Abstract
Pulse Width Modulation (PWM) inverters are of huge and great impact in many engineering disciplines. It plays a big role in the field of power electronics regarding voltage sources to vast amount of electronics equipments and machine controllers. The use of artificial intelligence in gate signals control in PWM voltage source inverter (VSI) is tackled, analyzed, and implemented in this paper. The PWM technique that investigated in this work is the Selective Harmonic Elimination (SHE). For this technique, the single phase H-bridge inverter is considered for the study. In the SHE based inverter, the fundamental voltage level and the harmonics selected for deletion are decided using a neural network ad fuzzy logics. For the SHE technique, the results of generating switching angle patterns, using the neural and the fuzzy model controllers, for driving H-bridge inverter, show almost exact resemblance, compared to those obtained using conventional controllers. Also the superiority at the intelligent models overcome the problem of delay time and have fast response in selecting and generating the PWM patterns required to regulate the inverter output voltage. Keywords: H-bridge inverter, Pulse Width Modulation, Selective Harmonic Elimination, Intelligent Techniques.
Highlights
In the past few decade the power electronics field witnessed a rapid growth in power semiconductors and digital techniques, which makes it possible to build systems with high efficiency, reliable and low cost
The intelligent methods which are mentioned in this paper are implemented on (SHE Pulse Width Modulation (PWM)) to achieve the function of control instead of using digital signal processing which needs large look-up tables to save large amount of information about the values of modulation index and their corresponding switching angles values, as a result it needs a large memory to obtain high resolution
It ca be concluded that: 1. From the simulation results using neural network package in MATLAB/SIMULINK program, it is found that the Mean Square Error (MSE) for the training process is small and this refers to the closeness of the calculated output sets to the target sets and makes the new circuit equivalent to the original circuit, and from the waveforms of the output voltage of the full-bridge inverter and their Fast Fourier Transform (FFT) spectrum like the results for the actual values
Summary
In the past few decade the power electronics field witnessed a rapid growth in power semiconductors and digital techniques, which makes it possible to build systems with high efficiency, reliable and low cost. The most effective method is the PWM that has ability to regulate the magnitude and frequency of inverter output voltage, and eliminating or minimizing significant harmonic components of the output voltage This kind of VSI, based on PWM method, can be performed using different types of strategies. In order to obtain PWM patterns, number of nonlinear equations in terms of unknown switching angles, depend on number of harmonic components to be eliminated, have to be solved for each value of modulation index using numerical minimization approach. These can be achieved in off line and stored as look up tables. To obtain the amplitude of each harmonic content, Fourier series is applied, and the final result is given as [4]:
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
