Abstract: It is not only very essential for control system design but also for failure detection and diagnosis to set up a real time, precise and reliable dynamic model of liquid propellant rocket’s propulsion system. The feed forward neural network if successfully trained, can map the inputs to the desired outputs, so recent years have seen an extensive amount of research to explore its approximation properties. On the basis of studying RBF (Radial Basis Function) neural networks’ theory and system mechanism, a nonlinear dynamic neural networks’ model with multi inputs and multi outputs for liquid propellant rocket’s propulsion system was built. During the modeling, necessary dynamic information was included and parameters of model were also well chosen. The contrastive results of outputs of the model and measuring data of one real test firing demonstrates that the model is of many advantages, such as short computational time, better real time property and good precision. The model is very well fit for the applications of real time condition monitoring, fault diagnosis and control system design of liquid propellant rocket’s propulsion system.

Key words: Liquid propellant rocket engine;Propulsion system;Nonlinearity;Artificial neural metwork;Dynamic mod

摘要： 为了获得实时、准确、可靠的液体火箭推进系统非线性动态模型 ,使其适用于控制系统的设计和故障检测与诊断 ,基于RBF (RadialBasisFunction)神经网络理论和系统工作机理 ,综合考虑了系统的动态信息 ,适当选择了输入输出参数 ,建立了一种多输入多输出的液体火箭推进系统非线性动态模型。模型的输出与实际试车结果的对比分析表明 ,模型的计算时间短、实时性强、精度高 ,可用于液体火箭推进系统的实时状态监控、故障诊断及控制系统设计等。

关键词: 动态模型;神经网络;液体推进剂火箭发动机;推进系统;非线性;人工神经元网络