Improving the evaluation sensitivity of an ultrasonic pulse echo technique using a neural network classifier

被引：6
|
作者：
Thavasimuthu, M
Rajagopalan, C
Kalyanasundaram, P
Raj, B
机构：
[1] Division for PIE and NDT Development, Indira Gandhi Ctr. for Atom. Res., Kalpakkam
来源：
NDT & E INTERNATIONAL | 1996年 / 29卷 / 03期
关键词：
multiparameter approach; neural network classifier; weak signals; signal classification; ultrasonic testing;
D O I：
10.1016/0963-8695(96)80001-5
中图分类号：
TB3 [工程材料学];
学科分类号：
0805 ; 080502 ;
摘要：
In this paper, the use of an artificial neural network (ANN) for classifying weak ultrasonic signals has been attempted. The limitations of using a single conventional parameter for signal detection and classification (namely peak amplitude alone) are highlighted. Use of a multi-parameter approach is suggested. The ANN used is a multi-layered, feedforward, error-backpropagation network. Results are compared with those of conventional approaches. Copyright (C) 1996 Elsevier Science Ltd
引用
收藏
页码：175 / 179
页数：5
相关论文
共 50 条
  • [41] Fabric wrinkle evaluation using laser triangulation and neural network classifier
    Su, J
    Xu, BG
    OPTICAL ENGINEERING, 1999, 38 (10) : 1688 - 1693
  • [42] Observation and control of solidification processes by ultrasonic pulse-echo technique
    Drevermann, A
    Pickmann, C
    Sturz, L
    Zimmermann, G
    2004 IEEE Ultrasonics Symposium, Vols 1-3, 2004, : 537 - 540
  • [43] A neural network based classifier for ultrasonic raw data of the myocardium
    Kahl, L
    Orglmeister, R
    Schmailzl, KJG
    1997 IEEE ULTRASONICS SYMPOSIUM PROCEEDINGS, VOLS 1 & 2, 1997, : 1173 - 1176
  • [44] Improving Neural Network Classifier Using Gradient-Based Floating Centroid Method
    Islam, Mazharul
    Liu, Shuangrong
    Zhang, Xiaojing
    Wang, Lin
    NEURAL INFORMATION PROCESSING, ICONIP 2019, PT V, 2019, 1143 : 423 - 431
  • [45] Evaluation of small defects in carbon fibre reinforced composites using ultrasonic pulse echo amplitude
    Wong, BS
    Sheng, TK
    Guo, NQ
    Guan, TC
    INTERNATIONAL CONFERENCE ON EXPERIMENTAL MECHANICS: ADVANCES AND APPLICATIONS, 1997, 2921 : 177 - 181
  • [46] Determination of an ultrasonic transducer's sensitivity and impedance in a pulse-echo setup
    Lopez-Sanchez, Ana L.
    Schmerr, Lester W., Jr.
    IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL, 2006, 53 (11) : 2101 - 2112
  • [47] Prediction and sensitivity analysis of compressive strength in segregated lightweight concrete based on artificial neural network using ultrasonic pulse velocity
    Tenza-Abril, A. J.
    Villacampa, Y.
    Solak, A. M.
    Baeza-Brotons, F.
    CONSTRUCTION AND BUILDING MATERIALS, 2018, 189 : 1173 - 1183
  • [48] A Pulse Compression Technique for Improving the Temporal Resolution of Ultrasonic Testing
    Jiao, Jingpin
    Ma, Ting
    Hou, Song
    Wu, Bin
    He, Cunfu
    JOURNAL OF TESTING AND EVALUATION, 2018, 46 (03) : 1238 - 1249
  • [49] Improving radar observations of precipitation with a Meteosat neural network classifier
    Pankiewicz, GS
    Johnson, CJ
    Harrison, DL
    METEOROLOGY AND ATMOSPHERIC PHYSICS, 2001, 76 (1-2) : 9 - 22
  • [50] Improving radar observations of precipitation with a Meteosat neural network classifier
    G. S. Pankiewicz
    C. J. Johnson
    D. L. Harrison
    Meteorology and Atmospheric Physics, 2001, 76 : 9 - 22
12345