基于主成分分析及多维高斯贝叶斯的超声流量计故障智能诊断方法

doi:10.3969/j.issn.1000-1158.2020.12.08

摘要
图/表
参考文献(18)
相关文章 (15)

全文: PDF (511 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要提出了基于多维高斯贝叶斯模型的设备故障智能诊断流程,包括数据的筛选与结构化分析、数据的降维、模型的构建、诊断结果的检验与分析等。研究表明采用主成分分析方法进行降维时,不同的诊断对象在降维参数的选择方面存在较大差别,诊断效果因诊断对象和样本数量的不同而有所差异。利用公开发表的超声波流量计数据库对流程进行验证。结果显示:针对B型流量计进行280次、C型流量计进行550次智能故障诊断,故障状态的首选正确识别率分别达到99.3%和95.1%,较k-最近邻(KNN)聚类分析算法有一定的优势。

	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
	朱建新
	吕宝林
	乔松
	王溢芳
	陈嘉宏

关键词 ：计量学, 超声波流量计, 高斯贝叶斯, 智能诊断, 主成分分析

Abstract：The intelligent failure diagnosis method for equipment based on multivariate Gaussian Bayesian model was proposed. The method included data screening and structural analysis,data dimensionality reduction, model construction, verification and diagnostic results analysis. When using principal component analysis method for dimensionality reduction, it was shown that the selection of dimensionality reduction parameters has great influence on diagnosis result. The diagnostic effect varied with the property and quantity of samples. A publicly published ultrasonic flowmeter database was used to verified the method. By performing 280 and 550 failure diagnoses on two type of ultrasonic flowmeters (type B and type C) respectively, it was found that the correct failure recognition rate were up to 99.3% and 95.1%. Compared with the nearest neighbor KNN clustering analysis algorithm, this failure diagnosis method shows certain advantages.

Key words： metrology ultrasonic flowmeter Gaussian Bayesian smart failure diagnosis primary component analysis

收稿日期: 2019-10-17 发布日期: 2020-12-08

PACS:

TB937

基金资助:国家重点研发计划项目(2018YFF0215105);工信部智能制造综合标准化项目(工信厅装函［2018］265号);安徽省重点研发项目(1704a0902039);国机集团重大科技专项(国机科［2017］456号);合肥通用机械研究院有限公司博士基金(2018010618)

作者简介: 朱建新(1976-),浙江金华人,合肥通用机械研究院有限公司研究员、博士,主要从事设备可靠性,工程风险分析及设备智能运维方面的研究。Email: zhujianxin@hgmri.com

引用本文:

朱建新,吕宝林,乔松,王溢芳,陈嘉宏. 基于主成分分析及多维高斯贝叶斯的超声流量计故障智能诊断方法[J]. 计量学报, 2020, 41(12): 1494-1499.
ZHU Jian-xin,Lü Bao-lin,QIAO Song,WANG Yi-fang,CHEN Jia-hong. Application of Primary Component Analysis and Multivariate Gaussian Bayesian Method on Intelligent Failure Diagnosis of Ultrasonic Flowmeter. Acta Metrologica Sinica, 2020, 41(12): 1494-1499.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2020.12.08 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2020/V41/I12/1494

［1］Chen X D, Ai Z B, Yang T C, et al. Several Failure Analysis Cases of Pressure Equipment Under the Condi-tions of Complex Medium Environment［C］//ASME 2011 Pressure Vessels and Piping Conference, Balti-more, Maryland, USA, 2011.
［2］田立勇,张一辙. 基于局部均值分解与快速独立成分分析的潜水泵故障诊断［J］. 计量学报, 2020, 41(5): 585-591.
Tian L Y, Zhang Y Z. Fault Diagnosis of Submersible Pumps Based on Local Mean Decomposition and Fast Independent Component Analysis［J］. Acta Metrologica Sinica, 2020, 41(5): 585-591.
［3］秦炎锋,魏中坤,关凯书. 压缩机供液泵叶片失效分析［J］. 流体机械,2014, 42 (10): 60-63.
Qin Y F, Wei Z K, Guan K S. Failure Analysis of Liquid Ring Compressor Service Liquid Pump Bladez［J］. Fluid Machinery, 2014, 42 (10): 60-63.
［4］秦海勤,张耀涛,徐可君. 双转子-支承-机匣耦合系统碰摩振动响应分析及试验验证［J］. 机械工程学报, 2019, 55 (19): 75-83.
Qin H Q, Zhang Y T, Xu K J. Rubbing Vibration Response Theoretical Analysis and Experimental Verifica-tion for a Double Rotor Support Casing System［J］. Journal of Mechanical Engineering, 2019, 55 (19): 75-83.
［5］张金凤, 李继猛, 杨莹, 等. 基于改进耦合增强随机共振的滚动轴承故障诊断［J］. 计量学报, 2019, 40 (3):385-391.
Zhang J F, Li J M, Yang Y, et al. Rolling Bearing Fault Diagnosis Based on Improved Coupling-enhanced Stoch-astic Resonance［J］. Acta Metrologica Sinica, 2019, 40 (3): 385-391.
［6］时培明, 孙鹏, 袁丹真. 基于非线性耦合双稳态随机共振的轴承微弱故障信号增强检测方法研究［J］. 计量学报, 2018, 39 (3): 373-376.
Shi P M, Sun P, Yuan D Z. Research on the Enhanced Detection Method of Bearing Fault Weak Fault Signal Based on Nonlinear Coupled Bistable Stochastic Reson-ance［J］. Acta Metrologica Sinica, 2018, 39 (3): 373-376.
［7］李艳颖,贝叶斯网络学习及数据分类［M］. 北京: 科学出版社,北京:2018.
［8］周志华,机器学习［M］. 北京:清华大学出版社, 2017.
［9］赵申坤, 姜潮, 龙湘云. 一种基于数据驱动和贝叶斯理论的机械系统剩余寿命预测方法［J］. 机械工程学报, 2018, 54 (12): 115-124.
Zhao S K, Jiang C, Long X Y. Remaining Useful Life Estimation of Mechanical Systems Based on the Data-driven Method and Bayesian Theory［J］. Journal of Mechanical Engineering, 2018, 54 (12): 115-124.
［10］刘浩然, 李轩, 马明, 等. 一种针对水泥回转窑故障诊断的贝叶斯网络模型［J］.计量学报, 2014, 35 (5): 500-506.
Liu H R, Li X, Ma M, et al. A Fault Diagnosis Bayesian Network Model for Cement Rotary Kiln［J］. Acta Metrologica Sinica, 2014, 35 (5): 500-506.
［11］刘浩然, 孙美婷, 王海羽, 等. 基于分类优化贝叶斯结构算法的篦冷机参数状态分析及其算法收敛性分析［J］. 计量学报, 2019, 40 (4): 662-669.
Liu H R, Sun M T, Wang H Y, et al. Parameter state analysis of grate cooler based on Bayesian structure algo-rithm based on classification optimization & and conver-gence analysis［J］. Acta Metrologica Sinica, 2019, 40 (4): 662-669.
［12］刘东,王昕,黄建荧,等. 基于贝叶斯网络的水电机组振动故障诊断研究［J］. 水力发电学报,2019, 38 (2):112-120.
LIU Dong,WANG Xin,HUANG J Y, et al. Vibration fault diagnosis for hydro-power units based on Bayesian network［J］. Journal of Hydroelectric Engineering, 2019, 38 (2): 112-120.
［13］徐宾刚,屈梁生,陶肖明. 转子故障贝叶斯诊断网络的研究［J］. 机械工程学报,2004, 40 (1): 66-72.
Xu B G, Qu L S, Tao X M. Bayesian network frame-work for rotor fault diagnosis［J］. Journal of Mechanical Engineering, 2004, 40 (1): 66-72.
［14］Bishop C M. Pattern recognition and machine learning［M］. Singapore: Springer,2006.
［15］朱建新, 陈学东, 吕宝林, 等. 基于多维高斯贝叶斯的机械设备失效/故障智能诊断及参数影响分析［J］. 机械工程学报, 2020, 56 (4): 35-41.
Zhu J X, Chen X D, Lü B L, et al. Smart Failure/Fault Diagnosis and Influence Analysis for Mechanical Equipment with Multivariate Gaussian Bayesian Method［J］. Journal of Mechanical Engineering, 2020, 56 (4): 35-41.
［16］成乾. 基于最大熵区间分析的测量不确定度评定［J］. 计量学报, 2019, 40 (1): 172-176.
YAO C Q. Measurement Uncertainty Evaluation Based on Maximum Entropy Interval Analysis［J］. Acta Metro-logica Sinica, 2019, 40 (1): 172-176.
［17］Gyamfi K S, Brusey J, Hunt A, et al. Linear dimensi-onality reduction for classification via a sequential Bayes error minimisation with an application to flow meter diagnostics［J］. Expert Systems with Applications, 2017 (91)252-262.
［18］Gyamfi K S, Marshall C. Ultrasonic flowmeter diagnostics data set［EB/OL］.［2018-01-13］. http:// archive.ics.uci.edu/ml.