风力发电变频水泵智能控制策略研究

Research of Intelligent Control Strategy for Variable Frequency Pump Based on Wind Power Generation

针对风力发电机和逆变器的特点,给出了风能变频水泵的两输入两输出耦合系统时变模型结构。保持逆变器输入电压恒定的前提下,扰动逆变器输出交流电的频率来实现风力发电机的最大功率跟踪。根据解耦和神经网络的思想,采用两个回归神经网络(DRNN)在线调整两个PID控制器的参数,一个神经元解耦补偿器完成系统的解耦,实现了不依赖于对象模型的自适应PID解耦控制。计算机仿真结果验证了该控制策略可行性,这为以后进一步研究奠定了基础。

Aiming at characteristics of wind driven generator and inverter,a model structure of wind power variable frequency pump was proposed,which was a coupling system of two input and two output.Maximum power tracking of wind power generation would be achieved by disturbing output frequency of Alternating Current(AC)of inverter,while holding input voltage of inverter be constant.Based on the principle of decoupling and recurrent neural network,two Diagonal Recurrent Neural Network(DRNN)was adopted to adjust the parameters of two PID controllers on - time,and one nerve cell decouple compensator was adopted for decoupling the system,which implementing non-model adaptive decouple PID control.Finally,validity of proposed control strategy was revealed via computer simulations,and it would be foundation for more study.