Shale gas fracturing downhole accident early diagnosis and alarm method and device

Abstract

The embodiments of the present invention provide a shale gas fracturing downhole accident early diagnosis and alarm method and device. The method includes the following steps that: the on-line monitoring data of reference variables which reflect a shale gas fracturing downhole condition are acquired; the time window of the online data is set according to a preset width; the time window is dividedinto a plurality of time segments with the same width, and linear fitting is performed on the online monitoring data in each time segment, so that the linear relationship curve of the online monitoring data in each time segment can be correspondingly obtained; corresponding trend feature primitives are determined according to the slope of the linear relationship curve of each time segment, trend feature vectors are built according to the trend feature primitives; and the trend feature vectors are substituted into a preset accident classifier, so that accident types corresponding to the onlinemonitoring data can be predicted, and corresponding alarm information is sent. With the shale gas fracturing downhole accident early diagnosis and alarm method and device of the embodiments of the present invention adopted, shale gas fracturing downhole accident early diagnosis and alarm can be achieved.

Description

technical field [0001] The present application relates to the technical field of shale gas fracturing downhole accident diagnosis and alarm technology, in particular to an early diagnosis and alarm method and device for shale gas fracturing downhole accidents. Background technique [0002] In recent years, the large-scale fracturing operation mode of shale gas has improved construction efficiency, increased gas production, and reduced fracturing costs. However, the real-time diagnosis and alarm of underground accidents are still not well resolved. At present, at the fracturing construction site, downhole accidents are judged manually based on the change process of the fracturing construction curve on the data acquisition system, but manual analysis will lead to lag and misjudgment in accident diagnosis. Therefore, it is necessary to study the early diagnosis and alarm methods of shale gas downhole accidents. [0003] Although the pattern classification method is widely use...

AI Technical Summary

Problems solved by technology

If the traditional pattern classification method is directly applied to the diagnosis of downhole accidents in shale gas fracturing, it will lead to high leakage alarms, false alarms and delayed alarms.

Images