An enhanced method for the identification of ferritic morphologies in welded fusion zones based on gray-level co-occurrence matrix: A computational intelligence approach
Restricted accessResearch articleFirst published online April, 2021
An enhanced method for the identification of ferritic morphologies in welded fusion zones based on gray-level co-occurrence matrix: A computational intelligence approach
This work focuses on the identification of five of the most common ferritic morphologies present in welded fusion zones of low carbon steel through images acquired by photomicrographies. With this regards, we discuss the importance of the gray-level co-occurrence matrix to extract the features to be used as the input of the computational intelligence techniques. We use artificial neural networks and support vector machines to identify the proportions of each morphology and present the error identification rate for each technique. The results show that the use of gray-level co-occurrence extraction allows a less intense computational model with statistical validity and the support vector machine as a computational intelligence technique allows smaller variability when compared to the artificial neural networks.
AWS. Welding handbook: welding processes, Part I, 9th ed. Miami: AWS, 2004.
2.
DeCostBLFrancisTHolmEA. Exploring the microstructure manifold: image texture representations applied to ultrahigh carbon steel microstructures. Acta Mater2017; 133: 30–40.
3.
CampbellAMurrayPYakushinaE, et al.New methods for automatic quantification of microstructural features using digital image processing. Mater Des2018; 141: 395–406.
4.
SowardsJWGnäupel-HeroldTMcColskeyJD, et al.Characterization of mechanical properties, fatigue-crack propagation, and residual stresses in a microalloyed pipeline-steel friction-stir weld. Mater Des2015; 88: 632–642.
5.
ErdelyPStaronPMaawadE, et al.Design and control of microstructure and texture by thermomechanical processing of a multi-phase TiAl alloy. Mater Des2017; 131: 286–296.
6.
LiuHSunHLiuB, et al.An ultrahigh strength steel with ultrafine-grained microstructure produced through intercritical deformation and partitioning process. Mater Des2015; 83: 760–767.
7.
JengSLLeeHTKuoTY, et al.The effects of Mn and Nb on the microstructure and mechanical properties of alloy 152 welds. Mater Des2015; 87: 920–931.
8.
PeelMSteuwerAPreussM, et al.Microstructure, mechanical properties and residual stresses as a function of welding speed in aluminium AA5083 friction stir welds. Acta Mater2003; 51: 4791–4801.
9.
QueyRDawsonPBarbeF. Large-scale 3d random polycrystals for the finite element method: generation, meshing and remeshing. Comput Methods Appl Mech Eng2011; 200: 1729–1745.
10.
SunYCecenAGibbsJW, et al.Analytics on large microstructure datasets using two-point spatial correlations: coarsening of dendritic structures. Acta Mater2017; 132: 374–388.
11.
KondoRYamakawaSMasuokaY, et al.Microstructure recognition using convolutional neural networks for prediction of ionic conductivity in ceramics. Acta Mater2017; 141: 29–38.
12.
BostanabadRBuiATXieW, et al.Stochastic microstructure characterization and reconstruction via supervised learning. Acta Mater2016; 103: 89–102.
13.
ChowdhuryAKautzEYenerB, et al.Image driven machine learning methods for microstructure recognition. Comput Mater Sci2016; 123: 176–187.
14.
GolaJBritzDStaudtT, et al.Advanced microstructure classification by data mining methods. Comput Mater Sci2018; 148: 324–335.
15.
ZhangLXuZWeiS, et al.Grain size automatic determination for 7050 al alloy based on a fuzzy logic method. Rare Metal Mater Eng2016; 45: 548–554.
16.
Vakharia V, Kiran MB, Dave NJ, et al. Feature extraction and classification of machined component texture images using wavelet and artificial intelligence techniques. In: 2017 8th international conference on mechanical and aerospace engineering, Prague, Czech Republic, 22–25 July 2017, pp.140–144.
17.
StucknerJFreiKMcCueI, et al.Aquami: An open source python package and GUI for the automatic quantitative analysis of morphologically complex multiphase materials. Comput Mater Sci2017; 139: 320–329.
18.
SeitaMNimerfrohMMDemkowiczMJ. Acquisition of partial grain orientation information using optical microscopy. Acta Mater2017; 123: 70–81.
19.
LiDReichBBrennerD. Statistical and image analysis for characterizing simulated atomic-scale damage in crystals. Comput Mater Sci2017; 135: 119–126.
20.
OrtegonJLedesma-AlonsoRBarbosaR, et al.Material phase classification by means of support vector machines. Comput Mater Sci2018; 148: 336–342.
21.
de Aguiar EP, Verneck LS, Moreira A, et al. Type-1 fuzzy logic system applied to classification of rail head defects. In: Fourth Brazilian conference on fuzzy systems (IV CBSF), Campinas, Brazil, 2016.
22.
de Aguiar EP. Fuzzy logic system applied to classifications problems in railways. PhD Thesis, Universidade Federal de Juiz de Fora, Brazil, 2016.
23.
PereiraCRPereiraDRRosaGH, et al.Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification. Artif Intell Med2018; 87: 67–77.
24.
SachdevaJKumarVGuptaI, et al.A package-SFERCB-“segmentation, feature extraction, reduction and classification analysis by both SVM and ANN for brain tumors”. Appl Soft Comput2016; 47: 151–167.
25.
YadavARAnandRDewalM, et al.Multiresolution local binary pattern variants based texture feature extraction techniques for efficient classification of microscopic images of hardwood species. Appl Soft Comput2015; 32: 101–112.
26.
LiuYQinQLiuH-H, et al.Investigation of an image processing method of step-index multimode fiber specklegram and its application on lateral displacement sensing. Optic Fiber Technol2018; 46: 48–53.
27.
WebelJGolaJBritzD, et al.A new analysis approach based on Haralick texture features for the characterization of microstructure on the example of low-alloy steels. Mater Charact2018; 144: 584–596.
28.
FengJTengQHeX, et al.Reconstruction of three-dimensional heterogeneous media from a single two-dimensional section via co-occurrence correlation function. Comput Mater Sci2018; 144: 181–192.
29.
FilhoPPRdos SantosJCFreitasFNC, et al.New approach to evaluate a non-grain oriented electrical steel electromagnetic performance using photomicrographic analysis via digital image processing. J Mater Res Technol2017.
30.
DuttaSBaratKDasA, et al.Characterization of micrographs and fractographs of cu-strengthened HSLA steel using image texture analysis. Measurement2014; 47: 130–144.
31.
DuttaSDasABaratK, et al.Automatic characterization of fracture surfaces of AISI 304ln stainless steel using image texture analysis. Measurement2012; 45: 1140–1150.
32.
YanSZhouHXingB, et al.Crystal plasticity in fusion zone of a hybrid laser welded al alloys joint: from nanoscale to macroscale. Mater Des2018.
33.
WangXLiBLiM, et al.Study of local-zone microstructure, strength and fracture toughness of hybrid laser-metal-inert-gas-welded A7N01 aluminum alloy joint. Mater Sci Eng A2017; 688: 114–122.
34.
LeoPD'OstuniSCasalinoG. Hybrid welding of AA5754 annealed alloy: role of post weld heat treatment on microstructure and mechanical properties. Mater Des2016; 90: 777–786.
35.
YanSChenHMaC, et al.Local corrosion behaviour of hybrid laser-MIG welded Al-Zn-Mg alloy joints. Mater Des2015; 88: 1353–1365.
36.
LancasterJF. Metallurgy of welding, 6th ed. England: Abington Publishing, 1999.
37.
IIW. IIW Doc. IX-1533-88: Guide to the light microscope examination of ferritic steel weld metals. Paris: International Institute of Welding, 1988.
ASTM. ASTM E562-11: standard test method for determining volume fraction by systematic manual point count. West Conshohocken, PA: American Society for Testing and Materials, 2012.
40.
Howard Demuth MB. Neural network toolbox user's guide. Natick, MA: The MathWorks, 2002.
41.
Haykin S. Neural networks and learning machines. Upper Saddle River, NJ: Pearson Prentice Hall, 2009.
HaralickRShanmugamKDinsteinI. Textural features for image classification. IEEE Trans Syst Man Cybernet1973; 3: 610–621.
44.
CuiMPrasadSMahrooghyM, et al.Decision fusion of textural features derived from polarimetric data for levee assessment. IEEE J Select Topics Appl Earth Observ Remote Sens2012; 5: 970–976.
45.
Thakare VS and Patil NN. Classification of texture using gray level co-occurrence matrix and self-organizing map. In: 2014 international conference on electronic systems, signal processing and computing technologies, Nagpur, India, 2014, pp.350–355.
46.
Nikoo H, Talebi H and Mirzaei A. A supervised method for determining displacement of gray level co-occurrence matrix. In: 2011 7th Iranian conference on machine vision and image processing, Tehran, Iran, 2011, pp.1–5.
47.
Kun W and Songtao K. Identification method of waste based on gray level co-occurrence matrix and neural network. In: 2011 international conference on materials for renewable energy environment, Beijing, China, 2011, vol. 1, pp.929–931.
48.
BhandariSHDeshpandeSM. Analysis of engineered surfaces for product quality monitoring. Int J Comput Appl2011; 33: 284–292.
49.
Yang J and Guo J. Image texture feature extraction method based on regional average binary gray level difference co-occurrence matrix. In: 2011 international conference on virtual reality and visualization, Beijing, China, 2011, pp.239–242.
50.
Hu Y, Zhao CX and Wang HN. Directional analysis of texture images using gray level co-occurrence matrix. In: 2008 IEEE Pacific-Asia workshop on computational intelligence and industrial application, Wuhan, China, 2008, pp.277–281.
51.
Suganya R and Rajaram S. Feature extraction and classification of ultrasound liver images using Haralick texture-primitive features: application of SVM classifier. In: 2013 international conference on recent trends in information technology (ICRTIT), Chennai, India, 2013, pp.596–602.
52.
Preethi G and Sornagopal V. MRI image classification using GLCM texture features. In: 2014 international conference on green computing communication and electrical engineering (ICGCCEE), Coimbatore, India, 2014, pp.1–6.
53.
MoellerMF. A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw1993; 6: 525–533.
54.
Hsieh CJ, Chang KW and Lin CJ, et al. A dual coordinate descent method for large-scale linear SVM. In: Proceedings of the 25th international conference on machine learning, ICML'08, Helsinki, Finland, 2008, pp.408–415.
55.
XiaoL. Dual averaging methods for regularized stochastic learning and online optimization. J Mach Learn Res2003; 11: 2543–2596.
56.
MakridakisS. Accuracy measures: theoretical and practical concerns. Int J Forecast1993; 9: 527–529.
57.
KimSKimH. A new metric of absolute percentage error for intermittent demand forecasts. Int J Forecast2016; 32: 669–679.
58.
HyndmanRJKoehlerAB. Another look at measures of forecast accuracy. Int J Forecast2006; 22: 679–688.
59.
DelisIPanzeriSPozzoT, et al.A unifying model of concurrent spatial and temporal modularity in muscle activity. J Neurophysiol2014; 111: 675–693.
60.
Pérez-NombelaSBarrosoFTorricelliD, et al.Modular control of gait after incomplete spinal cord injury: differences between sides. Spinal Cord2016; 55: 79–86.
61.
Moore D. The basic practice of statistics, 1. W.H. Freeman, 2007. New York, USA.
62.
Silva GC, Caldeira L and Jr MLL. Comparing two different arc welding processes through the welding energy: the complete dataset, http://doi.org/10.17632/zgchnmjkj7.1.
63.
SilvaGCde CastroJAFilhoRMM, et al.Comparing two different arc welding processes through the welding energy: a selection analysis based on quality and energy consumption. J Brazil Soc Mech Sci Eng2019, pp. 41.
64.
Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on artificial intelligence - volume 2, IJCAI'95, 1995, pp.1137–1143. San Francisco, CA: Morgan Kaufmann Publishers Inc.
65.
BishopCM. Neural networks for pattern recognition, Oxford: Oxford University Press, 1995.
66.
RipleyBD. Pattern recognition and neural networks, Cambridge: Cambridge University Press, 1996.
