{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:22:43Z","timestamp":1761110563107,"version":"3.37.3"},"reference-count":41,"publisher":"Wiley","license":[{"start":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T00:00:00Z","timestamp":1606089600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009102","name":"Education Department of Jiangxi Province","doi-asserted-by":"publisher","award":["GJJ161104","GJJ161122","20171BAB206037","61903176","62001202"],"award-info":[{"award-number":["GJJ161104","GJJ161122","20171BAB206037","61903176","62001202"]}],"id":[{"id":"10.13039\/501100009102","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010857","name":"Jiangxi Provincial Department of Science and Technology","doi-asserted-by":"publisher","award":["GJJ161104","GJJ161122","20171BAB206037","61903176","62001202"],"award-info":[{"award-number":["GJJ161104","GJJ161122","20171BAB206037","61903176","62001202"]}],"id":[{"id":"10.13039\/501100010857","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["GJJ161104","GJJ161122","20171BAB206037","61903176","62001202"],"award-info":[{"award-number":["GJJ161104","GJJ161122","20171BAB206037","61903176","62001202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2020,11,23]]},"abstract":"<jats:p>Accurate and rapid defect identification based on pulsed eddy current testing (PECT) plays an important role in the structural integrity and health monitoring (SIHM) of in-service equipment in the renewable energy system. However, in conventional data-driven defect identification methods, the signal feature extraction is time consuming and requires expert experience. To avoid the difficulty of manual feature extraction and overcome the shortcomings of the classic deep convolutional network (DCNN), such as large memory and high computational cost, an intelligent defect recognition pipeline based on the general Warblet transform (GWT) method and optimized two-dimensional (2-D) DCNN is proposed. The GWT method is used to convert the one-dimensional (1-D) PECT signal to a 2D grayscale image used as the input of 2D DCNN. A compound method is proposed to optimize the baseline VGG16, a well-known DCNN, from four aspects including reducing the input size, adding batch normalization layer (BN) after every convolutional layer(Conv) and fully connection layer (FC), simplifying the FCs, and removing unimportant filters in Convs so as to reduce memory and computational costs while improving accuracy. Through a pulsed eddy current testing (PECT) experiment considering interference factors including liftoff and noise, the following conclusion can be obtained. The time-frequency representation (TFR) obtained by the GWT method not only has excellent ability in terms of the transient component analysis but also is less affected by the reduction of image size; the proposed optimized DCNN can accurately identify defect types without manual feature extraction. And compared to the baseline VGG16, the accuracy obtained by the optimized DCNN is improved by 7%, to about 99.58%, and the memory and computational cost are reduced by 98%. Moreover, compared with other well-known DCNNs, such as GoogLeNet, Inception V3, ResNet50, and AlexNet, the optimized network has significant advantages in terms of accuracy and computational cost, too.<\/jats:p>","DOI":"10.1155\/2020\/9518945","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T01:35:38Z","timestamp":1606268138000},"page":"1-18","source":"Crossref","is-referenced-by-count":4,"title":["Intelligent Defect Identification Based on PECT Signals and an Optimized Two-Dimensional Deep Convolutional Network"],"prefix":"10.1155","volume":"2020","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8430-640X","authenticated-orcid":true,"given":"Baoling","family":"Liu","sequence":"first","affiliation":[{"name":"Jiangxi Engineering Research Center of High Power Electronics and Grid Smart Metering, Nanchang Institute of Technology, Nanchang, China"}]},{"given":"Jun","family":"He","sequence":"additional","affiliation":[{"name":"State Grid Jiangxi Electric Power Research Institute, Beijing, China"}]},{"given":"Xiaocui","family":"Yuan","sequence":"additional","affiliation":[{"name":"Jiangxi Engineering Research Center of High Power Electronics and Grid Smart Metering, Nanchang Institute of Technology, Nanchang, China"}]},{"given":"Huiling","family":"Hu","sequence":"additional","affiliation":[{"name":"Jiangxi Engineering Research Center of High Power Electronics and Grid Smart Metering, Nanchang Institute of Technology, Nanchang, China"}]},{"given":"Xuan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Jiangxi Engineering Research Center of High Power Electronics and Grid Smart Metering, Nanchang Institute of Technology, Nanchang, China"}]},{"given":"Zhifang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Jiangxi Engineering Research Center of High Power Electronics and Grid Smart Metering, Nanchang Institute of Technology, Nanchang, China"}]},{"given":"Jie","family":"Peng","sequence":"additional","affiliation":[{"name":"Jiangxi Engineering Research Center of High Power Electronics and Grid Smart Metering, Nanchang Institute of Technology, Nanchang, China"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/s10033-017-0122-4"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ndteint.2016.12.003"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/j.sna.2015.12.026"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1080\/10589759.2015.1034715"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sna.2019.05.026"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/tie.2020.2973876"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2019.2951060"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1080\/10589759.2013.823608"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.3901\/jme.2006.02.063"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ndteint.2011.01.009"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2016.2514778"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/s10921-018-0545-6"},{"issue":"2","key":"13","first-page":"116","article-title":"Enhancement of pulsed eddy current response based on power spectral density after continuous wavelet transform decomposition","volume":"12","author":"A. Benyahia","year":"2018","journal-title":"International Journal of Computer and Information Engineering"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ndteint.2016.12.009"},{"issue":"5","key":"15","doi-asserted-by":"crossref","first-page":"2329","DOI":"10.1109\/JSEN.2019.2951302","article-title":"Detection and classification of defects using ECT and multi-level SVM model","volume":"20","author":"D. J. Pasadas","year":"2019","journal-title":"IEEE Sensors Journal"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ab0793"},{"article-title":"On the performance of GoogLeNet and AlexNet applied to sketches","author":"P. Ballester","key":"17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10171"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/tsm.2019.2902657"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2019.103048"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ndteint.2018.09.010"},{"issue":"15","key":"21","first-page":"4558","article-title":"A two-dimensional convolutional neural network optimization method for bearing fault diagnosis","volume":"39","author":"X. Xiong","year":"2019","journal-title":"Proceeding of the CSEE"},{"article-title":"Network trimming, a data-driven neuron pruning approach towards efficient deep architectures","year":"2016","author":"H. Hu","key":"22"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2020.107667"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2019.02.001"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ab4488"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.3390\/s20051334"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2018.07.039"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1109\/tie.2012.2206331"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsv.2014.09.025"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1109\/jsen.2018.2812848"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.21629\/jsee.2017.03.09"},{"article-title":"Pruning filters for efficient convnets","year":"2016","author":"H. Li","key":"32"},{"article-title":"The lottery ticket hypothesis, finding sparse; trainable neural networks","year":"2018","author":"J. Frankle","key":"33"},{"first-page":"2736","article-title":"Learning efficient convolutional networks through network slimming","author":"Z. Liu","key":"34"},{"article-title":"Pruning convolutional neural networks for resource efficient inference","year":"2016","author":"P. Molchanov","key":"35"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ndteint.2009.01.005"},{"key":"37","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2019.2914257"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2014.2314061"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"K. Simonyan","key":"40"},{"article-title":"Batch normalization, accelerating deep network training by reducing internal covariate shift","year":"2015","author":"S. Ioffe","key":"41"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2020\/9518945.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2020\/9518945.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2020\/9518945.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T17:30:43Z","timestamp":1669743043000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/complexity\/2020\/9518945\/"}},"subtitle":[],"editor":[{"given":"Kailong","family":"Liu","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,11,23]]},"references-count":41,"alternative-id":["9518945","9518945"],"URL":"https:\/\/doi.org\/10.1155\/2020\/9518945","relation":{},"ISSN":["1099-0526","1076-2787"],"issn-type":[{"type":"electronic","value":"1099-0526"},{"type":"print","value":"1076-2787"}],"subject":[],"published":{"date-parts":[[2020,11,23]]}}}