Adaptive rapid defect identification in ECPT based on K-means and automatic segmentation algorithm

  • Xuegang Huang
  • Chun Yin
  • Sara Dadras
  • Yuhua Cheng
  • Libing Bai
Original Research
  • 45 Downloads

Abstract

To enhance the detection efficiency in eddy current pulsed thermography, an adaptive feature extraction algorithm for defect identification is developed in this paper. The proposed algorithm involves four stages, namely, the thermal image segmentation, the variable interval search, the distance correlation clustering analysis and the between-class distance decision making. The transient thermal responses (TTRs) with similar characteristics are collected into one data block. The thermal image segmentation and variable interval search can help reduce the repetitive calculation in defect identification by choosing local optimums in each data block. The global optimum that has the largest sum of the between-class distance, is derived by first classifying the local optimums and then calculating the correlation distance of the thermal responses with the center points of each class. Finally, the TTRs with the largest between-class distance are regarded as the typical ones which can be used to identify the discriminative defect features of infrared image sequence. Finally, the comparison experiments are carried out to demonstrate the effectiveness and advantages of the proposed approach.

Keywords

Eddy current pulsed thermography Transient thermal response K-means clustering Pearson correlation Between-class distance Inner-class-distance 

References

  1. Al-Ayyoub M, Jararweh Y, Rababah A, Aldwairi M (2017) Feature extraction and selection for Arabic tweets authorship authentication. J Ambient Intell Human Comput 8:383–393CrossRefGoogle Scholar
  2. Arjun V, Sasi B, Rao BPC, Mukhopadhyay CK, Jayakumar T (2015) Optimisation of pulsed eddy current probe for detection of sub-surface defects in stainless steel plates. Sens Actuators A Phys 226:69–75CrossRefGoogle Scholar
  3. Avdelidis NP, Hawtin BC, Almond DP (2003) Transient thermography in the assessment of defects of aircraft composites. NDT E Int 36:433–439CrossRefGoogle Scholar
  4. Bai L, Gao B, Tian GY, Woo WL, Cheng Y (2013) Spatial and time patterns extraction of eddy current pulsed thermography using blind source separation. IEEE Sens J 13:2094–2101CrossRefGoogle Scholar
  5. Bi M, Xu J, Wang M, Zhou F (2016) Anomaly detection model of user behavior based on principal component analysis. J Ambient Intell Human Comput 7:547–554CrossRefGoogle Scholar
  6. Bousse M, Debals O, Lathauwer LD (2017) A tensor-based method for large-scale blind source separation using segmentation. IEEE Trans Signal Process 65:346–358MathSciNetCrossRefGoogle Scholar
  7. Cai B, Zhao Y, Liu H, Xie M (2017) A data-driven fault diagnosis methodology in three-phase inverters for PMSM drive systems. IEEE Trans Power Electron 32(7):5590–5600CrossRefGoogle Scholar
  8. Cao J, Zhang K, Luo M, Yin C, Lai X (2016) Extreme learning machine and adaptive sparse representation for image classification. Neural Netw 81:91–102CrossRefGoogle Scholar
  9. Cao J, Wang W, Wang J, Wang R (2017) Excavation equipment recognition based on novel acoustic statistical features. IEEE Trans Cybern 47(12):4392–4404CrossRefGoogle Scholar
  10. Cao J, Huang W, Zhao T, Wang J, Wang R (2017) An enhance excavation equipments classification algorithm based on acoustic spectrum dynamic feature. Multidimens Sys Signal Process 28:921–943CrossRefGoogle Scholar
  11. Chan CCH, Hwang Y, Wu H (2016) Marketing segmentation using the particle swarm optimization algorithm: a case study. J Ambient Intell Human Comput 7:855–863CrossRefGoogle Scholar
  12. Chen B, Xing L, Zhao H, Zheng N, Principe JC (2016) Generalized correntropy for robust adaptive filtering. IEEE Trans Signal Process 64:3376–3387MathSciNetCrossRefGoogle Scholar
  13. Cheng Y, Yin C, Chen Y, Bai L, Huang X, Zhou X, Yang F (2016) ICA fusion approach based on fuzzy using in eddy current pulsed thermography. Int J Appl Electrom Mech 52:443–451Google Scholar
  14. Gao B, Bai L, Woo W, Tian GY, Cheng Y (2014) Automatic defect identification of eddy current pulsed thermography using single channel blind source separation. IEEE Trans Instrum Meas 63:913–922CrossRefGoogle Scholar
  15. He X, He F, Cai W (2016) Underdetermined BSS based on Kmeans and AP clustering. Circ Syst Signal Process 35:2881–2913CrossRefGoogle Scholar
  16. He Y, Yang R (2015) Eddy current volume heating thermography and phase analysis for imaging characterization of interface delamination in CFRP. IEEE Trans Ind Inform 6:1287–1297CrossRefGoogle Scholar
  17. Huang H, Yin C, Huang J, Wen X, Zhao Z, Wu J, Liu S (2016) Hypervelocity impact of TiB2-based composites as front bumpers for space shield applications. Mater Des 97:473–482CrossRefGoogle Scholar
  18. Islam MMM, Kim JM (2017) Time–frequency envelope analysisbased sub-band selection and probabilistic support vector machines for multi-fault diagnosis of low-speed bearings. J Ambient Intell Human Comput.  https://doi.org/10.1007/s12652-017-0585-2Google Scholar
  19. Li S, Zhou X, Pan F, Shi H, Li K, Wang H (2017) Correlated and weakly correlated fault detection based on variable division and ICA. Comput Ind Eng 112:320–335CrossRefGoogle Scholar
  20. Li X, Wang L (2015) On the study of fusion techniques for bad geological remote sensing image. J Ambient Intell Human Comput 6:141–149CrossRefGoogle Scholar
  21. Li Y, Yan B, Li D, Jing H, Li Y, Chen Z (2016) Pulse-modulation eddy current inspection of subsurface corrosion in conductive structures. NDT E Int 79:142–149CrossRefGoogle Scholar
  22. Lo K, Ni S, Huang Y (2010) Non-destructive test for pile beneath bridge in the time, frequency, and time–frequency domains using transient loading. Nonlinear Dyn 62:349–360CrossRefMATHGoogle Scholar
  23. Luo Y, Huang J, Kanemoto T, Guo M, Tang F (2013) New acoustic monitoring method using cross-correlation of primary frequency spectrum. J Ambient Intell Human Comput 4:293–301CrossRefGoogle Scholar
  24. Maldague X (2001) Theory and practice of infrared technology for nondestructive testing. Wiley, New YorkGoogle Scholar
  25. Mourad N, Reilly JP, Kirubarajan T (2017) Majorizationminimization for blind source separation of sparse sources. Signal Process 131:120–133CrossRefGoogle Scholar
  26. Omar MA, Parvataneni R, Zhou Y (2010) A combined approach of selfreferencing and principle component thermography for transient, steady, and selective heating scenarios. Infrared Phys Techn 53:358–362CrossRefGoogle Scholar
  27. Rao YN, Erdogmus D, Rao GY, Principe JC (2005) Fast error whitening algorithms for system identification and control with noisy data. Neurocomputing 69:158–181CrossRefGoogle Scholar
  28. Ruhi M, Morshed BI (2015) Unsupervised eye blink artifact denoising of EEG data with modified multiscale sample entropy, kurtosis, and wavelet-ICA. IEEE J Biomed Health Inf 19:158–165CrossRefGoogle Scholar
  29. Wang XF, Zhu WD (2015) A modified incremental harmonic balance method based on the fast Fourier transform and Broydens method. Nonlinear Dyn 81:981–989MathSciNetCrossRefMATHGoogle Scholar
  30. Xu Y, Deng X (2016) Fault detection of multimode non-Gaussian dynamic process using dynamic Bayesian independent component analysis. Neurocomputing 200:70–79CrossRefGoogle Scholar
  31. Xu C, Zhou N, Xie J, Gong X, Chen G, Song G (2016) Investigation on eddy current pulsed thermography to detect hidden cracks on corroded metal surface. NDT E Int 84:27–35CrossRefGoogle Scholar
  32. Yala N, Fergani B, Fleury A (2017) Towards improving feature extraction and classification for activity recognition on streaming data. J Ambient Intell Human Comput 8:177–189CrossRefGoogle Scholar
  33. Yin C, Dadras S, Huang X, Mei J, Cheng Y (2017) Energysaving control strategy for lighting system based on multivariate extremum seeking with Newton algorithm. Energy Convers Manag 142:504–522CrossRefGoogle Scholar
  34. Yin C, Huang X, Chen Y, Dadras S, Zhong SM, Cheng Y (2017) Fractional-order exponential switching technique to enhance sliding mode control. Appl Math Model 44:705–726MathSciNetCrossRefGoogle Scholar
  35. Zuo C, Jovanov L, Goossens B, Luong HQ, Philips W, Liu Y, Zhang M (2016) Image denoising using quadtree-based nonlocal means with locally adaptive principal component analysis. IEEE Signal Proc Lett 23:434–438CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Hypervelocity Aerodynamics InstituteChina Aerodynamics Research and Development CenterMianyangPeople’s Republic of China
  2. 2.School of Automation EngineeringUniversity of Electronic Science and Technology of ChinaChengduPeople’s Republic of China
  3. 3.Electrical and Computer Engineering DepartmentUtah State UniversityLoganUSA

Personalised recommendations