The Application of a New PCA Algorithm on Fault Recognition for Oilfield's Sensor Equipment

Tong Wang; Xue Lin; Chun Fang Liu

doi:10.4028/www.scientific.net/AMR.546-547.1024

Paper Titles

Research of Hybrid Scheduling Based on Network Calculus in Coal Mine Ethernet
p.1003

Observer-Based H_∞ Control of T-S Fuzzy Model
p.1008

Research on the Space Manipulator Control in Capturing Object Based on Noncontact Impedance Control
p.1014

The Application of MEMS Gyroscope in Stable Platform of Infrared Guidance
p.1020

The Application of a New PCA Algorithm on Fault Recognition for Oilfield's Sensor Equipment
p.1024

Guaranteed Cost Control for a Class of Switched Descriptor Systems
p.1030

Study on the Communication Mechanism of Two-Grade CAN Based Marine Distributed Control System
p.1035

Adaptive Modified Projective Synchronization Between Genesio and Rossler Chaotic Systems with Uncertainties
p.1040

Design of Mobile Robotic Control System Based on ARM
p.1045

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 546-547The Application of a New PCA Algorithm on Fault...

The Application of a New PCA Algorithm on Fault Recognition for Oilfield's Sensor Equipment

Abstract:

According to the characteristics of the production measures process in oilfield , the algorithm based on iterative multi-PCA is presented. Building multi-PCA models based on diffident working conditions. The sensor data will be classified automatic through the weight to find the appropriate model for fault recognition. And adopting iterative algorithm to update the models for realizing on-line process monitoring. The simulation experiment shows that the method is effectiveness on fault diagnosis for oilfield's sensor equipment.

You might also be interested in these eBooks

Electrical Insulating Materials and Electrical Engineering

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 546-547)

Pages:

1024-1029

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.546-547.1024

Citation:

Cite this paper

Online since:

July 2012

Authors:

Tong Wang, Xue Lin, Chun Fang Liu

Keywords:

Fault Recognition, Iterative Algorithm, Multi-PCA, Oilfield Sensor Equipment

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Z. Hailin, Y. Ping. A Research on Fault Detection Diagnosis Technology for Sensor[J]. Shanghai: Mechatronics, 2001(5): 73-78.

Google Scholar

[2] L . Donghui, W. Leying, L. sheng. Fault Diagnosis of Sensors in Air-Conditioning System Based on PCA Method[J]. Beijing: Transactions of China Electrotechnical Society, 2008(6): 130-136.

Google Scholar

[3] Z. Liping, H. Feiqun, T. Liling, L. Xinguang. Study on sensor fault diagnosis of wet flue gas desulfurization system in thermal power plant based on PCA[J]. Fujian: Journal of Fuzhou University, 2011(39): 240-244.

Google Scholar

[4] G. Dong, W. Chongguang, Z. Beike, M. Xin. Method Combining PCA and SDG for Fault Diagnosis of Sensors and Its Application[J]. Beijing: Journal of System Simulation, 2011(23): 567-573.

Google Scholar

[5] F. Kchang. Sensor Fault Diagnosis Based on Structure Optimized PCA and Its Application[D]. Zhejiang: Zhejiang University, (2007).

Google Scholar

[6] M. Liling, W. Junzheng, S. Yue. A Process Monitoring Method Based on Multi-PCA Models[J]. Beijing: Transactions of Beijing Institute of Technology, 2004(24): 64-68.

Google Scholar

[7] T. Pangning, M. Steinbach,V. Kumar. Introduction to data mining[M]. Beijing: Post&Telecom press, (2005).

Google Scholar

[8] L. Weihua, H. Henry Yue, Sergio Valle-Cervantes, S. Joe Qin. Recursive PCA for adaptive process monitoring[J]. Elsevier: Journal of Process Control, 2000(10): 471-486.

DOI: 10.1016/s0959-1524(00)00022-6

Google Scholar

[9] L. Shaobo. Study of Monitoring and Fault Diagnosis in Industrial Process Based on the theory of Multivariate Statistics[D], Harbin: Harbin University of Science and Technology, (2008).

Google Scholar