Based on particle swarm optimization BP network of selective harmonic elimination technique research

This paper presents a BP network based on improved particle swarm optimization to solve the selective harmonic elimination technique of switch angles. One of the difficulties of selective harmonic elimination technique is solving the switch angles, the traditional method has shortcomings such as initial value selection is difficult and the iterative process complex. Traditional BP algorithm also has shortcomings such as slow convergence speed and easy to fall into local weights. Use the improved particle swarm algorithm to optimize neural network´s weights, threshold and connection structure. Then use the trained network to solve SHEPWM switching angles. The simulation results show that the optimized BP network convergence rate increased significantly, and solving the switch angles accuracy is improved significantly.