神经网络控制与电流模式控制的性能比较研究

Research on Performance Comparison between Neural Network Control and Current Mode Control

AC/DC开关变换器非线性程度很高,输入电流为非正弦形式,功率因数极低。为改善功率因数,对神经网络控制器(NNC)与电流模式控制器(CMC)的控制效果进行了仿真比较研究。结果证实,使用神经网络控制器可以获得很高的功率因数;在参数变化时,神经网络控制器比电流模式控制器的性能更佳,且容错能力异常突出。相比之下,神经网络控制器的性能优于电流模式控制器。

AC/DC switching converters are highly nonlinear. Therefore they draw a non-sinusoidal current with a very low power factor. For the purpose to correct the power factor, we researched the controlling effect of both neural network controller（NNC） and current mode controller（CMC）. And comparisons are made between the simulation results of the NNC and those of the CMC. The results demonstrate that using NNC could achieve high power factor. The NN controllers perform better with parameter variations compared to the CMC. The fault tolerance capability of the NNC shows excellent results. The NNC excel CMC in integrated performance.