Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic picking method for ultrasonic test waveform first arrival of shale

An automatic picking and ultrasonic technology, applied in the basic research field of petrophysics of oil and gas exploration, can solve the problems of limited data processing speed, difficulty in ensuring consistency, and large workload, and achieve the effect of ensuring consistency

Inactive Publication Date: 2021-07-13
CHENGDU UNIVERSITY OF TECHNOLOGY
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the face of massive seismic data, the workload of first-arrival picking is increasing, which greatly limits the speed of data processing, and manual picking is difficult to ensure the consistency of picking
The existence of these problems affects the efficiency of shale oil and gas exploration

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
  • Automatic picking method for ultrasonic test waveform first arrival of shale
  • Automatic picking method for ultrasonic test waveform first arrival of shale
  • Automatic picking method for ultrasonic test waveform first arrival of shale

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] A method for automatically picking up the first arrival of a shale ultrasonic test waveform, comprising the following steps:

[0044] (1) Get as figure 1 For the synthesized microseismic data shown, the non-aliasing sampling time of the training data is determined, and the training input data is sampled gather by gather according to the selected sampling time window to form a one-dimensional vector combination as a training data set.

[0045] (2) Use the supervised convolutional neural network algorithm to train the vector combination. The training flow chart is as follows: figure 2shown. In this embodiment, the convolution layer and the pooling layer algorithm are selected as the hidden layer to achieve the goal of local connection and weight sharing and obtain a waveform separator, which can separate the input signal or waveform into effective waves and Invalid wave, in which the effective waveform is assigned a value of 1, and the invalid waveform is assigned a va...

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 shale ultrasonic test waveform first arrival automatic pickup method. The method comprises the following steps: acquiring rock ultrasonic experiment test data of a known shale reservoir; sampling the test data based on the non-aliasing time and forming vectors, and selecting a part of gathers as a training number set; according to the training number set, training by using a supervised convolutional neural network algorithm to obtain a waveform classifier; obtaining ultrasonic data of target shale, performing waveform classification on the ultrasonic data by using the waveform classifier, and dividing the ultrasonic data into waveform data and non-waveform data; determining a non-zero point of the waveform data, and based on the non-zero point, extracting an effective time window through a vertical continuation method; and performing waveform attribute feature clustering analysis on the waveform signal in the effective time window by using an unsupervised fuzzy clustering machine learning algorithm, and obtaining a waveform first arrival according to a clustering analysis result. According to the method, the shale ultrasonic test waveform first arrival can be stably, efficiently and automatically picked up.

Description

technical field [0001] The invention relates to the technical field of rock physics basic research for oil and gas exploration, in particular to an automatic picking method for the first arrival of shale ultrasonic test waveforms. Background technique [0002] In the field of oil and gas exploration, rock physics is the common basis and bridge connecting the three disciplines of geology, geophysics, and petroleum engineering. It mainly studies the elastic properties of rocks; yield. Combining rock physics, logging analysis, geological analysis, and seismic attributes, lithology, fluid, and hydrate can be predicted. The development characteristics of rock physics provide a solid foundation for the development of oil and gas detection technology. With a deeper understanding of the geological characteristics of rocks, it plays a decisive role in linking the structural characteristics of rocks with seismic elastic parameters, and the most important thing is the elastic response...

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): G01V1/30G01V1/28G01V1/50
CPCG01V1/307G01V1/288G01V1/50
Inventor 谢剑勇张俊杰方艳萍付京城张关磊王兴建曹俊兴
Owner CHENGDU UNIVERSITY OF TECHNOLOGY