Well drilling overflow working condition identification method and device

Abstract

The invention discloses a well drilling overflow working condition identification method and device. The method comprises the following steps: acquiring well drilling historical data; based on a wavelet transform algorithm, performing genetic algorithm training of overflow point thresholds on the drilling historical data to obtain a threshold of each kind of feature data; the threshold value is used for carrying out mutation point detection on the feature data; acquiring various characteristic data of the drilling well from the real-time logging data of the drilling well; performing wavelet transform processing on each kind of feature data, and extracting high-frequency signal features of each kind of feature data; according to the threshold value of each kind of feature data and the high-frequency signal features of each kind of feature data, overflow point identification is conducted on the multiple kinds of feature data of the drilling well. According to the invention, the efficiency and accuracy of drilling overflow condition identification can be improved; and meanwhile, the overflow working condition can be subjected to early prediction and early warning, and the drilling safety is improved.

Description

technical field [0001] The invention relates to the technical field of oil drilling, in particular to an identification method and device for drilling overflow working conditions. Background technique [0002] This section is intended to provide a background or context to embodiments of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] As oil and gas exploration and development gradually develop into deep and complex formations, the risk of overflow during drilling is increasing. Oil and gas drilling experience shows that the time from overflow discovery to blowout is very fast, and the interval is within 30 minutes for two-thirds, and half of them are within 10 minutes. [0004] If the overflow cannot be detected in time, it may lead to a dangerous well control situation, or even a serious accident such as the scrapping of the wellbore and casualties. Save precious time, thereby e...

AI Technical Summary

Problems solved by technology

[0005] Traditional drilling technology identifies overflow by artificially tracking the characteristic parameters obtained by the comprehensive logging tool, analyzing the flow difference between the inlet and outlet and the volume change of the total surface pool, etc. Only after reaching a certain height can the ground parameters change, which leads to a serious delay in the detection of overflow by this method, and relies heavily on the experience, responsibility and awareness of the monitoring personnel

[0006] At present, the proposed methods such as artificial neural network and Bayesian network still have limitations in automatic judgment of parameter changes and complex identification, and cannot effectively identify complex features in continuous long-term work, let alone accurately and early identification of overflow

Images