Dynamic drilling data abnormal trend detection method

Abstract

The invention discloses a dynamic drilling data abnormal trend detection method. The method comprises the following steps: s1, reading and converting real-time data; s2, integrating five different algorithms to calculate trend change indexes of the time series drilling data; s3, obtaining a final risk index through joint voting calculation of the trend detection indexes; s4, automatically updatingan alarm threshold value along with the change of the data by utilizing a dynamic threshold value calculation method; and s5, judging whether the final risk index exceeds a threshold value or not, and deciding whether to trigger an alarm or not. According to the invention, the data driving method is used for detecting the abnormal trend of the real-time data, so that the uncertainty of the real-time data can be solved; the invention can be used for monitoring drilling data exception caused by various reasons and warning risks in a physical application range, and the calculation process is simple and rapid; the invention can be applied to accurately evaluating data exception caused by working condition change in the drilling process so as to effectively realize risk in-time early warning in a drilling management system and reduce the misjudgment probability.

Description

technical field [0001] The invention belongs to the technical field of oil and gas drilling, in particular to a method for detecting abnormal trends of dynamic drilling data. Background technique [0002] The judgment of drilling dangerous accidents is often not satisfied with monitoring the abnormality of a single data, and usually needs to detect multiple data at the same time, and it is easy to miss important information by using the visual observation method. Existing drilling hazard accident identification systems mostly rely on physical models. The use of physical models requires a large amount of data input and calculation, and its application range is limited. Due to the long detection time interval, it is impossible to detect rapidly developing downhole dangerous conditions such as gas intrusion in time. Most of the downhole complex conditions in the drilling process, such as gas invasion, lost circulation, pipe sticking and other accidents, will show certain data ...

AI Technical Summary

Problems solved by technology

The published real-time drilling data trend analysis method can only detect the abnormal increase and decrease trend of the data, but cannot detect the abnormal increase and decrease rate change trend of the data, and the threshold setting is often derived from a large amount of practical accumulation, which cannot be used in the new environment. Meet the requirement of adequately detecting potential risks without a large number of false positives

Images