基于灰色关联度趋势分析的加注泵异常监测
张江鹏1,2，李增光2，徐绯然2，田波2，陈浩*,1
（1.国防科技大学 电子科学学院，湖南 长沙 410073；2.中国西昌卫星发射中心 技术部，四川 西昌 615000）
摘要：加注泵是航天发射场的关键设备，其工作异常监测对于航天发射任务的成功与否有十分重要的影响。因此，以灰色关联度趋势分析法为基础，建立了一种加注泵灰色关联度偏离指数模型，用以进行加注泵工作状态的异常监测。该模型采用回归拟合的方法建立灰色关联度标准数据序列，解决了加注泵因过渡工况数据样本少、数据波动较大造成的标准数据序列代表性不够、误差较大的问题；通过考察灰色关联度偏离强度累积效应，建立了灰色关联度偏离指数，解决了加注泵状态参数波动大导致异常诊断误判率较高的问题。以航天发射场常规推进剂加注泵为对象，说明了该模型的具体构建及应用步骤。应用结果表明，该改进模型能够提高异常监测的准确性、有效降低误判率，可以为加注泵异常监测提供重要的科学判据。
关键词：加注泵；异常监测；灰色关联度
中图分类号：TP23 文献标志码：A doi：10.3969/j.issn.1006-0316.2024.06.011
文章编号：1006-0316 (2024) 06-0075-06
Anomaly Monitoring of Filling Pump Based on Grey Correlation Degree Trend Analysis
ZHANG Jiangpeng1,2，LI Zengguang2，XU Feiran2，TIAN Bo2，CHEN Hao1
( 1.College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China; 2. Technical Department, Xichang Satellite Launch Center, Xichang 615000, China )
Abstract：The filling pump is a key equipment of the space launch site, and its anomaly monitoring is crucial for the successful completion of the space launch mission. Based on the trend analysis method of grey correlation degree, a deviation index model of grey correlation degree for filling pumps is established for the anomaly monitoring of the filling pumps. This model uses the regression fitting method to establish a grey correlation degree standard data sequence, which solves the problem of insufficient representativeness and large errors in the standard data sequence caused by the small number of samples and large data fluctuations in the transitional working conditions of the filling pump. By examining the cumulative effect of grey correlation degree deviation intensity, a grey correlation degree deviation index is established to solve the problem of high misdiagnosis rate caused by large fluctuations in the state parameters of the filling pump. The specific construction and application steps of the model are explained taking the conventional propellant filling pump at the space launch site as the object. The application results indicate that the improved model can improve the accuracy of anomaly monitoring and effectively reduce the rate of false positives, providing important scientific criteria for the anomaly monitoring of filling pumps.
Key words：filling pump；anomaly monitoring；grey correlation degree
———————————————
收稿日期：2023-07-17
作者简介：张江鹏（1986－），男，陕西彬州人，硕士研究生，工程师，主要研究方向为工业智能、工业大数据分析，E-mail：cbener@163.com。
*通讯作者：陈浩（1982－），男，湖南长沙人，博士，教授，主要研究方向为计算智能、机器学习，E-mail：hchen@nudt.edu.cn。
（1.国防科技大学 电子科学学院，湖南 长沙 410073；2.中国西昌卫星发射中心 技术部，四川 西昌 615000）
摘要：加注泵是航天发射场的关键设备，其工作异常监测对于航天发射任务的成功与否有十分重要的影响。因此，以灰色关联度趋势分析法为基础，建立了一种加注泵灰色关联度偏离指数模型，用以进行加注泵工作状态的异常监测。该模型采用回归拟合的方法建立灰色关联度标准数据序列，解决了加注泵因过渡工况数据样本少、数据波动较大造成的标准数据序列代表性不够、误差较大的问题；通过考察灰色关联度偏离强度累积效应，建立了灰色关联度偏离指数，解决了加注泵状态参数波动大导致异常诊断误判率较高的问题。以航天发射场常规推进剂加注泵为对象，说明了该模型的具体构建及应用步骤。应用结果表明，该改进模型能够提高异常监测的准确性、有效降低误判率，可以为加注泵异常监测提供重要的科学判据。
关键词：加注泵；异常监测；灰色关联度
中图分类号：TP23 文献标志码：A doi：10.3969/j.issn.1006-0316.2024.06.011
文章编号：1006-0316 (2024) 06-0075-06
Anomaly Monitoring of Filling Pump Based on Grey Correlation Degree Trend Analysis
ZHANG Jiangpeng1,2，LI Zengguang2，XU Feiran2，TIAN Bo2，CHEN Hao1
( 1.College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China; 2. Technical Department, Xichang Satellite Launch Center, Xichang 615000, China )
Abstract：The filling pump is a key equipment of the space launch site, and its anomaly monitoring is crucial for the successful completion of the space launch mission. Based on the trend analysis method of grey correlation degree, a deviation index model of grey correlation degree for filling pumps is established for the anomaly monitoring of the filling pumps. This model uses the regression fitting method to establish a grey correlation degree standard data sequence, which solves the problem of insufficient representativeness and large errors in the standard data sequence caused by the small number of samples and large data fluctuations in the transitional working conditions of the filling pump. By examining the cumulative effect of grey correlation degree deviation intensity, a grey correlation degree deviation index is established to solve the problem of high misdiagnosis rate caused by large fluctuations in the state parameters of the filling pump. The specific construction and application steps of the model are explained taking the conventional propellant filling pump at the space launch site as the object. The application results indicate that the improved model can improve the accuracy of anomaly monitoring and effectively reduce the rate of false positives, providing important scientific criteria for the anomaly monitoring of filling pumps.
Key words：filling pump；anomaly monitoring；grey correlation degree
———————————————
收稿日期：2023-07-17
作者简介：张江鹏（1986－），男，陕西彬州人，硕士研究生，工程师，主要研究方向为工业智能、工业大数据分析，E-mail：cbener@163.com。
*通讯作者：陈浩（1982－），男，湖南长沙人，博士，教授，主要研究方向为计算智能、机器学习，E-mail：hchen@nudt.edu.cn。
设为首页 | 加入收藏 | 免责条款
《机械》杂志版权所有 Copyright©2008-2012 Jixiezazhi.com All Rights Reserved
电话：028-85925070 传真：028-85925073 E-mail：jixie@vip.163.com
地址：四川省成都锦江工业开发区墨香路48号 邮编：610063
Powered by PageAdmin CMS