改进粒子滤波和小波包在汽轮机振动诊断中的应用

doi:10.16182/j.issn1004731x.joss.201611025

系统仿真学报 ›› 2016, Vol. 28 ›› Issue (11): 2823-2831.doi: 10.16182/j.issn1004731x.joss.201611025

改进粒子滤波和小波包在汽轮机振动诊断中的应用

夏飞^1,2, 郝硕涛^2,3, 张浩^1,2, 彭道刚^2,3

1.同济大学电子与信息工程学院,上海 201804;
2.上海电力学院自动化工程学院,上海 200090;
3.上海发电过程智能管控工程技术研究中心,上海 200090

收稿日期:2015-09-08 修回日期:2016-01-04 出版日期:2016-11-08 发布日期:2020-08-13
作者简介:夏飞(1978-),男,江西南昌,博士生,副教授,研究方向为故障诊断、图像处理。
基金资助:
上海市"科技创新行动计划"高新技术领域科研项目(15111106800); 上海市发电过程智能管控工程技术研究中心项目(14DZ2251100); 上海市电站自动化技术重点实验室开放课题(13DZ2273800)

Application of Improved Particle Filter and Wavelet Packet in Turbine Vibration Diagnosis

Xia Fei^1,2, Hao Shuotao^2,3, Zhang Hao^1,2, Peng Daogang^2,3

1. School of Electronic and Information, Tongji University, Shanghai 201804, China;
2. College of Automation Engineering,Shanghai University of Electric Power, Shanghai 200090, China;
3. Shanghai Engineering Research Center of Intelligent Management and Control for Power Process, Shanghai 200090, China

Received:2015-09-08 Revised:2016-01-04 Online:2016-11-08 Published:2020-08-13

摘要/Abstract

摘要： 提出了一种改进粒子滤波和小波包分析相结合的汽轮机振动故障诊断方法。针对传统粒子滤波的样本退化问题,在重采样阶段提出了一种权值排序和优胜劣汰的改进粒子滤波算法。采用小波包分析的方法进行特征提取,利用SVM得到故障诊断结果。由结果可知,降噪信号的故障识别率明显高于原始信号的故障识别率。无论哪种信号,采用小波包分析提取特征向量进行故障诊断的识别率要高于采用FFT分析得到特征向量进行故障诊断的识别率,证明了本文提出方法的优越性。

关键词: 改进粒子滤波, 权值排序, 优胜劣汰, 小波包分析, 振动故障诊断

Abstract: A fault diagnosis method of improved particle filter and wavelet packet analysis was proposed in the application of turbine vibration. There was a sample degradation problem in the re-sampling stage of traditional particle filter. And a re-sampling algorithm which was a weight sorting and the survival of the fittest to obtain the improved particle filter was studied. The signal was filtered by the improved particle filter. Then wavelet packet analysis was used to extract the features from the noise reduction signal. Finally the fault diagnosis results were obtained by using SVM. It is shown that the fault identification rate of the noise reduction signal is significantly higher than that of original signal. No matter which kinds of signal are, the recognition rate of fault diagnosis using wavelet packet analysis is higher than that of FFT analysis. It shows the superiority of the improved particle filter and wavelet packet analysis in the stream vibration fault diagnosis.

Key words: improved particle filter, weight sorting, survival of the fittest, wavelet packet analysis, fault diagnosis of vibration

中图分类号:

TP391.9

夏飞, 郝硕涛, 张浩, 彭道刚. 改进粒子滤波和小波包在汽轮机振动诊断中的应用[J]. 系统仿真学报, 2016, 28(11): 2823-2831.

Xia Fei, Hao Shuotao, Zhang Hao, Peng Daogang. Application of Improved Particle Filter and Wavelet Packet in Turbine Vibration Diagnosis[J]. Journal of System Simulation, 2016, 28(11): 2823-2831.

参考文献 20

[1]	徐红燕, 张浩, 王晓平, 等. 基于小波分析的汽轮发电机组振动信号消噪和特征提取[J]. 华东电力, 2006, 34(9): 10-13.
[2]	刘晓平, 郑海起, 祝天宇. 粒子滤波在含噪齿轮箱故障盲源分离中的应用[J]. 中国机械工程, 2011, 22(15): 1853-1857.
[3]	张琪, 胡昌华, 乔玉坤. 基于权值选择的粒子滤波算法研究[J]. 控制与决策, 2008, 23(1): 117-120.
[4]	韩晓娟, 董泽, 孟磊, 等. Hilber-Huang变换在汽轮机故障诊断中的应用[J]. 华北电力大学学报, 2008, 35(1): 18-21.
[5]	王旭慧, 江琦. 小波分析在汽轮机振动故障诊断中的应用研究[J]. 电力学报, 2014, 29(1): 80-83.
[6]	陈景龙, 訾艳阳, 何正嘉, 等. 自适应冗余多小波及其在故障诊断中的应用[J]. 西安交通大学学报, 2012, 46(7): 44-49.
[7]	赵永刚. 汽轮机轴瓦振动故障特征提取研究[J]. 电站系统工程, 2013, 29(4): 59-60, 63.
[8]	艾瑞波. 基于小波包能量谱的汽轮机转子故障识别仿真[J]. 计算机仿真, 2013, 30(7): 133-136.
[9]	司娟宁, 刘金园, 董泽, 等. 基于主成分分析与支持向量机的汽轮机故障诊断[J]. 汽轮机技术, 2011, 53(2): 139-142.
[10]	韩中合, 刘浩明. 基于支持向量机的汽轮机振动故障诊断系统[J]. 汽轮机技术, 2013, 55(2): 127-130.
[11]	石志标, 宋全刚, 马明钊, 等. 基于改进粒子群优化支持向量机的汽轮机组故障诊断[J]. 动力工程学报, 2012, 32(6): 454-457, 462.
[12]	Lin Sang, Tieshan Zhang.Fault diagnosis of Steam Turbine Generator Unit Based on Support Vector Machine[J]. International Journal of Hybrid Information Technology (S1738-9968), 2013, 6(6): 101-1008.
[13]	徐涛. 基于多传感器融合的水下机器人自主导航方法研究 [D]. 青岛: 中国海洋大学, 2010.
[14]	刘晓平, 郑海起, 张训敏. 粒子滤波在轴承故障振动信号降噪中的应用[J]. 轴承, 2010, 45(9): 37-40.
[15]	潘宏侠, 门吉芳. 粒子滤波在轴承故障振动信号降噪中的应用[J]. 振动、测试与诊断, 2011, 31(3): 354-356, 398.
[16]	Gustafsson F, Gunnarsson F, Bergman Niclas, et al.Particle Filter for Positioning, Navigation, and Tracking[J]. Singal Processing (S1053-587X), 2002, 50(2): 425-437.
[17]	Hektor T, Karlsson H, Nordlund P J.A Marginalized Particle Filter Approach to an Integrated INS/TAP System[C]// IEEE/ION Position, Location and Navigation Symposium, California, USA. USA: IEEE, 2008: 766-770.
[18]	于志伟, 苏宝库, 曾鸣. 小波包分析技术在大型电机转子故障诊断系统中的应用[J]. 中国电机工程学报, 2005, 25(22): 158-162.
[19]	许小刚, 王松岭, 刘锦廉. 基于小波包能量分析及改进支持向量机的风机机械故障诊断[J]. 动力工程学报, 2013, 33(8): 606-612.
[20]	齐俊德, 李山, 陈冰. 基于小波包能量矩阵的轴承信号特征提取[J]. 振动与冲击, 2013, 32(21): 107-111.

改进粒子滤波和小波包在汽轮机振动诊断中的应用

Application of Improved Particle Filter and Wavelet Packet in Turbine Vibration Diagnosis

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 2

编辑推荐

Metrics

本文评价

[1]	夏飞, 王志成, 郝硕涛, 彭道刚, 余贝丽, 黄毅敏. 基于卡尔曼粒子滤波算法的锂电池SOC估计[J]. 系统仿真学报, 2020, 32(1): 44-53.
[2]	沈艳霞, 吴娟, 赵芝璞, 纪志成. 三电平逆变器多故障模式识别方法[J]. 系统仿真学报, 2017, 29(7): 1447-1457.