Research on harmonic detection method based on BP neural network used in induction motor controller

摘要

Harmonic currents in a motor controller not only increase the loss of the motor but also reduce the efficiency of the motor. Harmonic detection is the precondition of harmonic control. General harmonic detecting scheme uses the Fast Fourier Transform (FFT) to detect all the harmonics. In the motor control, we often do not care about the specific values of all the harmonics, but only some key harmonics or several overall indicators. For the above reasons, the harmonic detecting scheme based on back propagation (BP) neural network is proposed. In this paper, the analysis of BP and FFT algorithm is presented, and the results of BP and FFT are compared. It is easy to see the superiority of the BP neural network in terms of calculation. The simulation results of the motor harmonic detection validate that the BP neural network scheme is feasible, and the BP neural network detecting accuracy is close to FFT.