运载火箭测试数据分析与故障诊断方法
Data Analysis and Fault Diagnosis Methods for Launch Vehicles
汪灏 1陈卓 2杜璞玉 3彭炳锋 3罗滨鸿 3徐昕4
作者信息
- 1. 上海宇航系统工程研究所,上海 201109
- 2. 上海航天电子技术研究所,上海 201109;上海交通大学计算机科学与工程系,上海 200240
- 3. 上海航天电子技术研究所,上海 201109
- 4. 上海航天电子技术研究所,上海 201109;南京航空航天大学航天学院,南京 211106
- 折叠
摘要
针对如何从运载火箭大量历史测试发射数据中发掘有用信息的问题,提出了一种基于数据挖掘的运载火箭数据分析与故障诊断方法,为火箭的故障诊断、产品设计、状态检测提供服务;针对火箭数据的特性和实际业务分析的需求,使用基于皮尔逊系数的相关性分析方法、基于希尔伯特变换的包络分析方法、基于窗口滑动函数的故障诊断方法组建火箭数据分析平台,对运载火箭的数据进行了深层次的挖掘和诊断;采用某型号火箭测试数据对火箭数据分析平台进行了验证,结果表明:以数据驱动的火箭数据分析平台相关性分析准确、参数包络线绘制精准、可有效识别异常数据,分析结果与理论知识相符,具有较高的实用价值,相比于传统数据分析方法更为精准、全面.
Abstract
A data analysis and fault diagnosis method for launch vehicles based on data mining is proposed to explore useful infor-mation from a large amount of historical test launch data,providing services for rocket fault diagnosis,product design,and status de-tection.In view of the characteristics of rocket data and the needs of actual business analysis,the rocket data analysis platform is es-tablished by using the correlation analysis method based on Pearson coefficient,the envelope analysis method based on Hilbert trans-form,and the fault diagnosis method based on window sliding function,the deep-level exploration and diagnosis of launch vehicle data are achieved.The rocket data analysis platform is verified with the test data of a certain type of rocket.The results show that the data driven rocket data analysis platform provides accurate correlation analysis,the parameter envelope is accurately drawn,and the abnor-mal data is effectively identified.The analysis results are consistent with the theoretical knowledge,which has high practical value.Compared to traditional data analysis methods,it is more accurate and comprehensive.
关键词
火箭/故障诊断/数据分析/相关性/包络Key words
rocket/fault diagnosis/data analysis/correlation/envelope引用本文复制引用
出版年
2024
NETL
NSTL
万方数据