Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An artificial intelligence based electromagnetic logging inversion method based on high-speed forward modeling results training

An artificial intelligence and electromagnetic logging technology, applied in design optimization/simulation, special data processing applications, etc., can solve problems such as inaccurate results, insufficient data, falling into local extreme values, etc.

Active Publication Date: 2020-12-18
SHANDONG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to improve the speed and stability of the forward calculation, overcome the problem that the inversion algorithm is easy to fall into the local extremum, and solve the inaccurate results of the inversion due to insufficient 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An artificial intelligence based electromagnetic logging inversion method based on high-speed forward modeling results training
  • An artificial intelligence based electromagnetic logging inversion method based on high-speed forward modeling results training
  • An artificial intelligence based electromagnetic logging inversion method based on high-speed forward modeling results training

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] An artificial intelligence electromagnetic logging inversion method under high-speed forward modeling result training, including the following steps:

[0080] (1) Collect historical data measured by logging tools on known formations. The measured historical data includes 9 magnetic field components, namely Hxx, Hxy, Hxz, Hyx, Hyy, Hyz, Hzx, Hzy, Hzz; and through 9 Calculate the anisotropic conductivity of each formation with each magnetic field component; the calculation formula is shown in formula (I):

[0081]

[0082] (2) Obtain the output data of the forward modeling model, that is, output 9 magnetic field components for a large number of known formations other than step (1) through the forward modeling model, namely Hxx1, Hxy1, Hxz1, Hyx1, Hyy1, Hyz1, Hzx1, Hzy1, Hzz1; and calculate the anisotropic conductivity of each formation through 9 magnetic field components; the vertical resistivity, horizontal resistivity, thickness and relative dip angle of each layer i...

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

No PUM Login to View More

Abstract

The invention relates to a high speed forward result training artificial intelligent based electromagnetic logging inversion method. The method includes: (1) acquiring forward data; (2) collecting instrument acquisition data of known stratum information; (3) acquiring various kinds of information containing input parameters; (4) using 9 magnetic-field components, logging instrument receiving and transmitting parameters and the inclination as an input and using vertical specific resistance and horizontal specific resistance of different stratums and stratum boundary information as an output to construct a training set; (5) adopting a stepwise regression method to select an optimal prediction factor; (6) performing regression prediction analysis on an SVM neural network, and selecting a suitable kernel function construction model; and (7) inputting instrument acquisition data of unknown stratum information to the kernel function construction model, and predicting and acquiring other stratum inversion information. The method abandons the conventional linear inversion methods, induces an artificial intelligent method to the inversion algorithm innovatively, can perform accurate inversion on the unknown stratum information data, and can acquire the accurate result.

Description

technical field [0001] The invention relates to the technical field of electromagnetic logging inversion, and more specifically, relates to an electromagnetic logging inversion method based on artificial intelligence under high-speed forward modeling result training. Background technique [0002] In the process of oilfield exploration and development, well logging can understand the oil and gas content of the formation. Resistivity logging is an important measurement method for characterizing formations in geophysical exploration. The measured resistivity curves can provide various formation information, such as rock types, layer boundaries, and even formation anisotropy. [0003] Resistivity logging is a method of measuring the resistivity of rock (including the fluid therein) by using power supply electrodes and measuring electrodes arranged at different positions in the borehole. Resistivity logging can be divided into two parts, forward modeling and inversion. The forw...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/20
CPCG06F30/20
Inventor 李康朱高阳
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com