Pipeline anomaly distributed detection based on element-matrix trigger mechanism
HU Xu-guang
MA Da-zhong
SUN Qiu-ye
WANG Zhan-shan
LI Xiao-yu
Abstract：In order to real-time detection and reduce the number of data transmission on pipeline network that deliver a great deal of data frequently, a data model of station is established through the investigation on the station's data type and transmission and the method of pipeline anomaly distributed detection based on element-matrix trigger mechanism is also proposed. The method uses station device data to build the pipeline element-matrix, and the time of data transmission between tributary stations is decided by anomaly detection criteria based on random matrix's single ring theorem. Then, the pressure data of adjacent station is discounted by attenuation data model considering pipeline's angle. And the pipeline operating condition is gained by compared with the difference between real pressure data difference and model data dif-ference. Element-matrix trigger and attenuation data model are adopted in the method which reduce the frequency of data transmission between station and improve detection precision. Finally, the effectiveness of the proposed method is verified via simulation historical data processing.
Keywords：distributed detectionpipeline networkfault detectionevent-triggered
Publication Date：2017-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：11( 1035-1045 )