基于多元状态评估和相关分析的振动故障诊断

PDF(4208 KB)

振动与冲击 ›› 2024, Vol. 43 ›› Issue (17) : 269-277.

论文

基于多元状态评估和相关分析的振动故障诊断

黄杨森，王勇，刘云平，冯小健

作者信息 +

Vibration fault diagnosis based on multivariate state evaluation and correlation analysis

HUANG Yangsen, WANG Yong, LIU Yunping, FENG Xiaojian

Author information +

文章历史 +

摘要

针对运行状态汽轮发电机轴振、瓦振异常预警及其原因诊断困难问题，提出一种基于多元状态评估（Multivariate State Evaluation Technology ，MSET）和相关分析（Correlation Analysis，CA）的故障诊断方法。首先基于MSET和滑动窗口计算当前评价窗口内参量估计值与其运行值的残差；其次计算当前评价窗口内参数间相关系数与状态矩阵中对应相关系数的残差；再次通过为各参数相对偏差均值或残差均值、各相关系数残差设定阈值，从而提取出异常特征；最后基于异常特征和欧式距离进行振动异常预警和异常故障诊断。利用掌握的汽轮发电机运行数据测试验证，测试结果表明：所提故障诊断方法切实可行，与单一的参数自身变化评价或相关分析相比，可提取更多异常或故障特征，具备多故障诊断分析能力,更有利于振动异常预警和提高故障诊断准确性。

Abstract

A fault diagnosis method based on Multivariate State Evaluation Technology (MSET) and Correlation Analysis (CA) is proposed to address the issue of abnormal vibration warning and cause diagnosis for turbogenerator rotor in running state. Firstly, the residual error is calculated between the predicted value and the operating value in the current evaluation window based on MSET and Sliding Window Principle. Secondly, the residual error of the correlation coefficient between in the state matrix and in the current evaluation window is calculated. Thirdly, thresholds are set for the relative deviation mean or residual error of each parameter and the residual error of each correlation coefficient to extract the abnormal features. Finally, vibration warning and abnormal diagnosis are based on Euclidean Distance and the anomalous features. The fault diagnosis method is validated by the operation data of turbogenerators. The results show that the proposed diagnosis method is feasible and can extract more abnormal or fault features compared with the single parameter self-change evaluation or parameter correlation analysis. It has the ability to diagnose multiple faults, which is beneficial for anormal warning and improving the accuracy of diagnosis.

导出引用

黄杨森, 王勇, 刘云平, 冯小健. 基于多元状态评估和相关分析的振动故障诊断[J]. 振动与冲击, 2024, 43(17): 269-277

HUANG Yangsen, WANG Yong, LIU Yunping, FENG Xiaojian. Vibration fault diagnosis based on multivariate state evaluation and correlation analysis[J]. Journal of Vibration and Shock, 2024, 43(17): 269-277

参考文献

[1] 黄杨森. 基于BP神经网络的转子振动预警方法研究[J]. 发电设备,2023,37(03):186-191.
HUANG Yang-sen. Research on Early Warning Method for Rotor Vibration Based on BP Neural Network[J]. Power Equipment. 2023, 37(3): 186-191
[2] 黄杨森,刘云平,王勇等. 汽轮发电机组转子振动预警方法研究[J]. 机械强度,2023,45(03):541-547.
HUANG Yang-Sen, LIU Yun-Ping, WANG Yong, et al. RESEARCH ON EARLY WARNING METHOD OF ROTOR VIBRATION OF TURBOGENERATOR UNIT (MT)[J]. Journal of Mechanical Strength , 2023, (3):541-547.
[3] 张龙,吴荣真,周建民等. 滚动轴承性能退化的时序多元状态估计方法[J]. 振动.测试与诊断, 2021,41(06): 1096-1104+1235-1236.
ZHANG Long, WU Rong-zhen, ZHOU Jianmin, et al. Performance Degradation Assessment of Rolling Bearing Based on AR Model and Multivariate State Estimation Technique [J］. Journal of Vibration, Measurement and Diagnosis，2021，41（06）：1096-1104+1235-1236.
[4] 张龙,刘杨远,吴荣真等. 基于MSET重构模型整体优化的轴承性能退化评估方法[J]. 振动与冲击, 2023, 42(16): 251-261.
ZHANG Long, LIU Yang-yuan, WU Rong-zhen, et al. Evaluation of bearing performance degradation based on global optimization of an MSET reconstruction model. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(16): 251-261.
[5] Ziqi W, Changliang L,Feng Y. Condition monitoring of wind turbine based on incremental learning and multivariate state estimation technique[J]. Renewable Energy,2022,184:343-360.
[6] Hui G, Hongxia Z, Xiaobo C. Multivariate State Estimation Technique Combined with Modified Information Entropy Weight Method for Steam Turbine Energy Efficiency Monitoring Study[J]. Energies,2021,14(20):6795-6795.
[7] Wang Z, Liu C. Wind turbine condition monitoring based on a novel multivariate state estimation technique[J]. Measurement, 2021, 168.
[8] Lv Y, Fang F, Yang T, et al. An early fault detection method for induced draft fans based on MSET with informative memory matrix selection[J]. ISA Transactions, 2020, 102(prepublish) : 325-334.
[9] Yazhou L, Wei D, Liandie Z, et al. A novel fault early warning method for mechanical equipment based on improved MSET and CCPR[J]. Measurement,2023,218.
[10] 罗婵纯. 基于参数相关性分析的火电设备故障诊断方法[J].发电设备,2018,32(06):429-433.
Luo Chan-chun. Fault Diagnosis of Thermal Power Equipment Based on Parameter Correlation Analysis[J]. Power Equipment 2018,32(6): 429-433.
[11] 孙原理,宋志浩. 基于多物理场信号相关分析与支持向量机的离心泵故障诊断方法[J]. 振动与冲击,2022,41(06): 206-212.
SUN Yuan-li, SONG Zhi-hao. Centrifugal pump fault diagnosis based on the multi-physical field signals correlation analysis and support vector machine[J]. Journal of Vibration and Shock, 2022, 41(06): 206-212.
[12] 王颖,李录平,陈尚年等. 基于运行参数相关分析的汽轮机组碰磨故障诊断方法及其应用[J]. 汽轮机技术,2023,65(03):207-213.
Wang Ying, Li Lu-ping, Chen Shang-nian, et al. Rubbing Fault Diagnosis Method and Application of Steam Turbine Unit Based on Correlation Analysis of Operating Parameters[J]. TURBINE TECHNOLOGY, 2023,65(03):207-213.
[13] 孙和泰,孙彬,黄翔等. 汽轮发电机组振动故障诊断相关分析方法及应用[J]. 汽轮机技术,2020,62(04):292-294+299.
SUN He-tai, SUN Bin, HUANG Xiang, et al. Correlation Analysis Method and Application for Vibration Fault Diagnosis of Turbine Generator Unit[J]. TURBINE TECHNOLOGY, 2020,62(04):292-294+299.
[14] 林万德,刘雄,黄杨森等. 一种工况参数的预测方法、装置、设备及存储介质[P]. 中国, 202111160546.X, 2021-11-15.
[15] 隐极同步发电机技术要求: GB/T 7064—2017[S]. 北京: 中国标准出版社, 2018: 12.
[16] 李永刚,李和明,赵华. 汽轮发电机转子绕组匝间短路故障诊断新判据[J]. 中国电机工程学报, 2003(6): 112-116+169.
LI Yong-gang，LI He-ming，ZHAO Hua． The new criterion on in- terturn short-circuit fault diagnose of steam turbine generator rotor windings［J］． Proceedings of the CSEE, 2003, 23(6): 112-116+169.
[17] 张征平,刘石. 大型汽轮发电机转子匝间短路故障在线诊断方法[J].电力自动化设备,2012,32(08):148-152.
ZHANG Zheng-ping, LIU Shi. Online diagnosis of interturn short circuit for large turbine generator’s rotor[J]. Electric Power Automation Equipment,2012,32(08):148-152.
[18] 高庆水,刘石,张楚. 汽轮机座缸式轴承振动影响因素研究［J］. 振动与冲击, 2014, 33(13): 26-30.
GAO Qing-shui, LIU Shi, ZHANG Chu. Influential factors of vibration of bearings on turbine exhaust cylinder[J]. Journal of Vibration and Shock, 2014, 33(13): 26-30.
[19] 田永伟,杨建刚．大型旋转机械轴振瓦振比例关系的深入研究［J］．振动与冲击, 2008, 27(s1):82-84.
TIAN Yong-wei, YANG Jian-gang. Further research on the relationship between shaft vibration of large rotation machinery[J]. Journal of Vibration and Shock, 2008, 27(s1): 82-84.
[20] 施维新,石静波. 汽轮发电机组振动及事故：第二版[M]. 北京: 中国电力出版社, 2017.