Double-layer tubular column pulse eddy current data denoising method based on noise model

A pulsed eddy current and noise model technology, applied in neural learning methods, biological neural network models, pattern recognition in signals, etc., can solve problems that are difficult to adapt to actual systems, do not consider the mixture of multiple noises, and do not consider real noise.

Pending Publication Date: 2020-12-15
ZHEJIANG SHUREN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To sum up, the current pulse eddy current denoising method has the following three problems: first, Gaussian white noise is artificially added for denoising, which does not consider the real noise in the actual system, so it is difficult to adapt to the actual system; There is still some room for improvement in the denoising effect when the pure signal and the noise signal are effectively known; 3. The situation of mixing multiple noises is not considered

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
  • Double-layer tubular column pulse eddy current data denoising method based on noise model
  • Double-layer tubular column pulse eddy current data denoising method based on noise model
  • Double-layer tubular column pulse eddy current data denoising method based on noise model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0077] This embodiment discloses a noise model-based denoising method for pulsed eddy current data of a double-layer string, such as Figure 1 to Figure 3 As shown, it mainly includes the following steps:

[0078]Step 1) Starting from the deepest part of the double-layer pipe string, use the longitudinal long probe A of the electromagnetic flaw detection tester MTD-J to detect the double-layer pipe string of the weak magnetic field, and obtain a total of 11 point data consisting of A1-A11 Pulsed eddy current testing data. After one sampling period, the instrument moves up to continue data acquisition. The above data collection is repeated until the pulsed eddy current data collection of the entire double-layer string of weak magnetic tubing is completed, and the pulsed eddy current detection data composed of 11 point data at each depth is obtained. Among them, longitudinal probe A can collect 11 signals A1-A11, the sampling time range is 0.015-0.09ms, and the sampling point ...

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 double-layer tubular column pulse eddy current data denoising method based on a noise model, which comprises the following steps of: establishing four noise models by analyzing the characteristics of electromagnetic noise, jitter noise, temperature noise and oil tube eccentric noise in real noise; respectively designing a network model based on a linear noise parameter,a network model based on a sine jitter noise parameter and a network model based on a Gaussian white noise parameter, adding depth weight coefficients into the three noise components, and constructingan overall deep learning model based on noise model parameters suitable for solving by a deep learning method; constructing a simulation model based on material attributes, spatial dimensions, physical field interfaces and the like of the double-layer tubular column and performing simulating to obtain a pure signal of the double-layer tubular column as a training set; training the eddy current data of different well sections according to the overall deep learning model, obtaining noise model parameters, obtaining a noise model in the pulse eddy current signal of the whole double-layer tubularcolumn, and carrying out the adaptive denoising of the double-layer tubular column according to the noise model.

Description

technical field [0001] The invention relates to the technical field of nondestructive testing, in particular to a noise model-based denoising method for pulse eddy current data of a double-layer pipe string. Background technique [0002] In recent years, with the rapid development of my country's social economy, the demand for energy has risen sharply. Oil and gas energy, as an important energy source in the industrial field, has also seen an increasing demand. According to relevant statistics, the apparent consumption of natural gas in my country reached 2803×108 cubic meters in 2019, a year-on-year increase of 17.5%, and the daily peak gas consumption exceeded 10×108 cubic meters. Among them, high-sulfur gas fields naturally have deep buried gas layers, high H content 2 S, high pressure, high output and other characteristics. Due to the high content of H 2 S and CO 2 , the downhole corrosion environment is harsh. During the commissioning operation and production proces...

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): G06K9/00G06K9/62G06N3/04G06N3/08E21B47/00
CPCG06N3/08E21B47/00G06N3/045G06F2218/04G06F2218/12G06F18/214
Inventor 陈友荣施佳椰刘半藤周莹王章权金合丽
Owner ZHEJIANG SHUREN 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