under load conditions
In this paper, ANFIS-based controller was given for SR drives. The speed and torque control method existing in this paper and measure with the previous control plan (fuzzy &ANN), while it can be used in both no load and load running speeds and environment including speed and torque migrant, zero-speed stop.
And startup, and does not suppose the linear quality of the SR motor.Moreover, the planned method does not need of complex estimation to be carried out during the real-time operation, and no complex mathematical model of the SR motor is needed. A main thought in the research was the strength and safety of the speed controlling method.
- P. Lyons, S. R. MacMinn, and M. A. Preston, “Flux/current methods for SRM rotor position estimation,” in Proc. IEEE Industry Application Soc. Annu. Meeting, vol. 1, 1991, pp. 482–487.
- R. MacMinn, C. M. Steplins, and P. M. Szaresny, “Switched reluctance motor drive system and laundering apparatus employing same,” U.S. Patent 4 959 596, 1989.
- Ehsani, I. Husain, S. Mahajan, and K. R. Ramani, “New modulation encoding techniques for indirect rotor position sensing in switched reluctance motors,” IEEE Trans. Ind. Applicat., vol. 30, pp. 85–91, Jan./Feb. 1994.
- R. Dunlop and J. D. Marvelly, “Evaluation of a self commuted switched reluctance motor,” in Proc. Electric Energy Conf., 1987, pp. 317–320.
- Ramesh Palakeerthi, Subbaiah.P ,2014, ‘High Speed Charging and Discharging Current Controller Circuit to Reduce Back EMF by NeuroFuzzy Logic ‘, International Journal of Applied Engineering Research, 9, no.22