基于信息熵融合提取特征的发动机气路分析.pdfVIP

学兔兔 第33卷 第1期 仪 器 仪 表 学 报 Vol|33 No．1 2012年1月 Chinese Journal of Scientific Instrument Jan．2012 基于信息熵融合提取特征的发动机气路分析术 鲁 峰，黄金泉，仇小杰，邢耀东 (南京航空航天大学能源与动力学院 南京 210016) 摘 要：针对航空发动机多源信息冗余的健康参数估计问题，提出基于信息熵融合的特征提取方法，将其用于涡轴发动机气路 分析中。分别采用近似熵和互信息熵2种方法分析不同故障模式下传感器参数，对特征信息进行融合提取，根据2种信息熵不 同特点将每种故障模式下传感器参数分成强、弱2类，利用弱特征信号构建虚拟传感器，最后通过简约强特征信息和虚拟传感 器信息解决最小二乘支持向量回归机的样本稀疏性问题，实现健康参数蜕化估计。仿真结果表明采用信息熵融合的特征提取 方法有效地减少了输入参数维数，简约了特征样本，从而提高了发动机健康估计能力。 关键词：涡轴发动机；气路分析；信息融合；信息熵；特征提取；最小二乘支持向量机 中图分类号：V233 文献标识码：A 国家标准学科分类代码：590．25 Feature extraction based on information entropy fusion for turbo--shaft engine gas--path analysis Lu Feng，Huang Jinquan，Qiu Xiaojie，Xing Yaodong (College of Energy and Power Engineering，Nanjing University ofAeronautics and Astronautics，Na ng 210016，China) Abstract：Aiming at the problem of health parameter estimation of aero-engine with multi-source information，a hy- brid diagnosis method based on feature extraction of information entropy is proposed．Because of the information re- dundancy in different types of measurements for fault diagnosis，the feature under each fault mode is extracted and divided into strong relative characteristic signal and weak one，and the weak one is used to set up virtual sensor； then sparse least squares support vector regression is used to estimate the degradation of health parameter according to the two classes of information．Simulation result on some turbo-shaft engines shows that the method can effectively reduce the characteristic parameters，decrease the input dimension and simplify the training samples for the health estimation． Key words：turbo—shaft engine；gas·path analysis；information fusion；informa