出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Direct torque control (DTC) is preferably control method on high performance control ofinduction motors due to its advantages such as fast dynamic response, simple and robust controlstructure. However, high torque and current ripples are mostly faced problems in this controlmethod. This paper presents artificial neural network (ANN) based approach to the DTCmethod to overcome mentioned problems. In the study, by taking a different perspective to ANNand DTC integration, two different ANN models have been designed, trained and implemented.The first ANN model has been used for switch selecting process and the second one has beenused for sector determine process. Matlab/Simulink model of the proposed ANN based DTCmethod has created in order to compare with the conventional DTC and the proposed DTCmethods. The simulation studies have proved that the induction motor torque and currentripples have been reduced remarkably with the proposed method and this approach can be agood alternative to the conventional DTC method for induction motor control.
关键词：Direct torque control; Induction motor control; Artificial neural networks; Vector control
