A novel ultrasonic inspection method of the heat exchangers based on circumferential waves and deep neural networks

被引:6
|
作者
Malikov, Azamatjon Kakhramon Ugli [1 ]
Cho, Younho [2 ]
Kim, Young H. [3 ]
Kim, Jeongnam [1 ]
Kim, Hyung-Kyu [4 ]
机构
[1] Pusan Natl Univ, Grad Sch Mech Engn, Busan, South Korea
[2] Pusan Natl Univ, Sch Mech Engn, Busan 46241, South Korea
[3] Pusan Natl Univ, Inst Nucl Safety & Management, Busan, South Korea
[4] Korea Atom Energy Res Inst, Nucl Fuel Safety Res Div, Daejeon, South Korea
基金
新加坡国家研究基金会;
关键词
ultrasonic guided waves; heat exchangers; circumferential wave; continuous wavelet transform (CWT); leaky guided waves; deep neural networks; TRANSFORM METHOD; DEFECT; PIPE;
D O I
10.1177/00368504221146081
中图分类号
G40 [教育学];
学科分类号
040101 ; 120403 ;
摘要
The heat exchanger (HE) is an important component of almost every energy generation system. Periodic inspection of the HEs is particularly important to keep high efficiency of the entire system. In this paper, a novel ultrasonic water immersion inspection method is presented based on circumferential wave (CW) propagation to detect defective HE. Thin patch-type piezoelectric elements with multiple resonance frequencies were adopted for the ultrasonic inspection of narrow-spaced HE in an immersion test. Water-filled HE was used to simulate defective HE because water is the most reliable indicator of the defect. The HE will leak water no matter what the defect pattern is. Furthermore, continuous wavelet transform (CWT) was used to investigate the received CW, and inverse CWT was applied to separate frequency bands corresponding to the thickness and lateral resonance modes of the piezoelectric element. Different arrangements of intact and leaky HE were tested with several pairs of thin piezoelectric patch probes in various instrumental setups. Also, direct waveforms in the water without HE were used as reference signals, to indicate instrumental gain and probe sensitivity. Moreover, all filtered CW corresponding to resonance modes together with the direct waveforms in the water were used to train the deep neural networks (DNNs). As a result, an automatic HE state classification method was obtained, and the accuracy of the applied DNN was estimated as 99.99%.
引用
收藏
页数:26
相关论文
共 50 条
  • [21] A Novel Clustering-Based Filter Pruning Method for Efficient Deep Neural Networks
    Wei, Xiaohui
    Shen, Xiaoxian
    Zhou, Changbao
    Yue, Hengshan
    ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2020, PT II, 2020, 12453 : 245 - 258
  • [22] A novel deep neural networks based path prediction
    Joshi, Upasna
    Kumar, Rajiv
    CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2020, 23 (04): : 2915 - 2924
  • [23] A novel deep neural networks based path prediction
    Upasna Joshi
    Rajiv Kumar
    Cluster Computing, 2020, 23 : 2915 - 2924
  • [24] Condition-based inspection policies for boiler heat exchangers
    Huy Truong-Ba
    Cholette, Michael E.
    Borghesani, Pietro
    Ma, Lin
    Kent, Geoff
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2021, 291 (01) : 232 - 243
  • [25] Automatic inspection machine for maize kernels based on deep convolutional neural networks
    Ni, Chao
    Wang, Dongyi
    Vinson, Robert
    Holmes, Maxwell
    Tao, Yang
    BIOSYSTEMS ENGINEERING, 2019, 178 : 131 - 144
  • [26] Neural networks for cost estimation of shell and tube heat exchangers
    Duran, Orlando
    Rodriguez, Nibaldo
    Consalter, Luiz Airton
    IMECS 2008: INTERNATIONAL MULTICONFERENCE OF ENGINEERS AND COMPUTER SCIENTISTS, VOLS I AND II, 2008, : 1584 - 1589
  • [27] Neural networks for cost estimation of shell and tube heat exchangers
    Duran, Orlando
    Rodriguez, Nibaldo
    Consalter, Luiz Airton
    EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (04) : 7435 - 7440
  • [28] Monitoring of heat exchangers in preheat trains using neural networks
    Rimac, Nikola
    Andrijic, Zeljka Ujevic
    PETROLEUM SCIENCE AND TECHNOLOGY, 2024,
  • [29] Ultrasonic tomography imaging enhancement approach based on deep convolutional neural networks
    Malikov, Azamatjon Kakhramon Ugli
    Cuenca, Manuel Fernando Flores
    Kim, Beomjin
    Cho, Younho
    Kim, Young H.
    JOURNAL OF VISUALIZATION, 2023, 26 (05) : 1067 - 1083
  • [30] Ultrasonic tomography imaging enhancement approach based on deep convolutional neural networks
    Azamatjon Kakhramon ugli Malikov
    Manuel Fernando Flores Cuenca
    Beomjin Kim
    Younho Cho
    Young H. Kim
    Journal of Visualization, 2023, 26 : 1067 - 1083