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

A Method of Ultrasonic Signal Processing Based on Autoencoder

An ultrasonic signal and self-encoder technology, which is applied in the direction of instruments, code conversion, calculation, etc., can solve the problems of poor compatibility of signal noise reduction and screening, high calculation cost, and large amount of calculation, so as to avoid subjectivity and one-sidedness and improve accuracy. The effect of filtering out the influence of random noise on the signal

Active Publication Date: 2021-01-19
XI AN JIAOTONG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, both of the above two methods need to set artificial thresholds according to the noise distribution, which has poor compatibility with signal noise reduction screening and has certain subjectivity; and each signal processing process requires a large amount of computation and consumes a large amount of time. Computational cost of

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
  • A Method of Ultrasonic Signal Processing Based on Autoencoder
  • A Method of Ultrasonic Signal Processing Based on Autoencoder
  • A Method of Ultrasonic Signal Processing Based on Autoencoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The invention provides an ultrasonic signal processing method based on an autoencoder. The autoencoder (Autoencoder) built by the neural network compresses and decompresses the ultrasonic A-scan signal. The relevant weight and bias variables of the function, and use this as the noise reduction

[0049] S1. Preprocessing of ultrasonic signals;

[0050] Ultrasonic A-scan signal refers to the original signal received by the ultrasonic probe, with the echo sound path and amplitude as the horizontal and vertical axes respectively. The output format of a single A-scan signal is generally a one-dimensional array, in which each element represents the echo intensity at different sound paths.

[0051] S101. Firstly, the dimension of the above-mentioned one-dimensional array is increased. In order to make the amplitude completely distributed in the two-dimensional array, firstly, each element of the one-dimensional array is rounded. In addition, the row number row of the two-dimen...

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 an ultrasonic signal processing method based on an auto-encoder. The method includes preprocessing an ultrasound signal, and then superposing samples of the ultrasonic signals,establishing and classifying a sample library of the ultrasonic signals, compressing and decompressing the ultrasonic A scanning signals through an automatic encoder established through a neural network, obtaining related weights and bias variables of the feature functions based on deep learning, and performing noise reduction processing on subsequent ultrasonic signals by taking the related weights and bias variables as noise reduction parameters. The method is good in signal noise reduction screening compatibility, small in operand and low in calculation cost, and the feature extraction accuracy of the noise reduction auto-encoder is improved.

Description

technical field [0001] The invention belongs to the technical field of industrial ultrasonic nondestructive testing, and in particular relates to an ultrasonic signal processing method based on an autoencoder. Background technique [0002] As a non-contact measurement method, non-destructive testing has been widely used in processing and manufacturing industries. According to the testing requirements, non-destructive testing methods for internal defects of the tested object include: digital ray testing, ultrasonic testing and industrial CT testing. Since digital ray detection requires radiation as an energy source, its operation is highly professional and has certain damage to the human body; although industrial CT detection has high detection accuracy, it is costly and low in detection efficiency, and due to the above two types of detection equipment Due to its large size, online detection and on-site detection cannot be realized. The ultrasonic testing equipment is relat...

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): G06K9/00H03M7/30
Inventor 李兵高飞陈磊魏翔贺琛李应飞
Owner XI AN JIAOTONG 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