Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Measurement while drilling channel estimation method based on deep learning

A channel estimation and measurement-while-drilling technology, applied in the field of communication, can solve problems such as strong noise, non-linear transmission channel, interference, etc., and achieve high-precision, high-quality channel estimation

Active Publication Date: 2021-12-14
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention improves and designs a channel estimation method for measurement-while-drilling based on deep learning, which solves the problems existing in the prior art: the transmission channel of drilling fluid while drilling is due to its signal generation, transmission mechanism and surface The decision of the signal receiving environment, its transmission channel has serious nonlinearity and strong noise interference

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
  • Measurement while drilling channel estimation method based on deep learning
  • Measurement while drilling channel estimation method based on deep learning
  • Measurement while drilling channel estimation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In the drilling fluid MWD system, the drilling fluid pulse signal x(t) generated by the downhole drilling fluid generator is sent to the ground through the drilling fluid channel, and is collected by the pressure sensor on the ground. The received signal on the ground is:

[0024] y(t)=x(t)*h(t)+z(t) (2-1)

[0025] In formula (2-1), y(t) represents the received signal; x(t) is the downhole transmission signal, that is, the pressure wave generated by the pulse generator; h(t) is the time-domain pulse response of the channel, that is, the response to the drilling pipeline Channel description; "*" is a convolution operator; z(t) is a noise signal; usually to complete channel estimation, it is necessary to insert a known training sequence into x(t) at the sending end, and use the training sequence sent at the receiving end The corresponding y(t) completes the channel estimation; according to the Fourier transform, the convolution of the signal in the time domain corresponds...

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 discloses a measurement while drilling channel estimation method based on deep learning, and belongs to the field of communication, in particular to the technical field of measuring and collecting logging data near a drill bit in a drilling process of the drill bit and transmitting the collected data to a ground system in real time. According to the method, serious influences of noise on a system are considered, data input into a learning network firstly passes through a lightweight de-noising sub-network and then passes through a sub-network completing a channel estimation function, and channel estimation is finally completed. Compared with a traditional method, the method has obviously lower mean square error performance than LS and MMSE methods; and compared with an existing advanced deep learning method, DnCENet still has obvious superiority. In addition, in the aspect of robustness, the learning network provided by the invention has superiority. The method can be used for correct guidance of frequency point and code rate selection of a drilling fluid MWD telemetry system to improve the communication quality and rate, and can also be used for frequency domain equalization of a system in the future to improve the demodulation performance of the system.

Description

technical field [0001] The invention belongs to the communication field, in particular to the technical field of measuring and collecting logging data near the drill bit during the drilling process of the drill bit, and transmitting the collected data to the ground system in real time. Background technique [0002] Measurement while drilling is a technology that can measure and collect logging data near the drill bit during drilling, and transmit the collected data to the surface system in real time. Well logging data usually includes formation property information and various drilling engineering parameters. As one of the most mature information transmission technologies currently used in drilling while drilling, the basic working principle of the drilling fluid pressure signal transmission mode is to convert the information measured downhole into control information, and apply the control information to the downhole drilling hydraulic pressure. The force signal generator ...

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 Applications(China)
IPC IPC(8): G06F30/27G06F17/14G06F119/02
CPCG06F30/27G06F17/142G06F2119/02
Inventor 陈伟郭光明杨博
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products