Efficient speed control of induction motor using RBF based model reference adaptive control method

Abstract

Original scientific paperThis paper proposes a model reference adaptive speed controller based on artificial neural network for induction motor drives. The performance of traditional feedback controllers has been insufficient in speed control of induction motors due to nonlinear structure of the system, changing environmental conditions, and disturbance input effects. A successful speed control of induction motor requires a nonlinear control system. On the other hand, in recent years, it has been demonstrated that artificial intelligence based control methods were much more successful in the nonlinear system control applications. In this work, it has been developed an intelligent controller for induction motor speed control with combination of radial basis function type neural network (RBF) and model reference adaptive control (MRAC) strategy. RBF is utilized to adaptively compensate the unknown nonlinearity in the control system. The indirect field-oriented control (IFOC) technique and space vector pulse width modulation (SVPWM) methods which are widespread used in high performance induction motor drives has been preferred for drive method. In order to demonstrate the reliability of the control technique, the proposed adaptive controller has been tested under different operating conditions and compared performance of conventional PI controller. The results show that the proposed controller has got a clear superiority to the conventional linear controllers.Key words: Induction motor, neural network, model reference adaptive control, vector control.Učinkovito upravljanje brzinom induktivnog motora korištenjem metode adaptivnog upravljanja s referentnim modelom zasnovane na RBF-u. Ovaj rad prikazuje adaptivni regulator s referentnim modelom zasnovan na neuronskoj mreži za induktivne motore. Ponašanje tradicionalnih regulatora s povratnom vezom pokazalo se nedovoljno dobrom za upravljanje brzinom induktivnih motora zbog nelineatnosti strukture sustava, promjene okolišnih uvjeta, i efekta ulaznih poremećaja. Uspješno upravljanje brzinom induktivnog motora zahtjeva nealinearne upravljačke sustave. S druge strane, posljednjih godina pokazano je kako su upravljačke metode zasnovane na umjetnoj inteligenciji bitno uspješnije u primjenama upravljanja nelinearnim sustavima. U ovome radu razvijen je inteligentni regulator za upravljanje brzinom induktivnog motora s kombinacijom radijalne neuronske mreže (RBF) i strategije adaptivnog regulatora s referentnim modelom (MRAC). RBF je realiziran kako bi adaptivno kompenzirao nepoznatu nelinearnost u sustavu upravljanja. Tehnika indirektnog vektorskog upravljanja (IFOC) i metoda prostorno vektorske širinsko impulsne modulacije koje su široko korištene za induktivne motore visokih performansi preferirani su kao metode u ovome radu. Kako bi se prikazala pouzdanost tehnike upravljanja, predloženi adaptivni regulator ispitan je u različitih uvjetima rada i usporeeno je vladanje s obzirom na konvencionalni PI regulator. Rezultati pokazuju kako predloženi regulator očito pokazuje bolj...

Performance enhancement of multivariable model reference optimal adaptive motor speed controller using error-dependent hyperbolic gain functions

“…In order to deduce the authenticity of the selected Lyapunov function, its time-derivative is computed. The expression is given by (25).…”

“…Another robust approach to address the aforementioned problems is the utilization of model reference adaptive system (MRAS) that alters the system's performance by dynamically adjusting the parameters of the closed-loop speed controller, after every sampling interval [23,24]. The MRAS accomplishes this task by minimizing the error between the outputs of the reference model and the actual system, in real-time [25,26].…”