In order to solve the problems including poor signal denoising effect, low recognition rate, and poor real-time performance in wire rope magnetic flux leakage (MFL) testing, this paper proposes a new algorithm combining kernel extreme learning machine (KELM) with compressed sensing wavelet (CSW). Firstly, we consider a new mechanism and regularized orthogonal matching pursuit (ROMP) into CSW, and combine double-density wavelet transform (DD-DWT) to improve the result of wire rope signal noise reduction; Then, an effective normalization method is developed to improve the accuracy of classification. Finally, the detection accuracy and efficiency in wire rope quantitative identification are ameliorated through KELM. The effectiveness and novelties of the proposed algorithms are verified by the experimental platform based on unsaturated magnetic excitation non-destructive testing (NDT) device.
ZhanW.X., Research on singal process and quantiative recongnition method of broken wires wire rope, Ph.D. Qingdao Technological University, 2013.
2.
TanX.J. and ZhangJ.W., Evaluation of composite wire ropes using unsaturated magnetic excitation and reconstruction image with super-resolution, Applied Sciences8(5) (2018), 767.
3.
TianJ.ZhouJ.WangH. and MengG., Literature review of research on the technology of wire rope nondestructive inspection in china and abroad, EDP Sciences22 (2015), 03025.
4.
KaurD.AroraR.ChhabraS. and SharmaS, Characterization of LF and LMA signal of wire rope tester, International Journal of Advanced Research in Computer Science8(5) (2017).
5.
TanX.J. and ZhangJ.W., Study of unsaturated magnetic image processing in wire rope aplication, International Symposium on. IEEE2 (2017), 344–347.
6.
TianJ.ZhouJ. and WangH., Literature review of research on the technology of wire rope nondestructive inspection in china and abroad, EDP Sciences22 (2015), 03025, doi:10.1051/matecconf/20152203025.
7.
YanX.ZhangD. and PanS., Online nondestructive testing for fine steel wire rope in electromagnetic interference environment, NDT & E International92 (2017), 75–81, doi:10.1016/j.ndteint.2017.07.017.
8.
ZhaoM., Research on the technology of quantitative detection of local defect of wire rope by magnetic flux leakage, Ph.D. Harbin Institute of Technology, 2012.
9.
KaurA.GuptaA. and AggarwalH., Non-destructive evaluation and development of a new wire rope tester using parallely magnetized NdFeB magnet segments, Journal of Nondestructive Evaluation37(3) (2018), 61, doi:10.1007/s1092.
10.
ZhangJ.TanX. and ZhengP., Non-destructive detection of wire rope discontinuities from residual magnetic field images using the Hilbert-Huang transform and compressed sensing, Sensors17(3) (2017), 608, doi:10.3390/s17030608.
11.
ZhangJ. and TanX., Quantitative inspection of remanence of broken wire rope based on compressed sensing, Sensors16(9) (2016), 1366, doi:10.3390/s16091366.
12.
RaisutisR.KazysR. and MazeikaL., Propagation of ultrasonic guided waves in composite multi-wire ropes, Materials9(6) (2016), 451, doi:10.3390/ma9060451.
13.
DuW.Z.MaB.Z. and ZhengX., Finite element analysis on the wire breaking rule of 1 × 7IWS steel wire rope, EDP Sciences108 (2017), 01002, doi:10.1051/matecconf/201710801002.
14.
MaX.SuS. and WangW., Damage location and numerical simulation for steel wire under torsion based on magnetic memory method, International Journal of Applied Electromagnetics and Mechanics (2019), 1–24, (Preprint).
15.
FengB.KangY. and SunY., Influence of motion induced eddy current on the magnetization of steel pipe and MFL signal, International Journal of Applied Electromagnetics and Mechanics52(1–2) (2016), 357–362.
16.
CaoY.N.ZhangD.L. and XuD.G., Study on algorithms of wire rope localized flaw quantitative analysis based on three-dimensional magnetic flux leakage, Dianzi Xuebao (Acta Electronica Sinica)35(6) (2007), 1170–1173.
17.
ZhangJ.ZhengP. and TanX., Recognition of broken wire rope based on remanence using EEMD and wavelet methods, Sensors18(4) (2018), 1110, doi:10.3390/s18041110.
18.
YanX.ZhangD. and ZhaoF., Improve the signal to noise ratio and installation convenience of the inductive coil for wire rope nondestructive testing, NDT & E International92 (2017), 221–227, doi:10.1016/j.ndteint.2017.09.005.
19.
WangH.Y.TianJ. and MengG.Y., Study on the adaptive wavelet threshold denoising method for coal mine hoisting wire rope signals based on novel thresholding function, Insight-Non-Destructive Testing and Condition Monitoring60(2) (2018), 99–103, doi:10.1784/insi.2018.60.2.99.
20.
XuT., Gap measurement of point machine using adaptive wavelet threshold and mathematical morphology, Sensors16(12) (2016), 2006, doi:10.3390/s16122006.
21.
ChengC.PanQ.WangS., Research on MEMS gyroscope signal denoising based compressed sensing theory, Chinese Journal of Scientific Instrument33(4) (2012), 769–773.
22.
LiuQ.J., Time-frequency analysis and simulation of the watershed suspended sediment concentration based on the Hilbert-Huang transform (HHT) and artificial neural network (ANN) methods: A case study in the Loess Plateau of China, Catena179 (2019), 107–118, doi:10.1016/j.catena.2019.03.042.
23.
LiZ.DengY. and HuangH., ECG signal compressed sensing using the wavelet tree model, in: 2015 8th International Conference on Biomedical Engineering and Informatics (BMEI), IEEE, 2015, pp. 194–199, doi:10.1109/BMEI.2015.7401499.
24.
ZhangD.ZhaoM. and ZhouZ., Characterization of wire rope defects with gray level co-occurrence matrix of magnetic flux leakage images, Journal of Nondestructive Evaluation32(1) (2013), 37–43, doi:10.1007/s10921-012-0156-6.
25.
MallatS., A Wavelet Tour of Signal Processing, Elsevier, 1999.
26.
MallatS., A theory for multiresolution signal decomposition: the wavelet representation, IEEE Transactions on Pattern Analysis & Machine Intelligence7 (1989), 674–693, doi:10.1109/34.192463.
27.
J.J.Han and MirkoB., Microseismic and seismic denoising via ensemble empirical mode decomposition and adaptive thresholding, Geophysics80(6) (2015), 69–S80, doi:10.1190/geo2014-0423.1.
28.
GholipourA., Super resolution reconstruction in frequency, image, and wavelet domains to reduce through plane partial voluming in MRI, Medical Physics42(12) (2015), 6919–6932, doi:10.1118/1.4935149.
29.
QinY.N.GaoG.H. and LianM.J., Wire rope fault diagnosis based on wavelet analysis and support vector machine (SVM), Trans Tech Publications971 (2014), 1396–1399, doi:10.4028/www.scientific.net/AMR.971-973.1396.
30.
MeyerD. and WienF.T., Support vector machines, The Interface to libsvm in package e1071, 28 (2015).
31.
WanZ.YiS. and LiK., Diagnosis of elevator faults with LS-SVM based on optimization by K-CV, Journal of Electrical and Computer Engineering70 (2015), doi:10.1155/2015/935038.
32.
BuiD.T., Spatial prediction of rainfall-induced landslides for the Lao Cai area (Vietnam) using a hybrid intelligent approach of least squares support vector machines inference model and artificial bee colony optimization, Landslides14(2) (2017), 447–458, doi:10.1007/s10346-016-0711-9.
33.
CilimkovicM., Neural Networks and Back Propagation Algorithm, Vol. 15, Institute of Technology Blanchardstown, Blanchardstown Road North Dublin, 2015.
34.
ZhangD.ZhaoM. and ZhouZ., Quantitative inspection of wire rope discontinuities using magnetic flux leakage imaging, Materials Evaluation70(7) (2012).
35.
NeedellD. and RomanV., Signal recovery from incomplete and inaccurate measurements via regularized orthogonal matching pursuit, arXiv preprint arXiv, 0712.1360 (2007).
36.
RoyV. and ShailjaS., A NLMS based approach for artifacts removal in multichannel EEG signals with ICA and double density wavelet transform, in: 2015 Fifth International Conference on Communication Systems and Network Technologies, IEEE, 2015. doi:10.1109/CSNT.2015.61.
37.
HuangG.B.ZhouH.DingX. and ZhangR., Extreme learning machine for regression and multiclass classification, IEEE Trans. Systems, Man, Cybernetics: Part B42(2) (2012), 513–529, doi:10.1109/TSMCB.2011.2168604.
38.
LuH.DuB. and LiuJ., A kernel extreme learning machine algorithm based on improved particle swam optimization, Memetic Computing9(2) (2017), 121–128, doi:10.1007/s12293-016-0182-5.
39.
ZhangL.ZhangD. and TianF., SVM and ELM: who wins? Object recognition with deep convolutional features from imagenet, in: Proceedings of ELM-2015 Volume 1, Springer, Cham, 2016, pp. 249–263. doi:10.1007/978-3-319-28397-5_20.
40.
ChenC.LiW. and SuH., Spectral-spatial classification of hyperspectral image based on kernel extreme learning machine, Remote Sensing6(6) (2014), 5795–5814, doi:10.3390/rs6065795.
41.
ZhangY., Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces, Expert Systems with Applications96 (2018), 302–310, doi:10.1016/j.eswa.2017.12.015.
