基于专家思维的多维度故障诊断方法

doi:10.3901/JME.2017.23.032

机械工程学报 ›› 2017, Vol. 53 ›› Issue (23): 32-38.doi: 10.3901/JME.2017.23.032

• 特邀专栏：高端压缩机组高效可靠及智能化 • 上一篇下一篇

基于专家思维的多维度故障诊断方法

马波, 高金吉, 江志农

北京化工大学诊断与自愈工程研究中心北京 100029

收稿日期:2016-08-28 修回日期:2017-07-28 出版日期:2017-12-05 发布日期:2017-12-05
通讯作者: 马波(通信作者),男,1977年出生,副研究员。主要研究方向为智能诊断、设备故障监测与诊断。E-mail:mabo@mail.buct.edu.cn
基金资助:
国家重点基础研究发展计划资助项目（973计划，2012CB026000）。

Multi-dimensional Fault Diagnosis Method Based on Expert Thinking

MA Bo, GAO Jinji, JIANG Zhinong

Diagnosis and Self-Recovery Engineering Research Center, Beijing University of Chemical Technology, Beijing 100029

Received:2016-08-28 Revised:2017-07-28 Online:2017-12-05 Published:2017-12-05

摘要/Abstract

摘要： 针对目前专家系统诊断准确度不高的问题，提出一种基于专家故障诊断思维方式的多测点、多时间点、多敏感参数相融合的故障诊断方法。从故障诊断专家对设备异常进行分析诊断的思路出发，依据故障机理、故障响应特点及故障劣化规律，选择相关测点、多时间点的数据来构建敏感参数矩阵，并生成对应的故障矩阵和权重矩阵，对设备异常状态进行诊断。利用该方法对某石化一离心压缩机异常状态进行分析诊断，结论准确，且能避免不同时间点诊断结论冲突问题。

关键词: 故障矩阵, 故障诊断, 敏感参数矩阵, 权重矩阵, 专家思维

Abstract: In view of the low diagnosis accuracy of expert system at present, a multi-dimensional fault diagnosis method based on expert thinking is proposed, which fuse information of related points, multi-times and multi-sensitive parameters. Following the thinking when fault diagnosis expert analyze and diagnose the machine's abnormal state and base on the failure mechanism, response characteristics and deterioration law, select the data of related-points in multi-times to establish the matrix of sensitive parameters, then generate the fault matrix and weight matrix to diagnose the machine's abnormal state. The result is accurate and conflicts between different times can be avoided when using this method to analyze and diagnose the abnormal state of a machine in real petrochemical.

Key words: eight matrix, expert thinking, fault diagnosis, fault matrix, sensitive parameter matrix

中图分类号:

TP277

马波, 高金吉, 江志农. 基于专家思维的多维度故障诊断方法[J]. 机械工程学报, 2017, 53(23): 32-38.

MA Bo, GAO Jinji, JIANG Zhinong. Multi-dimensional Fault Diagnosis Method Based on Expert Thinking[J]. Journal of Mechanical Engineering, 2017, 53(23): 32-38.

参考文献

[1] SHENG Chenxing, LI Zhixiong, LI Qin, et al. Recent progress on mechanical condition monitoring and fault diagnosis[J]. Procedia Engineering, 2011(15):142-146.
[2] NIU G, YANG B S. Intelligent condition monitoring and prognostics system based on data-fusion strategy[J].Expert Systems with Applications, 2010, 37(12):8831-8840.
[3] NIU Gang, HAN Tian, YANG B S, et al. Multi-agent decision fusion for motor fault diagnosis[J]. Mechanical Systems and Signal Processing, 2007(21):1285-1299.
[4] ANTON, VITKO, LADISLAV, et al. Navigation and diagnosis of walking robot[J]. Mechanical Engineering and Automation, 2012, 54(9):568-572.
[5] OZYURT B, KANDEL A. A hybrid hierarchical neural network-fuzzy expert system approach to chemical process fault diagnosis[J]. Fuzzy Sets and Systems, 1996(83):11-25.
[6] QIAN Yu, XU Liang, LI Xinxi, et al. LUBRES:An expert system development and implementation for real-time fault diagnosis of a lubricating oil refining process[J]. Expert System with Application, 2008(35):1252-1266.
[7] NAN C, KHAN F, IQBAL M T. Real-time fault diagnosis using knowledge-based expert system[J]. Process Safety and Environmental Protection, 2008, 86:33-71.
[8] 吴蒙,贡壁,何振亚. 基于并行联想记忆的机械故障诊断专家系统[J]. 振动、测试与诊断, 1992, 12(2):1-5. WU Meng, GONG Bi, HE Zhenya. Mechanical fault diagnosis expert system based on parallel associative memory[J]. Zhendong Ceshi Yu Zhenduan/Journal of Vibration Measurement & Diagnosis, 1992, 12(2):1-5.
[9] 高金吉. 基于矩阵判别筛选法的机械故障诊断专家系统[J]. 振动、测试与诊断, 1998, 18(2):120-124. GAO Jinji. A mechanical fault diagnosis expert system based on matrix distinguishing sieve method[J]. Journal of Vibration Measurement & Diagnosis, 1998, 18(2):120-124.
[10] 姚剑飞,江志农,赵庆亮,等. 基于故障原因-征兆矩阵的故障诊断专家系统[J]. 振动、测试与诊断, 2009, 29(1):74-79. YAO Jianfei, JIANG Zhinong, ZHAO Qingliang. A fault diagnosis expert system based on fault cause-symptom matrix[J]. Zhendong Ceshi Yu Zhenduan/Journal of Vibration Measurement & Diagnosis, 2009, 29(1):74-78.
[11] 刘贵立,王立鹏,张国英. 基于Alopex神经网络的旋转机械故障诊断专家系统[J]. 振动、测试与诊断, 2004, 24(1):61-65. LIU Guili, WANG Lipeng, ZHANG Guoying. Research on horizontal vibration of 32 m span simply supported railroad bridges[J]. Zhendong Ceshi Yu Zhenduan/Journal of Vibration Measurement & Diagnosis, 2004, 24(1):61-65.
[12] 李萍. 基于多振动信号信息融合的旋转机械故障诊断方法[D]. 湘潭:湖南科技大学, 2008. LI Ping. The information fusion of rotating machinery fault diagnosis based on multi-vibration signal[D]. Xiangtan:Hunan University of Science and Technology, 2008.
[13] 谭青, 向阳辉. 加权证据理论信息融合方法在故障诊断中的应用[J]. 振动与冲击, 2008, 27(4):112-116. TAN Qing, XIANG Yanghui. Application of weighted evidential theory and its information fusion method in fault diagnosis[J]. Journal of Vibration & Shock, 2008, 27(4):112-116.
[14] 赵世荣, 黄向华. 应用神经网络信息融合诊断航空发动机故障[J]. 航空动力学报, 2008, 23(1):163-168. ZHAO Shirong, HUANG Xianghua. Fault diagnosis for aeroengine gas path components based on neural network multisensor data fusion[J]. Journal of Aerospace Power, 2008, 23(1):163-168.
[15] TRIBENI P B, SWAGATAM D. Multi-sensor data fusion using support vector machine for motor fault detection[J]. Information Science, 2012, 217:96-107.
[16] 原新,朱齐丹,兰海. 基于粗糙集理论的多传感器信息融合[J]. 哈尔滨工业大学学报, 2006, 38(10):1669-1673. YUAN Xin, ZHU Qidan, LAN Hai. Multi-sensor information fusion based on rough set theory[J]. Journal of Harbin Institute of Technology, 2006, 38(10):1669-1672.
[17] 项春. 离心式压缩机旋转失速的故障机理研究[J]. 振动、测试与诊断, 2002, 22(1):54-60. XIANG Chun. Fault mechanism of rotating stall of centrifugal compressor[J]. Journal of Vibration Measurement & Diagnosis, 2002, 22(1):54-60.
[18] 王洋,夏松波,高金吉. DH型离心空压机旋转失速故障诊断及治理[J]. 振动工程学报, 2000, 13(3):487-492. WANG Yang, XIA Songbo, GAO Jinji. Fault diagnosis and treatment of rotating stall for DH type centrifugal compressor[J]. Journal of Vibration Engineering, 2000, 13(3):487-492.
[19] NICOAL G, STEPHANE B, FRANCIS L, et al. Simulation of rotating stall in a whole stage of an axial compressor[J]. Computers & Fluids, 2010(39):1644-1655.
[20] 晋风华. 基于故障矢量的汽轮机叶片脱落故障诊断方法研究[J]. 燃气轮机技术, 2007, 20(3):35-37. JIN Fenghua. Research on the methods of fault orientation of blade sheding based on fault vector for steam turbine[J]. Gas Turbine Technology, 2007, 20(3):35-37.

基于专家思维的多维度故障诊断方法

Multi-dimensional Fault Diagnosis Method Based on Expert Thinking

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	沈长青, 汤盛浩, 江星星, 石娟娟, 王俊, 朱忠奎. 独立自适应学习率优化深度信念网络在轴承故障诊断中的应用研究[J]. 机械工程学报, 2019, 55(7): 81-88.
[2]	胡茑庆, 陈徽鹏, 程哲, 张伦, 张宇. 基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报, 2019, 55(7): 9-18.
[3]	李川, 张绍辉, José Valente de Oliveira. 基于次优网络深度学习的3D打印机故障诊断[J]. 机械工程学报, 2019, 55(7): 73-80.
[4]	王奉涛, 刘晓飞, 敦泊森, 邓刚, 韩清凯, 李宏坤. 基于萤火虫优化的核自动编码器在中介轴承故障诊断中的应用[J]. 机械工程学报, 2019, 55(7): 58-64.
[5]	姜洪开, 邵海东, 李兴球. 基于深度学习的飞行器智能故障诊断方法[J]. 机械工程学报, 2019, 55(7): 27-34.
[6]	熊鹏, 汤宝平, 邓蕾, 赵明航. 基于动态加权密集连接卷积网络的变转速行星齿轮箱故障诊断[J]. 机械工程学报, 2019, 55(7): 52-57.
[7]	翁军华,张剑锐,李达,郑海兴. 光伏系统直流电弧故障检测的抗干扰技术综述[J]. 电气工程学报, 2019, 14(3): 9-15.
[8]	汪久根, 柯梁亮. 基于残差网络的RV减速器故障诊断[J]. 机械工程学报, 2019, 55(3): 73-80.
[9]	程礼, 杨武奎, 梁涛, 文璧, 姚东野. 基于声模态的压气机/风扇气路故障诊断[J]. 机械工程学报, 2019, 55(13): 38-44.
[10]	陈雪峰, 王诗彬, 程礼. 航空发动机快变信号的匹配同步压缩变换研究[J]. 机械工程学报, 2019, 55(13): 13-22.
[11]	胡超凡, 王衍学. 基于张量分解的滚动轴承复合故障多通道信号降噪方法研究[J]. 机械工程学报, 2019, 55(12): 50-57.
[12]	彭丹丹, 刘志亮, 靳亚强, 秦勇. 基于软筛分停止准则的改进经验模态分解及其在旋转机械故障诊断中的应用[J]. 机械工程学报, 2019, 55(10): 122-132.
[13]	姚德臣, 杨建伟, 程晓卿, 王兴. 基于多尺度本征模态排列熵和SA-SVM的轴承故障诊断研究[J]. 机械工程学报, 2018, 54(9): 168-176.
[14]	宗鸣,冯超,郑安琪. 基于FPGA自适应滤波器的磁轴承位移传感器故障信号处理分析[J]. 电气工程学报, 2018, 13(8): 1-6.
[15]	李允公, 戴丽, 李国萌, 王波, 吴文寿. 基于听觉显著图的瞬态振动信号表征方法研究[J]. 机械工程学报, 2018, 54(7): 54-62.