While drilling measurement signal processing method based on wavelet denoising and neural network identification

A technology of neural network identification and measurement while drilling, applied in neural learning method, biological neural network model, measurement and other directions, can solve the problem of inability to realize measurement while drilling signal processing, etc., and achieve the effect of strong signal recognition ability and high processing speed.

Inactive Publication Date: 2018-06-15
SHANDONG UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above-mentioned J-wave detection method is applied to the technical field of ECG signals to remove low-frequency signals, and cannot realize the processing of measurement signals while drilling

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
  • While drilling measurement signal processing method based on wavelet denoising and neural network identification
  • While drilling measurement signal processing method based on wavelet denoising and neural network identification
  • While drilling measurement signal processing method based on wavelet denoising and neural network identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 1 shown.

[0047] A measurement-while-drilling signal processing method based on wavelet denoising and neural network identification, which processes the noisy signal obtained by simulating downhole parameters, including the following steps:

[0048]1) Analyze the downhole signal containing noise; transform the time domain signal into a frequency domain signal by fast Fourier transform to obtain the frequency distribution of the signal, and then obtain the frequency distribution of the useful signal and the frequency distribution of the noise signal to prepare for the filtering operation ;Such as figure 2 , Figure 4 shown; by observation Figure 4 It can be seen that there are signals around the frequency 0~0.8Hz (useful signal), 1.2Hz, 2.3Hz, 3.3Hz, 4.4Hz and 6.5Hz;

[0049] 2) Denoising the downhole signal containing noise by wavelet transform to obtain the denoising signal; the specific method of denoising the downhole signal containing noise by ...

Embodiment 2

[0054] The measurement-while-drilling signal processing method based on wavelet denoising and neural network identification as described in Embodiment 1, further, the BP neural network in the step 3) is a multi-layer feed-forward neural network, and the multi-layer feed-forward The neural network includes an input layer, a hidden layer and an output layer; the transfer function of the BP neural network is a logarithmic S-type function, that is, y=logsig(x); y∈(0,1); where, x is any input data, y is the corresponding output data, and the value range of y is 0~1.

Embodiment 3

[0056] Such as Figure 7 shown.

[0057] The measurement-while-drilling signal processing method based on wavelet denoising and neural network identification as described in Embodiment 2, further,

[0058] 3.1) The forward propagation process of the signal:

[0059] 3.1.1) The input of the i-th node in the hidden layer Among them, X1 is the input of the input layer, ω i，j is the weight of the input layer, i represents the i-th node of the hidden layer, and j represents the j-th node of the input layer; β n Is the threshold of the hidden layer, Y1 is the output of the output layer; M=9; n=1,2,3...M;

[0060] 3.1.2) The output of the i-th node in the hidden layer is O i = θ(net(i));

[0061] 3.1.3) The output Y1 of the output layer=φ[∑(O i · ω k,i )+a1]; k represents the kth node of the output layer; the value range of Y1 is (0,1), and a1 is the threshold of the output layer; the independent variable ω in the summation symbol k,i is the threshold between the hidden lay...

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 while drilling measurement signal processing method based on wavelet denoising and neural network identification. In a while drilling welllogging system, the interference oneffective signal obtaining is made by various noises caused by a slush pump and the like. According to the invention, noises generated during a while drilling welllogging process are analyzed; wavelet transform denoising is carried out and thus signal identification is carried out by a BP neural network pulse; and after denoising, effective signals with the frequency from 0 to 0.8Hz are obtainedand neural network identification is carried out to obtain pulses signals having the same number and the amplitudes being 1.

Description

technical field [0001] The invention relates to a measurement-while-drilling signal processing method based on wavelet denoising and neural network identification, which belongs to the technical field of logging-while-drilling. Background technique [0002] MWD (Measurement While Drilling) is a technology that uses drilling fluid as the transmission medium and the drilling fluid pressure pulse as the transmission mode to measure downhole data. Logging while drilling can not only be used for geosteering and drilling guidance, but also evaluate the oil and gas content of complex wells and complex formations. It has become a hot spot for oil service companies in the world to research and continuously introduce new methods and technologies. In recent years, major service companies have launched new logging-while-drilling data transmission systems one after another. The efficiency of logging-while-drilling data transmission has been continuously improved, which is more beneficial...

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): G06K9/00G06N3/08E21B47/18
CPCG06N3/084E21B47/18G06F2218/00G06F2218/06
Inventor 李康曹云飞
Owner SHANDONG UNIV
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap