Sensorless current prediction in single phase inverter circuits with machine learning algorithms

Authors : Hüseyin TÜRE, Selami BALCI, Kadir SABANCI, Muhammet Fatih ASLAN

Pages : 221-230

Doi:10.30521/jes.932581

View : 17 | Download : 10

Publication Date : 2021-09-30

Article Type : Research Paper

Abstract :Inverter circuits are widely used in power electronics applications such as electric motor control, induction heating or different Alternating Current insert ignore into journalissuearticles values(AC); loads. The control signal applied to the switching elements can affect the quality of the sinusoidal signal that occurs at the output of the inverter circuit by the means of voltage and current values. The inverter circuit topologies are generally designed as closed loop. However, these cause complexity of the circuit topology, increase the production costs and give difficulties in designing the control signals. In the present work, simulations of a single-phase inverter circuit with the Sinusoidal Pulse Width Modulation insert ignore into journalissuearticles values(SPWM); control signal are performed. Thus, the effect of the SPWM signals on the output of the inverter has been observed by changing the Modulation rate insert ignore into journalissuearticles values(M);, the carrier signal frequency insert ignore into journalissuearticles values(f_c); and the reference signal frequency insert ignore into journalissuearticles values(f_r);. Through the data obtained, the output current of a phase inverter without a sensor is estimated by Machine Learning Algorithms insert ignore into journalissuearticles values(MLA); such as Multi-Layer Perceptron insert ignore into journalissuearticles values(MLP);, Support Vector Machine insert ignore into journalissuearticles values(SVM); and K-Nearest Neighbors insert ignore into journalissuearticles values(KNN);.
Keywords : Inverter circuit, Machine learning algorithms, Sensorless control, Parameter estimating