The SVM suffers from the complex computational processes. Therefore, this paper presents a new space vector modulation controller based soft computing-high accuracy implementation of artificial neural network. An artificial neural network (ANN) structure is proposed to identify and estimated the conventional SVM for avoiding the complex computational problem and hence improve the performance of the photovoltaic inverter generation. The ANN model receives the αβ voltages information at the input side and generates the duty ratios (Ta, Tb, and Tc) as an output. | ISSN:2249-5789 Hussein Mutlag, International Journal of Computer Science & Communication Networks,Vol 7(1),1-16 A New Switching Controller Based Soft Computing-High Accuracy Implementation of Artificial Neural Network Dr. Ammar Hussein Mutlag, Siraj Qays Mahdi, Omar Nameer Mohammed Salim Department of Computer Engineering Techniques, Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq. ammar_alqiesy@, siraj_qays@, omarnamer2005@ Abstract Space vector modulation (SVM) controller generation. The ANN model receives the αβ is an advanced computation intensive pulse voltages information at the input side and width modulation (PWM) technique. System generates the duty ratios (Ta, Tb, and Tc) as performance by an output. The training data for ANN is applying a proper switching technique. To generated by simulating the conventional obtain a sinusoidal AC output waveform, the SVM. The total harmonic distortion (THD) SVM switching technique is widely used rate with ANN and conventional based SVM and implemented in the inverter control methods algorithm By namely root mean square error (RMSE), controlling the inverter switching scheme, mean absolute error (MAE), and mean error the harmonic content of the output voltage (ME) can be minimized. The SVM suffers from performance of the proposed ANN model. the Moreover, can to complex be reduce accomplished harmonics. computational processes. are are presented. used to statistical Three indices assessment analysis the using Therefore, this paper presents a new space histogram method is presented as well for vector modulation controller based soft further evaluating. The results show that the computing-high accuracy implementation of proposed ANN model is significantly robust artificial neural network. An artificial neural to realize a favorable response compared network (ANN) structure is proposed .
