基于多工况自动聚类的飞机发动机健康状态评估  

Aircraft Engine Health Condition Assessment Based on Multi Condition Automatic Clustering

作　　者：施浩[1,2] 黄亦翔[1] 刘成良[1] 

机构地区：[1]上海交通大学机械与动力工程学院,上海200240 [2]上海工程技术大学航空运输学院,上海201620

出　　处：《机电一体化》2016年第11期39-43,共5页Mechatronics

基　　金：国家科技支撑计划(2014BAA04B01);国家自然科学基金(51305258);上海市科委项目(1411104600)

摘　　要：提出了一种基于多工况聚类的飞机发动机健康状态评估方法。首先对工况进行自动划分;再从大量传感器数据中选取与发动机性能衰退趋势密切相关的传感器变量进行分析并提取特征,定义逻辑回归模型;最后给出对飞机发动机的健康状态评价。该方法在NASA提供的飞机发动机传感器数据上进行验证,对其健康性能状态进行评估,结果表明该方法不仅结果可靠,而且具有一定实用性,可为飞机发动机的剩余使用寿命预测提供一种可行且有效的理论方法和手段,对提高飞机发动机的安全性和可靠性具有重要价值。This paper presents a health evaluation method based on automatic clustering of the aircraft engine conditions. Firstly,from a large number of sensor data,the sensor variables closely related to the engine performance deterioration trend are selected for analysis and feature extraction. Secondly,the logistic model is defined to evaluate the aircraft engine health condition. Finally,the method for evaluating the performance of the engine health status is validated on the aircraft engine sensor data through a NASA verification procedure. The results show that the method is not only effective,but also practical for the aircraft. The accurate prediction of the remaining useful life of the engine has important value to improve the safety and reliability of aircraft engine.

关 键 词：健康评估 飞机发动机 自动工况划分 逻辑回归模型 K-MEANS聚类 

分 类 号：V263.6[航空宇航科学与技术—航空宇航制造工程]