With the increasing of pipe diameter and operation pressure, the severity of the accident consequences has been increased, especially for the impact on the high consequence area. The safety of oil and gas pipeline is very important.

At the same time, a lot of data were produced during the process and the amount of detection data signal has also reached the TB level. However, because the relationship between these data sets has not been established, most part of the “Big Data” in which the safety information of pipeline hidden was ignored and discarded.

In order to effectively use the relevant pipeline data of the defects, the mutual information method was adopted to establish a correlation analysis model. Its main purpose was extracting all the factors that lead to pipeline defects from the “Big Data” and determined the crucial factors from them.

A pipe segment on a long-distance pipeline with the length of 100km was taken as a case. Based on the correlation analysis model, the crucial factors which had great correlation relationship with pipeline defect were extracted, so as to provide reference to accident prevention. It is a new way of pipeline safety management.

This content is only available via PDF.
You do not currently have access to this content.