三相变流器的模糊PI神经网络控制研究

Research on Hybrid Fuzzy-PI Neural Networks Control for Three Phase Voltage Converters

提出了一种神经网络电流内环控制加混合模糊PI电压外环控制的双环控制结构。对三相电压型可逆变流器系统而言,神经网络电流内环控制使系统具有更强的鲁棒性,混合模糊PI电压外环控制加快了系统的响应速度。为了增强系统的抗扰性能还引入了电流前馈控制。最后通过仿真及试验验证了控制方案的正确性与可行性。

This paper presents a new dual-loop control structure, with a neural network current as the inner-loop and a hybrid fuzzy-PI voltage as the outer-loop. For three-phase voltage converter system, the neural network current inner-loop makes the whole system more robust, and the hybrid fuzzy-PI voltage out-loop enhances the responsiveness of three-phase voltage converter system. In order to improve the anti-interference of system, the current feed-forward compensator is put into three-phase voltage converter system. Finally, the feasibility of this method is verified by the results of simulation and experimentation.