基于DPCA与LSSVM的飞机发动机异常状态识别

Aircraft Engine Fault Diagnosis Based on DPCA and LSSVM

摘要:

针对飞机发动机异常状态识别精度差、效率低和易误诊漏诊等问题,提出了一种基于动态主元分析 (Dynamic Principal Component Analysis, DPCA)和最小二乘支持向量机(Least Square Support Vector Machine, LSSVM)的飞机发动机润滑系统异常状态识别方法。首先对发动机润滑系统参数进行DPCA处理以及在线检测是否有故障发生,如果有故障发生,再采用LSSVM方法进行异常状态识别。以某型飞机发动机润滑系统为例,对文中所提方法的准确性进行试验验证,由试验结果得出文中方法能有效提高飞机发动机异常状态识别准确率。

Abstract:

In view of the problems such as low accuracy, low efficiency and easy to misdiagnosis and missed diagnosis for aircraft engine fault diagnosis, an intelligent method of aircraft engine lubricating system fault diagnosis is presented. It is based on the Dynamic Principal Component Analysis (DPCA) method and the Least Square Support Vector Machine (LSSVM) method. At first, the DPCA method is employed to preprocess the lubricating system variables and detect whether there is a fault online. If there is a fault, the LSSVM method is used to state recognition. Then, the lubricating system of a certain type of aircraft engine is taken as an instance to verify the validity of the proposed method. Results show that the method can effectively improve the accuracy of fault diagnosis.