Open AccessMFO-ANN based FOPID Controller for Torque and Speed Control of SRM Drive System
Author(s) -
Kunisetti V. Praveen Kumar,
Dr.P. Ram Kishore Kumar Reddy,
P. Sujatha
Publication year - 2020
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.f4156.049620
Subject(s) - control theory (sociology) , torque , pid controller , torque ripple , matlab , minification , controller (irrigation) , computer science , artificial neural network , control engineering , direct torque control , engineering , control (management) , artificial intelligence , induction motor , voltage , temperature control , agronomy , physics , electrical engineering , biology , thermodynamics , programming language , operating system
This paper proposed an optimal control algorithm based Fractional Order PID (FOPID) controller for the torque ripple minimization of Switched Reluctance Motor (SRM) drive system. That convalesce both control loop task, the Moth Flame Optimization (MFO)- Artificial Neural Network (ANN) algorithm is insinuated. The routine of intelligent technique is principally as the objective function of system error minimization. At this time the quality inspired algorithm of MFO is firstly reconnoitered to optimize the speed and torque error from the SRM system. Instead the output of MFO algorithm is optimized and to finding the premium value, the ANN method is recuperated. Nonetheless, the output of MFO-ANN is imperiled to the input of FOPID controller. For tweaking the exact FOPID gains, the multi objective functions are grew. Created on the operation of propositioned algorithm by normalize the system speed and minimalize the torque ripples of SRM system. The qualities of the suggested procedure are force falconer and in addition to augmented level of the reliability and flexibility in answering the system error. Also the enactment of proposed MFO-ANN process is executed in the MATLAB/Simulink running platform.