论文部分内容阅读
通过监控航空发动机性能参数,准确判断发动机的工作状态,预知发动机的异常变化,为预防和排除故障提供充足的时间和决策依据。开发出利用QAR(quick access recorder,快速存取记录器)数据的发动机故障检测系统,该系统基于民航发动机的QAR数据,由于发动机正常运行数据容易获取,而故障样本难以获得,因而采用单类支持向量机(OCSVM),仅依靠发动机的健康数据建立其分类器。利用OCSVM分类器,监控后续航班参数是否出现异常,通过分析检测结果,实现发动机故障检测。采用该系统监控航空发动机性能参数,及时发现发动机运行状态异常,证明了系统的可行性和有效性。
By monitoring the performance parameters of aeroengine, accurately judge the working status of the engine, predict abnormal changes of the engine, and provide sufficient time and decision-making basis for prevention and troubleshooting. Developed an engine fault detection system using QAR (Quick Access Recorder) data based on QAR data from civil aviation engines, using single-class support due to easy availability of engine normal operating data and difficult-to-obtain fault samples Vector machines (OCSVMs) build their classifier based solely on the health data of the engine. Using OCSVM classifier to monitor the follow-up flight parameters whether anomalies, by analyzing the test results, the engine fault detection. By using the system to monitor the performance parameters of aeroengines and discovering the anomalies of the engine operating conditions in time, the feasibility and effectiveness of the system are proved.