中文摘要：

为实现航空发动机在巡航过程中的实时监控及时发现N2参数的异常变化,提高飞行安全水平,提出一种航空发动机N2基线的建模算法,通过基线可进一步求得N2的偏差值,进而对航空发动机进行实时性能监视.依据设定的飞行数据筛选原则和预处理方法建立模型样本,设计以高斯函数为隐含层激励函数和以线性函数为输出层激励函数的多输入单输出的RBF神经网络,通过Pearson相关性分析确定网络的输入节点,使用该网络得到预测N2基线.最后对预测偏差值和观测偏差值实施两配对非参数检验以验证网络精度,结果表明该方法是计算航空发动机巡航状态下N2基线的一种有效算法.

英文摘要：

For achieving real-time monitoring for the aero-engine during cruise phase,it promptly catches abnormal shift of aero-engine N2 parameters and improves flight safety level,and proposed a calculation method of the N2 baseline for the N2 shift value further and then implements real-time performance monitoring for aero-engine.According to given data screening rules and pre-processing methods,builts the model sample.Designes the multi-input and single-output RBF neural network with the Gaussian function selected as hidden layer transfer function and the Linear function selected as ouput layer transfer function,and input nodes are confirmed by Pearson correlation analysis.The predicted baseline is gotten by this mode.Finally,does two-sample masched-pairs nonparametric tests for observed values and predictes values to verify network accuracy.The results indicate that this method is an effective approach for calculating the N2 baseline of the aero-engine during cruise.