Seismic data fracture identification method and device based on convolutional neural network
A convolutional neural network and seismic data technology, applied in neural learning methods, biological neural network models, seismology, etc., can solve problems such as poor efficiency and accuracy of fracture identification
Pending Publication Date: 2021-10-22
PETROCHINA CO LTD
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The embodiment of the present invention provides a seismic data fracture identification method and device based on a convolutional neural network, which solves the problem that the existing fracture identification methods in the prior art require assumptions and the efficiency and accuracy of fracture identification are poor. technical problem
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 Construction
[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0029] In an embodiment of the present invention, a method for identifying faults in seismic data based on a convolutional neural network is provided, such as figure 1 As shown, the method includes:
[0030] Step 101: Acquiring seismic datasets;
[0031] Step 102: Mark each seismic data in the seismic data set with fracture features to obtain a label data set;
[0032] Step 103: constructing a semantic segmentation network structure model based...
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
The invention provides a seismic data fracture identification method and device based on a convolutional neural network, and the method comprises the following steps: obtaining a seismic data set; performing fracture feature labeling on each piece of seismic data in the seismic data set to obtain a label data set; constructing a semantic segmentation network structure model based on the combination of U-net and a deep residual network; training the semantic segmentation network structure model according to the seismic data set and the label data set to obtain an optimal semantic segmentation network structure model; and based on the optimal semantic segmentation network structure model, carrying out fracture identification on the obtained unknown seismic data volume to obtain a fracture identification result. According to the scheme, the network model is trained by using the earthquake big data, the trained network model has an intelligent effect when fracture identification is carried out, parameters do not need to be manually set in the fracture identification process, and fractures in unknown data can be directly predicted.
Description
technical field [0001] The present invention relates to the technical field of artificial intelligence and seismic data interpretation, in particular to a method and device for identifying seismic data fractures based on a convolutional neural network. Background technique [0002] In seismic exploration, structural interpretation plays a key role in oil and gas exploration and development, and fault system interpretation is an extremely important task in structural interpretation. In basin area research, it is necessary to find out the faults controlling the basin; in shale gas exploration and development, it is necessary to study the development and distribution of shale faults; in regional structure research, it is necessary to accurately explain the fault system; Control faults in oil and gas reservoirs. It can be seen that accurate and efficient identification of fault features is very important for oil and gas exploration and development. [0003] In traditional seis...
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 IPC IPC(8): G01V1/30G06K9/62G06N3/04G06N3/08
CPCG01V1/301G06N3/08G01V2210/642G06N3/045G06F18/241
Inventor 常德宽雍学善杨午阳李海山陈德武王一惠
Owner PETROCHINA CO LTD