End-to-end adversarial network fluid phase identification method
An identification method and technology of fluid phase, applied in seismology, instruments, measurement devices, etc., can solve problems such as deviation from physical laws, and achieve the effect of improving performance, avoiding the introduction of uncertain factors, and eliminating the need for linear solution links.
Pending Publication Date: 2022-05-03
CHINA PETROLEUM & CHEM CORP +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The purpose of the present invention is to provide an end-to-end adversarial network fluid phase recognition method for the problem that the use of attribute body training may deviate from the physical law in the prior art
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
[0038] Below in conjunction with accompanying drawing, the present invention is described in detail.
[0039] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0040] An end-to-end adversarial network fluid phase identification method, starting directly from the seismic data itself, retaining the hidden features and physical propagation laws of the seismic data to the greatest extent, looking for the law of oil and gas information in the target layer, and obtaining the results of fluid phase classification , forming an end-to-end deep learning model for seismic signals.
[0041] An end-to-end adversarial network fluid phase identification method, which ...
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 discloses an end-to-end adversarial network fluid phase identification method, which adopts an adversarial network design method, directly utilizes raw data seismic data to carry out fluid phase discrimination, can avoid the problem that effective signal features are weakened or removed due to seismic data denoising and other processing, and improves the accuracy of fluid phase identification. And the performance of the classification and discrimination network is improved by utilizing a game method, the limitation of utilizing single characteristic domains of amplitude and frequency in the past is broken through, the fluid phase is more effectively described, a current intermediate complex linear solving link is omitted, and introduction of uncertain factors and abrupt change of breaking away from a physical rule in a calculation process are avoided.
Description
technical field [0001] The invention relates to the technical field of fluid prediction in seismic exploration, in particular to an end-to-end confrontation network fluid phase identification method. Background technique [0002] Rock formations are composed of pore fluids and solid skeletons. When seismic waves penetrate underground rock formations, reflections will be formed. Reflected waves imply fluid-related information. Depending on the nature of the fluid, the characteristics of the seismic signal response are different. However, this feature is very weak in most cases, and it is difficult to obtain its response feature directly through the amplitude information. To obtain such fluid characteristics, in terms of pre-stack and post-stack methods, one uses the absorption attenuation anomaly or frequency anomaly of post-stack seismic data, and the other uses the AVO anomaly of pre-stack seismic data, but the above methods are all Linear calculation, the entire work area...
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 Applications(China)
IPC IPC(8): G01V1/36G01V1/30
CPCG01V1/36G01V1/30G01V2210/6161G01V2210/6169
Inventor 喻勤许多熊亮赵爽郑公营唐建明孔选林李曙光董霞吕其彪
Owner CHINA PETROLEUM & CHEM CORP