A Calculation Method of Formation Pore Pressure Based on Convolutional Neural Network and Eaton Formula
A technology of formation pore pressure and convolutional neural network, which is applied in the field of oil and gas drilling, can solve problems such as the inability to reflect the advantages of convolutional neural network in processing big data, and achieve the effect of avoiding subjectivity and uncertainty and improving calculation accuracy
Active Publication Date: 2021-02-02
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Existing special patents are mainly aimed at time-domain signals through time-frequency transformation for convolutional neural network pattern recognition. However, seismic and logging data in the depth domain in the field of drilling technology cannot reflect the advantages of convolutional neural networks in processing big data.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment example
[0040]Taking Well A in a certain block as an example, take Well A as the target well to be calculated for formation pore pressure, use 10 completed adjacent wells of Well A as modeling training samples, and select the upper Neogene strata with a depth of less than 1500 m in Well A as The test sample is sampled in the sampling interval of the normal compacted interval, and the interval velocity curve is as follows image 3 As shown, the data in this figure are raw data measured by seismic or logging tools.
[0041] A method for calculating formation pore pressure based on convolutional neural network and Eaton formula, comprising:
[0042] 1) Select completed well logging data for model training: overlapping sampling is performed on the logging curve parameters used to calculate formation pore pressure, and short-time Fourier transform is performed respectively to obtain the corresponding deep-frequency map of each sampling sample;
[0043] Wherein, the overlapping sampling is...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
A calculation method of formation pore pressure based on convolutional neural network and Eaton formula, including: overlapping sampling of well logging curves; sample 1D-2D transformation preprocessing based on short-time Fourier transform, converting one-dimensional depth domain logging curves to The sample is converted into a two-dimensional deep-frequency image; based on the convolutional neural network intelligent recognition model for normal compacted intervals, the data-driven method is used to extract the segmented features of the logging curves and identify the normal compacted intervals; According to the normal compaction trend line fitting equation, the Eaton formula is used to calculate the formation pore pressure profile. The invention adopts the formation pore calculation method based on the combination of data drive and physical model, which avoids human subjectivity in the process of constructing the normal compaction trend line, and improves the calculation accuracy of the formation pore pressure.
Description
technical field [0001] The invention relates to a formation pore pressure calculation method based on a convolutional neural network and an Eaton formula, belonging to the technical field of oil and gas drilling. Background technique [0002] Formation pore pressure is one of the important parameters for the study of wellbore stability, drilling engineering design and reservoir evaluation. Effective and accurate prediction of formation pore pressure is of great significance for optimal and fast drilling and protection of oil and gas reservoirs. The Eaton method is currently the most commonly used calculation method for formation pore pressure. This method uses seismic or logging data to calculate formation pore pressure according to the normal compaction trend line. It has the characteristics of good continuity, high resolution, and strong practicability. The construction of the normal compaction trend line is the premise of using the Eaton method to calculate the formation ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/27G06N3/04G06N3/08G06F17/14G01V11/00G06F119/14
CPCG06F30/27G06N3/084G06F17/141G01V11/00G06F2119/14G06N3/045
Inventor 管志川韩超许玉强李敬皎李成
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)