基于RBF神经网络的进气压力控制方法研究

Intake Pressure Control Method Based on RBF

针对高空台进气压力控制系统的强非线性特性和被控对象难以精确建模的问题,传统的PID控制在被试发动机进行加减速等过渡态时难以满足进气压力控制性能要求,提出了基于数据驱动的高空台压力控制方法,设计了基于RBF(Radial Basis Function,径向基函数)神经网络的最优控制架构,通过分析进气压力控制系统的输入和输出,给出了进气压力控制系统的RBF神经网络控制方法;利用高空台的大量试验数据对所设计的控制方法进行了训练和测试。测试结果表明,所设计的智能控制方法有良好的控制性能,能够满足进气压力的过渡态自适应控制。

Because of the strong nonlinear characteristics of the air inlet pressure control system of the altitude platform and the difficulty in modelling the controlled object accurately,the traditional PID control is difficult to meet the performance requirements of the pressure control when the engine is in the transition state.The pressure control method of altitude platform based on data driving is proposed.The optimal control architecture based on RBF(Radial Basis Function)neural network is designed,and the RBF neural network model is built by analyzing the input and output of the intake pressure control system.The control method is trained and tested by using a large number of test data of the altitude platform.The test results show that the designed intelligent control method has good control performance and can meet the transitional adaptive control of intake pressure.