BP neural network-based pre-drilling mud leakage prediction method for complex well conditions

Abstract

The invention discloses a BP neural network-based pre-drilling mud leakage prediction method for complex well conditions. The method comprises the steps of S1, collecting historical seismic attribute data of a target area and engineering and geological data information corresponding to leakage cases; s2, performing standardization processing on the collected data, and performing conversion processing on all the data in order to facilitate implementation of the method; s3, taking the preprocessed historical seismic data as input, taking a leakage condition as output, taking a real leakage state as a standard value, and performing supervised training and optimization to obtain a leakage prediction neural network model; and S4, inputting instant seismic data of a target area, and automatically judging the leakage condition corresponding to each depth of the area by the model. The problems that in-well conditions are difficult to accurately predict before drilling under existing complex well conditions, and mud leakage is prone to occurring are solved.

Description

technical field [0001] The invention relates to the technical field of drilling construction, in particular to a method for predicting mud leakage before drilling in complex well conditions based on a BP neural network. Background technique [0002] During the drilling and production process, lost circulation often occurs when drilling into a zone with fracture development and / or a zone with karst cave development. Drilling in formations where lost circulation is prone to occur is a relatively complicated drilling work. Drilling in the above formations is very easy to induce major downhole accidents such as blowout and pipe sticking. More importantly, drilling engineering accidents directly affect the discovery and protection of oil and gas layers, resulting in a decline in the effectiveness of exploration and development. For example, the currently commonly used technical means in the Tazhong North Slope area of ​​the Tarim Basin is to test and analyze the lost circulation...

AI Technical Summary

Problems solved by technology

[0004] For this reason, the present invention provides a method for predicting mud loss before drilling in complex well conditions based on BP neural network, so as to solve the problems that it is difficult to accurately predict the conditions in the well and prone to mud loss before drilling in complex well conditions.

Images