This paper presents the implementation of selective harmonic elimination (SHE) in a five-level inverter structure using artificial neural networks (ANNs). SHE is an effective low-frequency modulation technique to eliminate selected harmonics and control multilevel converters. The use of ANN-SHE requires the calculation of the optimum values of switching angles via the solving system of nonlinear equations for the total harmonic distortion (THD) reduction, where the nonlinear equations are founded by the complex Fourier series analysis of the inverter output voltage. The procured switching angle values are directly implemented by a multilayer perceptron (MLP) algorithm without a lookup table. The ANN model is obtained by training the neural network (NN), taking the modulation index (M) as an input and approximating switching angles as an output. A thorough analysis was carried out to show the programming steps of the proposed ANN-based SHE using Matlab/ Simulink environment. A realized inverter prototype steered by the proposed ANN-based SHE was tested with various modulation indexes on a real-time mode using a digital signal processor (DSP) C2000 Delfino-TMS320F28379Dembedded board. A comparison between the simulation results and the experimental data is presented. The obtained results illustrate that the experimental results match the simulation closely, and the ANN model provides a fast and precise estimate of the switching angles for each value of the modulation index.

No abstract

No abstract

No abstract

This paper explains the implementation of a small-signal model for a new five-level series resonant inverter structure. The proposed circuit combines the advantages of multilevel inverters and the characteristics of the physical phenomena, resonance. The small-signal model offers the possibility to design a linearized linear time-invariant (LTI) model around an equilibrium point based on first order Taylor series. After that, the performance of the proposed five-level series resonant inverter and its smallsignal model are evaluated in MATLAB/Simulink environment. Compared with a MATLAB model generated using the system identification toolbox, the developed small-signal model exhibited a good accuracy in frequency and time domains. In addition, a hardware test bench is developed to validate the proposed model. Both simulation and experimental results shows that the proposed multilevel resonant inverter is very interesting for high-voltage high-frequency applications. As a perspective, from the results obtained, we suggest the use of small-signal AC analysis for multilevel series resonant inverter modeling. The paper contains rich information of the recently used tools for dynamic systems modeling and analysis of nonlinear processes that can be applied for the modeling and analysis of other power electronics inverters.INDEX TERMS AC analysis of dynamic nonlinear system, five-level series resonant inverter, inverter mathematical model, multilevel inverter simulation, model of inverter, small-signal modeling.