CN112334921A - 解释用于检测固体的探伤仪读出和数字信号的方法 - Google Patents

解释用于检测固体的探伤仪读出和数字信号的方法 Download PDF

Info

Publication number
CN112334921A
CN112334921A CN201980039939.XA CN201980039939A CN112334921A CN 112334921 A CN112334921 A CN 112334921A CN 201980039939 A CN201980039939 A CN 201980039939A CN 112334921 A CN112334921 A CN 112334921A
Authority
CN
China
Prior art keywords
digital signals
flaw detector
interpreting
solids
detector readout
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201980039939.XA
Other languages
English (en)
Inventor
R·N·尤雷夫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Neural Network Scanner Co ltd
Original Assignee
Neural Network Scanner Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Neural Network Scanner Co ltd filed Critical Neural Network Scanner Co ltd
Publication of CN112334921A publication Critical patent/CN112334921A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/192—Recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references
    • G06V30/194—References adjustable by an adaptive method, e.g. learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
  • Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

一种解释用于检测固体的探伤仪读出和数字信号的方法，用于将对固体进行无损检测时产生的探伤仪读出或数字信号的形式的数据，根据预期用途转换成机器可读形式、人类可读形式或控制命令。

Description

解释用于检测固体的探伤仪读出和数字信号的方法
本发明涉及固体的无损检测领域。现有许多已知的固体的无损检测方法，但是，目前，由于必须有复杂的解释算法或人工参与过程，它们的使用受到了限制。
在提出的技术方案中，该任务基于机器学习方法，首先通过神经网络解决。检测产生的数字信号(1)被划分为信息区域(2)，这些区域被标记以确定检测中的特性。之后，通过神经网络计算出所需特性的特征。为了测试训练质量，使用测试读出测试标记的数字信号信息区域。这导致经过测试的、训练后的神经网络(3)，其中将数字信号传输到该神经网络，并通过设备或用户所需的形式，是否存在所需特性的信息由一个单独界面返回(4)。为了持续提高训练质量，通过用户对解释结果的评估来执行对神经网络的附加训练(5)。通过交叉验证方法评估执行的识别质量。

Claims (1)

1.一种解释用于检测固体的探伤仪读出和数字信号的方法，其特征在于，所述解释是通过对幅值-频率和频谱特征的标记数据进行过预训练的神经网络来执行，并且能够获得通过交叉验证方法进行检查检测关于固体所需特性是否存在的人类可读或机器可读的响应，或者获得基于所需特性是否存在的控制命令。
CN201980039939.XA 2018-04-23 2019-03-04 解释用于检测固体的探伤仪读出和数字信号的方法 Pending CN112334921A (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
RU2018115274A RU2685744C1 (ru) 2018-04-23 2018-04-23 Способ расшифровки дефектограмм и оцифрованных сигналов исследования твёрдых тел
RU2018115274 2018-04-23
PCT/RU2019/050024 WO2019209144A1 (ru) 2018-04-23 2019-03-04 Способ расшифровки дефектограмм и оцифрованных сигналов исследования твёрдых тел

Publications (1)

Publication Number Publication Date
CN112334921A true CN112334921A (zh) 2021-02-05

Family

ID=66314690

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201980039939.XA Pending CN112334921A (zh) 2018-04-23 2019-03-04 解释用于检测固体的探伤仪读出和数字信号的方法

Country Status (9)

Country Link
US (1) US20210042591A1 (zh)
EP (1) EP3786859A4 (zh)
JP (1) JP2021522527A (zh)
KR (1) KR20210003198A (zh)
CN (1) CN112334921A (zh)
AU (1) AU2019257862A1 (zh)
EA (1) EA202092474A1 (zh)
RU (1) RU2685744C1 (zh)
WO (1) WO2019209144A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20220101319A (ko) 2021-01-11 2022-07-19 주식회사 엘지에너지솔루션 배터리 팩, 전동 휠체어, 및 자동차

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6650779B2 (en) * 1999-03-26 2003-11-18 Georgia Tech Research Corp. Method and apparatus for analyzing an image to detect and identify patterns
US7215811B2 (en) * 2000-11-22 2007-05-08 Osama Moselhi Method and apparatus for the automated detection and classification of defects in sewer pipes
DE102007020240A1 (de) * 2007-04-24 2008-10-30 Sms Demag Ag Verfahren zur Erkennung und Klassifizierung von Oberflächenfehlern auf stranggegossenen Brammen
FR2925690B1 (fr) * 2007-12-21 2010-01-01 V & M France Controle non destructif,en particulier pour des tubes en cours de fabrication ou a l'etat fini.
US8135202B2 (en) * 2008-06-02 2012-03-13 Nec Laboratories America, Inc. Automated method and system for nuclear analysis of biopsy images
RU2505800C2 (ru) * 2012-05-10 2014-01-27 Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Национальный исследовательский Томский государственный университет" (ТГУ) Способ рентгеновской томографии и устройство для его осуществления
JP6629455B2 (ja) * 2017-02-20 2020-01-15 Ｓｅｒｅｎｄｉｐｉｔｙ株式会社 外観検査装置、照明装置、撮影照明装置

Also Published As

Publication number Publication date
RU2685744C1 (ru) 2019-04-23
US20210042591A1 (en) 2021-02-11
KR20210003198A (ko) 2021-01-11
JP2021522527A (ja) 2021-08-30
EP3786859A4 (en) 2022-01-19
WO2019209144A1 (ru) 2019-10-31
EA202092474A1 (ru) 2021-01-29
AU2019257862A1 (en) 2020-12-10
EP3786859A1 (en) 2021-03-03

Similar Documents

Publication Publication Date Title
DK2108120T3 (en) Method and device for non-destructive testing using eddy currents
Sun et al. On-line detection of eggshell crack based on acoustic resonance analysis
EP3489780A3 (en) Examining apparatus, examining method, program and recording medium
ZA200701188B (en) Use of C3a and derivatives thereof as a biomarker for colorectal ademona and/or carcinoma; diagnosis method and test system using the same
CN109932333B (zh) 声学振动和近红外光谱融合的水果坚实度测量系统和方法
CN109190272B (zh) 基于弹性波和机器学习的混凝土结构缺陷检测方法
CN102928514A (zh) 一种基于频率特征的木材应力波无损检测方法
DE10325406B4 (de) Schadensermittlung an zu prüfenden Strukturen mittels Ultraschall
KR20150088926A (ko) 음주 판별 방법, 이를 수행하기 위한 기록매체 및 단말기
WO2009134496A3 (en) Multi-threat detection portal
CN108844856B (zh) 基于冲击弹性波和机器学习的套筒灌浆缺陷无损检测方法
CN112334921A (zh) 解释用于检测固体的探伤仪读出和数字信号的方法
GB2545807A (en) Infrared thermographic porosity quantification in composite structures
US9835593B2 (en) Apparatus and method for determining cracked eggs by driving vibration
EP2629082A3 (de) Vorrichtung zur Detektion eines Partialdrucks und Verfahren zum Betreiben derselben
CN105928697A (zh) 一种燃气阀响应时间测量装置与方法
SE1450404A1 (sv) Förfarande och anordning för inspektion av strukturer med ultraljud
JP2018200217A (ja) 打音検査装置及び打音検査方法
Sheik et al. Continuous prediction in chemoresistive gas sensors using reservoir computing
Janapati et al. Fatigue crack quantification approach based on multi-path unit-cell concept in sensor network
Wirtz et al. Improved signal processing of acoustic emission for structural health monitoring using a data-driven approach
RU2660403C1 (ru) Способ беспороговой автоматической интеллектуальной регистрации сигналов акустической эмиссии устройством неразрушающего контроля
RU2637376C1 (ru) Аппроксимационный способ определения геометрических размеров дефектов сплошности в ферромагнитных изделиях и устройство для его осуществления
Batko et al. Application of wavelet methods to magnetic testing of steel ropes
Sun et al. Automated acoustic scanning of concrete bridge decks and delamination identification

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination