Online-Trained Radial Basis Function Neural Network Compensator for Current Harmonics Suppression of Electric Drives
Chenhao Zhao, Yuefei Zuo, Huanzhi Wang, Christopher H. T. Lee
Abstract
The extended state observer (ESO)-based deadbeat active disturbance rejection control (DB-ADRC) is commonly employed for high-performance torque or current control, however, it performs poorly when rejecting current harmonics caused by periodic disturbances, such as inverter nonlinearities and flux harmonics. The internal model-based method, such as resonant control, can be combined with ESO to mitigate current ripples when the harmonic frequencies are known, which however is not always the case in real applications. In this article, an online-trained radial basis function neural network (RBFNN) compensator with fast training process is integrated into the DB-ADRC system to simultaneously suppress the aperiodic and harmonic disturbances without knowing harmonic frequencies. By using the proposed scheme, current harmonics under various speed and load conditions can be effectively suppressed without affecting dynamic performance. Various experiments are conducted on the test bench based on the dSPACE MicroLabBox and permanentmagnet synchronous motor to validate the effectiveness of the proposed method.