基于异类信息融合的齿轮健康评估方法

摘要
图/表
参考文献(11)
相关文章 (15)

全文: PDF (2198 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对齿轮传统健康评估方法中特征描述单一，齿轮箱中多种参数信息未能有效利用的问题，为更准确地监测齿轮运行的健康状况，提出一种基于异类特征信息融合的齿轮健康评估方法。对前期正常状态运行的齿轮采集振动、油液、铁谱等多种信号并提取特征指标，建立各类特征的模糊C均值聚类中心；利用模糊理论输出待测信号对于正常状态信号的隶属度作为各类特征的健康评估指标；以隶属度构造基本概率赋值函数，应用D-S证据理论组合规则，在决策层进行异类信息融合，从而完成齿轮的健康评估。通过对齿轮全寿命试验的数据处理与对比分析，证明该方法能够有效地评估齿轮健康状况。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈俊康1
	陈小虎1
	郑东辉2

关键词 ：异类信息融合, 模糊C均值, D-S证据理论, 健康评估, 齿轮

Abstract：Aiming at problems in gear traditional health assessment of feature description being unitary and information of many parameters in gear box being not used effectively, a gear health assessment method based on heterogeneous information fusion was proposed to more correctly monitor gear health during operation.Firstly, various signals including vibration, oil fluid and ferrography, etc.were collected and their feature indexes were extracted for a gear in early normal operation state, and the fuzzy C-means (FCM) clustering center was established for each kind of features.Secondly, the fuzzy theory was used to output the membership degree of the signal to be measured to the normal state signal as the health assessment index of various kinds of features.Finally, the membership degree was used to construct the basic probability assignment function, and the combined rules of Dempster-shafer (DS) evidence theory was adopted to perform heterogeneous information fusion at the decision-making level to complete a gear’s health assessment.The effectiveness of the proposed method was verified through data processing and contrastive analysis for gear whole life tests.

Key words： heterogeneous information fusion fuzzy C-mean (FCM) DS evidence theory health assessment gear

收稿日期: 2018-09-06 出版日期: 2020-01-28

引用本文:

陈俊康1，陈小虎1，郑东辉2. 基于异类信息融合的齿轮健康评估方法[J]. 振动与冲击, 2020, 39(3): 219-226.
CHEN Junkang1, CHEN Xiaohu1, ZHENG Donghui2. Gear health assessment method based on heterogeneous information fusion. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(3): 219-226.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2020/V39/I3/219

[1] 潘玉娜. 滚动轴承的性能退化特征提取及评估方法研究[D]. 上海交通大学, 2011.
PAN Yuna. Study on Feature Extraction and Assessment Method of Rolling Element Bearing Performance Degradation [D]. Shanghai Jiaotong University, 2011.
[2] 王宝祥, 潘宏侠, 杨卫. 滚动轴承的状态监测与性能退化评估[J]. 中国工程机械学报, 2017, 15(1):72-76.
WANG Baoxiang, PAN Hongxia, YANG Wei. Condition monitoring and performance degradation assessment on rolling bearings [J]. Chinese Journal of Construction Machinery, 2017, 15(1):72-76.
[3] 季云, 王恒, 朱龙彪,等. 基于DPMM-CHMM的机械设备性能退化评估研究[J]. 振动与冲击, 2017(23):170-174.
JI Yun, WANG Heng, ZHU Longbiao, LIU Xiao. Performance degradation assessment for mechanical equipment based on DPMM-CHMM [J]. Journal of Vibration and Shock, 2017(23):170-174.
[4] 阙子俊, 金晓航, 孙毅. 基于UKF的轴承剩余寿命预测方法研究[J]. 仪器仪表学报, 2016, 37(9):2036-2043.
QUE Zijun, JIN Xiaohang, SUN Yi. Ｒemaining useful life prediction forbearings with the unscentedKalman filter-based approach [J]. Chinese Journal of Scientific Instrument, 2016, 37(9):2036-2043.
[5] 潘泉, 王增福, 梁彦,等. 信息融合理论的基本方法与进展（II）[J]. 控制理论与应用, 2012, 29(10):599-615.
PAN Quan, WANG Zengfu, LIANG Yan. Basic methods and progress of information fusion (Ⅱ) [J]. Control Theory & Applications, 2012, 29(10):599-615.
[6] 周建民, 徐清瑶, 张龙,等. 基于小波包Tsallis熵和FCM的滚动轴承性能退化评估[J]. 机械传动, 2016(5):110-115.
ZHOU Jianming, XU Qingyao, ZHANG Long. Ｒolling Bearing Performance Degradation Assessmentbased on the Wavelet Packet Tsallis Entropy and FCM [J]. Mechanical tranmission, 2016(5):110-115.
[7] 彭毅. 基于振动和油液信息融合的发动机故障诊断方法研究[D]. 广西大学, 2014.
PENG Yi. Fault diagnosis method research of engine based on vibration and oil information fusion [D]. Guangxi University, 2014.
[8] 刘韬. 基于隐马尔可夫模型与信息融合的设备故障诊断与性能退化评估研究[D]. 上海交通大学, 2014.
LIU Tao. Study of Hidden Markov Model and Information Fusion in Equipment Fault Diagnosis and Performance Degradation Assessment [D]. Shanghai Jiaotong University, 2014.
[9] 潘玉娜, 陈进, 李兴林. 基于模糊c-均值的设备性能退化评估方法[J]. 上海交通大学学报, 2009(11):1794-1797.
PAN Yuna, CHEN Jin, LI Xinglin. Fuzzy c-Means Based Equipment Performance Degradation Assessment [J]. Journal of Shanghai Jiaotong University, 2009(11):1794-1797.
[10] Gong M, Liang Y, Shi J, et al. Fuzzy C-means clustering with local information and kernel metric for image segmentation.[J]. IEEE Transactions on Image Processing, 2013, 22(2):573-584.
[11] Bezdek J C. Pattern Recognition with Fuzzy Objective Function Algorithms[J]. Advanced Applications in Pattern Recognition, 1981, 22(1171):203-239.