状态子空间在往复压缩机自动预警方法的研究与应用

赵雨薇; 马波; 沈炳生; 张进杰

doi:10.13433/j.cnki.1003-8728.2016.0413

状态子空间在往复压缩机自动预警方法的研究与应用

doi: 10.13433/j.cnki.1003-8728.2016.0413

1.
北京化工大学诊断与自愈工程研究中心, 北京 100029;
2.
中国石油大港石化公司, 天津 300280

基金项目:

国家重点基础研究发展计划("973"计划)项目(2012CB026000)与国家自然科学重点基金项目(51135001)资助

详细信息

作者简介:
赵雨薇(1989-),硕士研究生,研究方向为往复机械故障诊断与预警技术,bjzxzyw1015@163.com

通讯作者:
马波(联系人),副教授,博士,mabo@mail.buct.edu.cn

计量
- 文章访问数: 188
- HTML全文浏览量: 38
- PDF下载量: 7
- 被引次数: 0
出版历程
- 收稿日期: 2014-05-29
- 刊出日期: 2016-04-05

Study on Application of State Subspace for Automatic Alarm of Reciprocating Compressor

1.
Diagnosis and Self-Recovery Engineering Research Center, Beijing University of Chemical Technology, Beijing 100029, China;
2.
China National Petroleum Dagang Petrochemical Corp., Tianjin 300280, China

摘要

摘要: 往复压缩机现有报警方式单一,多采用"单特征值报警"与"门限报警"的方式,经常导致设备盲目停车而影响生产,无法综合分析设备当前运行状态是否异常并提前预警。针对该问题,提出一种基于状态子空间的往复压缩机自动预警方法。该方法提取设备运行状态信号的特征参数,构造多维特征矩阵,利用核主元分析(kernel principal component analysis,KPCA)方法对多维特征矩阵进行降维,构建状态子空间,计算正常状态和当前状态子空间之间的差异度,并通过故障案例数据自学习得到差异度指标的报警阈值。经实际故障案例验证,该方法能大幅提前往复压缩机典型故障报警时间点,提高在线状态监测系统的故障预警能力。
- 自动预警 /
- 状态子空间 /
- 多维特征矩阵 /
- KPCA /
- 差异度
Abstract: The use of "single feature alarm" and "threshold alarm" makes the single alarm mode for the reciprocating compressor, which leads to blindly parking and affect the production. It is also unable to analyze whether the operating condition of equipment is abnormal or not comprehensively and to alarm in advance. An automatic alarm system for reciprocating compressor based on state subspace is proposed in this paper. Features of operating condition signals of the equipment are extracted to construct a multidimensional feature matrix. The dimension is then reduced by KPCA (Kernel Principal Component Analysis, KPCA) method to construct the state subspace. The difference degree between the normal state subspace and the current state subspace is calculated and the alarm threshold of the difference degree is obtained by self-learning of data of fault cases. Verified by actual failure cases, the method can significantly advance the alarm time point of typical failure of reciprocating compressor and improve the fault alarm ability of online condition monitoring system.
- accident prevention /
- alarm system /
- algorithms /
- condition subspace /
- difference degree

HTML全文

参考文献(15)

[1]	余良俭.往复压缩机故障诊断技术现状与发展趋势[J].流体机械,2014,42(1):36-39 Yu L J. Review on fault diagnosis technology for reciprocating compressors[J]. Fluid Machinery, 2014,42(1):36-39 (in Chinese)
[2]	陈光军,胡昌华,任章.一种基于时频分析的故障状态监测方法[J].机械科学与技术,2004,23(3):303-305 Chen G J, Hu C H, Ren Z. A fault diagnosis method based on time-frequency analysis[J]. Mechanical Science and Technology, 2004,23(3):303-305 (in Chinese)
[3]	马波,高金吉,江志农.往复压缩机活塞杆断裂早期预警技术的研究[J].机械强度,2008,30(3):445-449 Ma B, Gao J J, Jiang Z N. Research on the piston rod fracture Early warning technique of reciprocating compressor[J]. Journal of Mechanical Strength, 2008,30(3):445-449 (in Chinese)
[4]	Tran V T, AlThobiani F, Ball A. An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks[J]. Expert Systems with Applications, 2014,41(9):4113-4122
[5]	Schultheis S M, Lickteig C A, Parchewsky R. Reciprocating compressor condition monitoring[C]//Proceedings of the Thirty-sixth Turbomachinery Symposium. 2007:107-113
[6]	刘卫华,郁永章.往复压缩机故障诊断技术研究现状与展望[J].压缩机技术,1999,(3):49-52 Liu W H, Yu Y Z. Present situation of fault diagnosis technology study and prospect of reciprocating compressors[J]. Compressor Technology, 1999,(3):49-52 (in Chinese)
[7]	何平,张卫民,程红亮.压缩机故障信号的机理分析[J].机械研究与应用,2002,15(2):5-7 He P, Zhang W M, Cheng H L. Mechanism analysis of compressor's failure signal [J]. Mechanical Research & Application, 2002,15(2):5-7 (in Chinese)
[8]	廖广兰,史铁林,黄弢,等.核主元分析在透平机械状态监测中的应用[J].振动、测试与诊断,2005,25(3):182-185 Liao G L, Shi T L, Huang T, et al. Application of kernel principal component to turbines condition monitoring[J]. Journal of Vibration, Measurement & Diagnosis, 2005,25(3):182-185 (in Chinese)
[9]	Tian X M, Deng X G. A fault detection method using multi-scale kernel principal component analysis[C]//Proceedings of the 27th Chinese Control Conference. Kunming: IEEE, 2008:25-29
[10]	Guo K, San Y, Zhu Y. Nonlinear process monitoring using wavelet kernel principal component analysis[C]//Proceedings of 2012 International Conference on Systems and Informatics. Yantai: IEEE, 2012:432-438
[11]	孙闯,何正嘉,张周锁,等.基于状态信息的航空发动机运行可靠性评估[J].机械工程学报,2013,49(6):30-37 Sun C, He Z J, Zhang Z S, et al. Operating reliability assessment of aero-engine based on condition information[J]. Journal of Mechanical Engineering, 2013,49(6):30-37 (in Chinese)
[12]	Deng X G, Tian X M, Chen S. Modified kernel principal component analysis based on local structure analysis and its application to nonlinear process fault diagnosis[J]. Chemometrics and Intelligent Laboratory Systems, 2013,127: 195-209
[13]	Cherry G A, Qin S J. Multiblock principal component analysis based on a combined index for semiconductor fault detection and diagnosis[J]. IEEE Transactions on Semiconductor Manufacturing, 2006,19(2):159-172
[14]	Dunia R, Qin S J. Joint diagnosis of process and sensor faults using principal component analysis[J]. Control Engineering Practice, 1998,6(4):457-469
[15]	杨帆,胡金海,陈卫,等.主元分析方法在航空发动机故障检测与诊断中的应用[J].机械科学与技术,2008,27(3):330-333 Yang F, Hu J H, Chen W, et al. Application of principal component analysis to fault detection and diagnosis of aeroengines[J]. Mechanical Science and Technology for Aerospace Engineering, 2008,27(3):330-333 (in Chinese)