摘要
在软开关谐振功率变换器系统中,由于增加了谐振元件以及系统本身存在的严重的非线性和时变不确定性等特点,极大地影响了系统输出电压的动态响应性能。针对这一问题,该文提出了一种新的控制策略,将基于PID的神经网络控制器,用于脉宽调制型的软开关谐振功率变换器中,提高系统的动态响应性能。这种控制器是一种新型的误差前向反馈神经网络,将神经网络和PID控制规律融为一体,利用M atlab6.5软件中的电力系统仿真模块(S imPowerSystem s)对该系统进行仿真,结果表明这种控制方法可以使得功率变换器获得较好的动态性能。
In the soft switch resonant converter systems, because of the strong non - linearity of the systems themselves and the addition of the resonant components, their dynamic properties of output voltage are seriously affected. To solve this problem, this paper presents a new control strategy that is used to PWM soft switch resonant converter. This controller based on neural network is a novel error forward propagation feedback neural network, and combines the neural net work with the PID controller regulation. Based on the Power System Simulation Blocksets （SimPowerSystems） of Matlab6.5,the simulation results confirm that this new controller can improve the dynamic properties of the power converter.
出处
《计算机仿真》
CSCD
2006年第2期279-282,共4页
Computer Simulation
