数据协调方法在传感器故障监测中的应用

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

清华大学辅仁网/2017-07-07

数据协调方法在传感器故障监测中的应用

蒋晓隆,刘培(

),李政

Data reconciliation for sensor fault monitoring

Xiaolong JIANG,Pei LIU(

),Zheng LI

State Key Laboratory of Control and Simulation of Power System and Generation Equipments, Department of Thermal Engineering, Tsinghua University, Beijing 100084, China

摘要:

HTML
输出: BibTeX | EndNote (RIS) 背景资料

文章导读

摘要以某电厂1 000 MW机组高压给水加热器及抽汽管道系统为对象,研究数据协调方法在传感器故障检测、识别和数据重构中的应用。数据协调过程中,采用主导因素法建立设备特性参数模型,构建参数间的特性约束关系。仿真案例研究结果表明: 该方法能够有效检测和识别传感器故障,故障数据重构平均相对误差2.42%,具有较高精度。

关键词 ：传感器故障监测,数据协调,火电厂

Abstract：Data reconciliation method is used to improve sensor fault detection, identification and data rebuilding for a high pressure feedwater heater and extraction steam pipe system in a 1 000 MW coal-ired power generation unit. The dominant factor modeling method is used to build the characteristic constraint relationships between the parameters. A case study shows that this method can efficiently detect, identify and rebuild data after sensor faults with an average relative error in the rebuilt data of 2.42%.

Key words：sensor fault monitoring data reconciliation thermal power plant

收稿日期: 2013-07-04 出版日期: 2015-03-17

引用本文:

蒋晓隆,刘培,李政. 数据协调方法在传感器故障监测中的应用[J]. 清华大学学报（自然科学版）, 2014, 54(6): 763-768.
Xiaolong JIANG,Pei LIU,Zheng LI. Data reconciliation for sensor fault monitoring. Journal of Tsinghua University(Science and Technology), 2014, 54(6): 763-768.

链接本文:

http://jst.tsinghuajournals.com/CN/或 http://jst.tsinghuajournals.com/CN/Y2014/V54/I6/763

图表:

某电厂1 000 MW机组高压给水加热器及抽汽管道示意图

高压给水加热器温度型线

#1高压给水加热器特性参数UA₁回归模型

#1高压给水加热器特性参数UA₂回归模型

高加给水管道总特性参数(0.5ξ/A²)回归模型

#2抽汽管道总特性参数(0.5ξ/A²)回归模型

特性参数	测定系数 R²	均方根误差	平均相对误差/%
#1高加 UA₁/UA₂	0.990 1/0.962 1	19.41/15.45	0.92/1.85
#2高加 UA₁/UA₂	0.989 9/0.925 4	27.56/15.81	1.02/2.75
#3高加 UA₁/UA₂	0.985 7/0.957 2	9.90/18.90	0.95/2.08
给水管道 (0.5ξ/A²)	0.965 8	7.92	0.53
#1抽汽管道 (0.5ξ/A²)	0.787 4	23.40	1.09
#2抽汽管道 (0.5ξ/A²)	0.893 7	19.37	2.38
#3抽汽管道 (0.5ξ/A²)	0.368 5	29.30	5.86

特性参数回归模型拟合优度和定标精度

训练样本数据协调目标函数γ₀分布

给水流量的正常和异常数据

测试样本数据协调目标函数值

序列消去检验求解得到数据协调目标函数值

给水流量正常数据和重构数据

参考文献:

[1]	司风琪, 周建新, 仇晓智, 等. 独立成分分析方法在电站热力过程数据检验中的应用[J]. 中国电机工程学报, 2008, 28(26): 77-81. SI Fengqi, ZHOU Jianxin, QIU Xiaozhi, et al.Application of independent component analysis on the data validation of thermodynamic system in power plant[J].Proceedings of the CSEE, 2008, 28(26): 77-81. (in Chinese)
[2]	仇韬, 张清峰, 丁艳军, 等. PCA在非线性系统传感器故障检测和重构中的应用[J]. 清华大学学报: 自然科学版, 2006, 46(5): 708-711. QIU Tao, ZHANG Qingfeng, DING Yanjun, et al.Nonlinear sensor fault detection and data rebuilding based on principle component analysis[J].J Tsinghua Univ: Sci and Tech, 2006, 46(5): 708-711. (in Chinese)
[3]	邱天, 丁艳军, 吴占松. 基于主元分析的故障可检测性的统计指标比较[J]. 清华大学学报: 自然科学版, 2006, 46(8): 1447-1450. QIU Tian, DING Yanjun, WU Zhansong. Sensor fault detection statistics based on principal component analysis[J]. J Tsinghua Univ: Sci and Tech, 2006, 46(8): 1447-1450. (in Chinese)
[4]	Bagajewicz M, JIANG Qiyou, Sanchez M. Performance evaluation of PCA tests in serial elimination strategies for gross error identification[J]. Chemical Engineering Comunications, 2013, 183(1): 119-139.
[5]	Sharifi R, Langari R. Isolability of faults in sensor fault diagnosis[J].Mechanical Systems and Signal Processing, 2011, 25: 2733-2744.
[6]	李蔚, 盛德仁, 陈坚红, 等. 双重BP神经网络组合模型在实时数据预测中的应用[J]. 中国电机工程学报, 2007, 27(17): 94-97. LI Wei, SHENG Deren, CHEN Jianhong, et al.The application of double BP neural network combined forecasting model in real-ime data predicting[J].Proceedings of the CSEE, 2007, 27(17): 94-97. (in Chinese)
[7]	董学育, 刘志远, 陈来九. 基于人工神经元网络的测量数据正确性的验证方法在发电厂控制系统中的应用研究[J]. 中国电机工程学报, 1999, 19(12): 46-50. DONG Xueyu, LIU Zhiyuan, CHEN Laijiu. A study on the validation of measured data based on the ANN and its application in the control system for power plant[J]. Proceedings of the CSEE, 1999, 19(12): 46-50. (in Chinese)
[8]	王雷, 张瑞青, 盛伟, 等. 基于支持向量机的回归预测和异常数据检测[J]. 中国电机工程学报, 2009, 29(8): 92-96. WANG Lei, ZHANG Ruiqing, SHENG Wei, et al.Regression forcast and abnormal data detection based on support vector regression[J].Proceedings of the CSEE, 2009, 29(8): 92-96. (in Chinese)
[9]	鲍文, 于达仁, 王伟, 等. 基于关联规则的火电厂传感器故障检测[J]. 中国电机工程学报, 2003, 23(12): 170-174. BAO Wen, YU Daren, WANG Wei, et al.Sensor fault detection in thermal power plants based on association rule[J].Proceedings of the CSEE, 2003, 23(12): 170-174. (in Chinese)
[10]	Narasimhan S, Jordache C. Data Reconciliation & Gross Error Detection [M]. Houston, TX: Gulf Publishing Company, 2000.
[11]	刘福国, 王学同, 苏相河, 等. 基于系统测量冗余的电厂异常运行数据检测与校正[J]. 中国电机工程学报, 2003, 23(7): 204-207. LIU Fuguo, WANG Xuetong, SU Xianghe, et al.Detection and reconciliation on the abnormal operationa data based on redundancy measurement in a power plant[J]. Proceedings of the CSEE, 2003, 23(7): 204-207. (in Chinese)
[12]	吕崇德. 热工参数测量与处理 [M]. 北京: 清华大学出版社, 2001. L Chongde. Thermal Parameter Measurement and Processing [M]. Beijing: Tsinghua University Press, 2001. (in Chinese)
[13]	LIN Tsungpo. An Adaptive Modeling and Simulation Environment for Combined-ycle Data Reconciliation and Degredation Estimation [D]. Atlanta, GA: Georgia Institute of Technology, 2008.
[14]	杨波, 李政. 火电机组热力系统主导因素建模方法研究[J]. 中国电机工程学报, 2005, 25(24): 96-102. YANG Bo, LI Zheng. Dominant factor modeling method for the thermal system of power station[J].Proceedings of the CSEE, 2005, 25(24): 96-102. (in Chinese)

No related articles found!