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

作　　者：乔彦平 郭迎清[1] 高红岗 QIAO Yanping;GUO Yingqing;GAO Honggang(School of Power and Energy,Northwestern Polytechnical University,Xi'an 710072,China;Science and Technology on Altitude Simulation Laboratory,AECC Sichuan Gas Turbine Establishment,Mianyang 621700,China;School of Civil Aviation,Northwestern Polytechnical University,Xi'an 710072,China)

机构地区：[1]西北工业大学动力与能源学院,陕西西安710072 [2]中国航发四川燃气涡轮研究院高空模拟技术重点实验室,四川绵阳621700 [3]西北工业大学民航学院,陕西西安710072

出　　处：《测控技术》2024年第2期11-16,共6页Measurement & Control Technology

基　　金：国家稳定支持课题项目(GJCZ-0032-19)。

摘　　要：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.

关 键 词：高空台 压力控制 智能控制 自适应控制 RBF神经网络 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论] V23[自动化与计算机技术—计算机科学与技术]