Artificial Intelligence-Enabled Crack Length Estimation From Acoustic Emission Signal Signatures

被引:2
|
作者
Ennis, Shane [1 ]
Giurgiutiu, Victor [1 ]
机构
[1] Univ South Carolina, Dept Mech Engn, Columbia, SC 29208 USA
来源
JOURNAL OF NONDESTRUCTIVE EVALUATION, DIAGNOSTICS AND PROGNOSTICS OF ENGINEERING SYSTEMS | 2024年 / 7卷 / 01期
关键词
acoustic emission; damage classification; diagnostic feature extraction; elastic wave; prognosis; sensors; ultrasonics; CLASSIFICATION; GROWTH; STEEL;
D O I
10.1115/1.4064011
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
This article addresses the classification of fatigue crack length using artificial intelligence (AI) applied to acoustic emission (AE) signals. The AE signals were collected during fatigue testing of two specimen types. One specimen type had a 1-mm hole for crack initiation. The other specimen type had a 150-mu m wide slit of various lengths. Fatigue testing was performed under stress intensity factor control to moderate crack advancement. The slit specimen produced AE signals only from crack advancement at the slit tips, whereas the 1-mm hole specimens produced AE signals from both crack tip advancement and crack rubbing or clapping. The AE signals were captured with a piezoelectric wafer active sensor (PWAS) array connected to MISTRAS instrumentation and aewin software. The collected AE signals were preprocessed using time-of-flight filtering and denoising. Choi Williams transform converted time domain AE signals into spectrograms. To apply machine learning, the spectrogram images were used as input data for the training, validation, and testing of a GoogLeNet convolutional neural network (CNN). The CNN was trained to sort the AE signals into crack length classes. CNN performance enhancements, including synthetic data generation and class balancing, were developed. A three-class example with crack lengths of (i) 10-12 mm, (ii) 12-14 mm, and (iii) 14-16 mm is provided. Our AI approach was able to classify the AE signals into these three classes with 91% accuracy, thus proving that the AE signals contain sufficient information for crack estimation using an AI-enabled approach.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] An Artificial Intelligence Approach to Fatigue Crack Length Estimation from Acoustic Emission Waves in Thin Metallic Plates
    Garrett, Joseph Chandler
    Mei, Hanfei
    Giurgiutiu, Victor
    APPLIED SCIENCES-BASEL, 2022, 12 (03):
  • [2] Artificial Intelligence-Enabled Science Poetry
    Kirmani, Ahmad R.
    ACS ENERGY LETTERS, 2022, 8 (01) : 574 - 576
  • [3] Artificial intelligence-enabled healthcare delivery
    Reddy, Sandeep
    Fox, John
    Purohit, Maulik P.
    JOURNAL OF THE ROYAL SOCIETY OF MEDICINE, 2019, 112 (01) : 22 - 28
  • [4] Artificial intelligence-enabled smart city construction
    Jiang, Yanxu
    Han, Linfei
    Gao, Yifang
    JOURNAL OF SUPERCOMPUTING, 2022, 78 (18): : 19501 - 19521
  • [5] Artificial intelligence-enabled enterprise information systems
    Zdravkovic, Milan
    Panetto, Herve
    ENTERPRISE INFORMATION SYSTEMS, 2022, 16 (05)
  • [6] Prediction of certainty in artificial intelligence-enabled electrocardiography
    Demolder, Anthony
    Nauwynck, Maxime
    De Pauw, Michel
    De Buyzere, Marc
    Duytschaever, Mattias
    Timmermans, Frank
    De Pooter, Jan
    JOURNAL OF ELECTROCARDIOLOGY, 2024, 83 : 71 - 79
  • [7] Artificial intelligence-enabled decision support in nephrology
    Tyler J. Loftus
    Benjamin Shickel
    Tezcan Ozrazgat-Baslanti
    Yuanfang Ren
    Benjamin S. Glicksberg
    Jie Cao
    Karandeep Singh
    Lili Chan
    Girish N. Nadkarni
    Azra Bihorac
    Nature Reviews Nephrology, 2022, 18 : 452 - 465
  • [8] Artificial intelligence-enabled smart city construction
    Yanxu Jiang
    Linfei Han
    Yifang Gao
    The Journal of Supercomputing, 2022, 78 : 19501 - 19521
  • [9] A BREAKTHROUGH IN ARTIFICIAL INTELLIGENCE-ENABLED MATERIALS DISCOVERY
    Bailey, Mary Page
    Chemical Engineering (United States), 2021, 128 (01):
  • [10] Clinical Evaluation of Artificial Intelligence-Enabled Interventions
    Hogg, H. D. Jeffry
    Martindale, Alexander P. L.
    Liu, Xiaoxuan
    Denniston, Alastair K.
    INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2024, 65 (10)