Research on Selective Harmonic Elimination Technique based on Particle Swarm Optimization

Harmonic elimination of multilevel inverters is a complicated optimization issue involving constrained nonlinear transcendental equations with multiple solutions. A method to the selective harmonic elimination (SHE) technique by applying a particle swarm optimization (PSO) based on varied inertia weight in the iterative procedure is presented in this paper, which can avoid falling into the local optimum and improve the algorithm robustness so as to acquire the global optimum of the solution space. The proposed scheme can quickly obtain diverse solutions of switching patterns, while it is hard to determine them through conventional approaches like iterative techniques and resultant theory. Here, considering the elimination of low-order harmonics, these switching angles are calculated offline by computer. Theoretical results are analyzed and verified by simulations for a three-level neutral point clamped (3L-NPC) inverter. Simulation results show that the above mentioned approach effectively eliminates the specified lower order harmonics, whereas the switching angle trajectory and total harmonic distortion (THD) of output voltage are different.