面向多工况设备故障诊断的改进灰色关联分析法
张江鹏，付云伟，吴纯治，郭鸿宇，杨文*
（中国西昌卫星发射中心 技术部，四川 西昌 615000）
摘要：针对传统灰色关联分析法不能直接应用于多工况设备故障诊断、不能进行关联度趋势分析、典型故障标准数据序列难以建立等缺点，提出了一种改进灰色关联分析方法。该方法根据设备控制参数区分不同工况，在不同工况下分别进行灰色关联分析；通过改进关联系数计算方法，使不同待检序列的灰色关联度具有可比较性，并据此提出了关联度趋势分析法；结合关联度趋势分析，使用关联度阈值对设备异常工作状态进行诊断，解决了典型故障标准数据序列难以建立的问题。以航天发射场常规推进剂加注泵气缚故障诊断为例，说明了该方法的具体应用步骤，结果表明了该方法的可行性和有效性。和传统方法比，该方法适用于多工况设备，能够进行关联度趋势分析，具有广泛的应用范围和较大的应用价值。
关键词：灰色关联分析；多工况；故障诊断
中图分类号：TP23 文献标志码：A doi：10.3969/j.issn.1006-0316.2023.06.010
文章编号：1006-0316 (2023) 06-0067-07
Improved Grey Correlation Analysis Method for Fault Diagnosis of Multi-mode Equipment
ZHANG Jiangpeng，FU Yunwei，WU Chunzhi，GUO Hongyu，YANG Wen
( Technical Department, Xichang Satellite Launch Center, Xichang 615000, China )
Abstract：Aiming at the shortcomings of the traditional grey relational analysis method, which cannot be directly applied to the fault diagnosis of multi-mode equipment, cannot be used for correlation trend analysis, and is difficult to establish a typical fault standard data sequence, an improved grey relational analysis method is proposed. The method distinguishes different working modes according to the equipment control parameters, and conducts grey correlation analysis under different working modes. By improving the calculation method of the correlation coefficient, the gray correlation degrees of different sequences to be tested are comparable, and based on this, a correlation trend analysis method is proposed. Combined with the trend analysis of the correlation degree, the abnormal working state of the equipment is diagnosed by using the correlation degree threshold, which solves the problem that the typical fault standard data sequence is difficult to establish.Taking the air-binding fault diagnosis of the conventional propellant filling pump in the space launch site as an example, the specific application steps of the method are explained, and the results show the feasibility and effectiveness of the method. Compared with the traditional method, this method is suitable for multi-mode equipment, can carry out correlation trend analysis, and has a wide range of applications and greater application value.
Key words：grey correlation analysis；multi-mode；fault diagnosis
———————————————
收稿日期：2022-06-14
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：251770353@qq.com。
*通讯作者：杨文（1981－），男，四川内江人，博士，高级工程师，主要研究方向为工业智能，E-mail：whutyw@126.com。
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