Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Materials Science
  4. Volume 17, Issue 2
  5. Article
Volume 17, Issue 2
  • ISSN: 2666-1454
  • E-ISSN: 2666-1462

Abstract

Background

Metal surface roughness detection is an essential step of quality control in the metal processing industry. Due to the high manual involvement and poor efficiency of traditional roughness testing, rapid automated vision detection has received increasing attention in product quality control. Many methods have focused on extracting features related to roughness from images by means of mathematical statistics. However, these methods often rely on extensive experiments and complex calculations, while being sensitive to external environmental disturbances.

Methods

In this paper, a convolution neural network-based approach for metal surface roughness evaluation has been proposed. The convolutional neural network was initialized using a transfer learning strategy, and the data augmentation technique was applied to the benchmark dataset for sample expansion.

Results

To evaluate this approach, samples of 4 types of roughness classes were prepared. The samples were divided into a training set, validation set, and test set in the ratio of 7:2:1. The accuracy of the neural network on the test set was found to be above 86%.

Conclusion

The effectiveness of the proposed approach and its superiority over manual detection have been demonstrated in the experiments.

© 2024 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cms/10.2174/2666145416666230420093435
2024-06-01
2024-11-26

  • From This Site

    /content/journals/cms/10.2174/2666145416666230420093435
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. CurryN. TangZ. MarkocsanN. NylénP. Influence of bond coat surface roughness on the structure of axial suspension plasma spray thermal barrier coatings-Thermal and lifetime performance.Surf. Coat. Tech.2015268152310.1016/j.surfcoat.2014.08.067
     [Google Scholar]
  2. MasuoH. TanakaY. MorokoshiS. Influence of defects, surface roughness and HIP on the fatigue strength of Ti-6Al-4V manufactured by additive manufacturing.Int. J. Fatigue201811716317910.1016/j.ijfatigue.2018.07.020
     [Google Scholar]
  3. MalekiE. BagherifardS. BandiniM. GuaglianoM. Surface post-treatments for metal additive manufacturing: Progress, challenges, and opportunities.Addit. Manuf.2021372210.1016/j.addma.2020.101619
     [Google Scholar]
  4. JeyapoovanT. MuruganM. Surface roughness classification using image processing.Measurement20134672065207210.1016/j.measurement.2013.03.014
     [Google Scholar]
  5. MacekW. MarciniakZ. BrancoR. RozumekD. KrólczykG.M. A fractographic study exploring the fracture surface topography of S355J2 steel after pseudo-random bending-torsion fatigue tests.Measurement202117810944310.1016/j.measurement.2021.109443
     [Google Scholar]
  6. LeachR. Optical measurement of surface topography.201110.1007/978‑3‑642‑12012‑1
     [Google Scholar]
  7. KobayashiT. ShockeyD.A. Fracture surface topography analysis (FRASTA)—Development, accomplishments, and future applications.Eng. Fract. Mech.201077122370238410.1016/j.engfracmech.2010.05.016
     [Google Scholar]
  8. NikolaevN. PetzingJ. CouplandJ. Focus variation microscope: Linear theory and surface tilt sensitivity.Appl. Opt.201655133555356510.1364/AO.55.003555 27140371
     [Google Scholar]
  9. WangS. WanJ. ZhangD. LiD. ZhangC. Towards smart factory for industry 4.0: A self-organized multi-agent system with big data based feedback and coordination.Comput. Netw.201610115816810.1016/j.comnet.2015.12.017
     [Google Scholar]
  10. OztemelE. GursevS. Literature review of Industry 4.0 and related technologies.J. Intell. Manuf.202031112718210.1007/s10845‑018‑1433‑8
     [Google Scholar]
  11. WangX. HanY. LeungV.C.M. NiyatoD. YanX. ChenX. Convergence of edge computing and deep learning: A comprehensive survey.IEEE Commun. Surv. Tutor.202022286990410.1109/COMST.2020.2970550
     [Google Scholar]
  12. KöksalG. Batmaz İ Testik MC. A review of data mining applications for quality improvement in manufacturing industry.Expert Syst. Appl.20113810134481346710.1016/j.eswa.2011.04.063
     [Google Scholar]
  13. GuptaA. SinghH. AggarwalA. Taguchi-fuzzy multi output optimization (MOO) in high speed CNC turning of AISI P-20 tool steel.Expert Syst. Appl.20113866822682810.1016/j.eswa.2010.12.057
     [Google Scholar]
  14. Çaydaş U, Ekici S. Support vector machines models for surface roughness prediction in CNC turning of AISI 304 austenitic stainless steel.J. Intell. Manuf.201223363965010.1007/s10845‑010‑0415‑2
     [Google Scholar]
  15. PalaniS. NatarajanU. ChellamalaiM. On-line prediction of micro-turning multi-response variables by machine vision system using adaptive neuro-fuzzy inference system (ANFIS).Mach. Vis. Appl.2013241193210.1007/s00138‑011‑0378‑0
     [Google Scholar]
  16. ShahabiH.H. RatnamM.M. Simulation and measurement of surface roughness via grey scale image of tool in finish turning.Precis. Eng.20164314615310.1016/j.precisioneng.2015.07.004
     [Google Scholar]
  17. VorburgerT.V. TeagueE.C. Optical techniques for on-line measurement of surface topography.Precis. Eng.198132618310.1016/0141‑6359(81)90038‑6
     [Google Scholar]
  18. TianG.Y. LuR.S. GledhillD. Surface measurement using active vision and light scattering.Opt. Lasers Eng.200745113113910.1016/j.optlaseng.2006.03.005
     [Google Scholar]
  19. VesselenyiT. MogaI. MuduraP. Surface roughness image analysis using fractal methods.18th International Symposium of the Danube-Adria-Association-for-Automationand-Manufacturing Zadar, CROATIA2007pp. Oct 24-27; 2007; 811-2.
     [Google Scholar]
  20. AliJ.M. JailaniH.S. MuruganM. Surface roughness evaluation of milled steel surfaces using wavelet transform of laser speckle line images.Lasers Eng.2019444-6371384
     [Google Scholar]
  21. GuoR. BianD. Vision system for surface roughness and surface defect measurement.Opt. Eng.2019586110.1117/1.OE.58.6.064103
     [Google Scholar]
  22. YiH.A. ZhaoX.J. TangL. ChenY.L. YangJ. Measuring grinding surface roughness based on singular value entropy of quaternion.Meas. Sci. Technol.202031111110.1088/1361‑6501/ab9aa9
     [Google Scholar]
  23. HaralickR.M. ShanmugamK. DinsteinI. Textural features for image classification.Stud. Media Commun.197361062110.1109/TSMC.1973.4309314
     [Google Scholar]
  24. SebastianV.B. Gray level co-occurrence matrices: Generalisation and some new Features.Int J Comp Sci Eng Informa20122215115710.5121/ijcseit.2012.2213
     [Google Scholar]
  25. Roberti de SiqueiraF. Robson SchwartzW. PedriniH. Multi-scale gray level co-occurrence matrices for texture description.Neurocomputing201312033634510.1016/j.neucom.2012.09.042
     [Google Scholar]
  26. LiangC YangW M ZhouF LiaoQ M Roughness classification with aggregated discrete fourier transform.IEICE Trans Inf Syst2014e97d1027697910.1587/transinf.2014EDP7082
     [Google Scholar]
  27. ChenS. FengR. ZhangC. ZhangY. Surface roughness measurement method based on multi-parameter modeling learning.Measurement201812966467610.1016/j.measurement.2018.07.071
     [Google Scholar]
  28. LiW. LuW. LiS. ZhaoY. LiQ. Research on extraction method of roughness parameters of relay circular contacts.IEEJ Trans. Electr. Electron. Eng.2020157995100110.1002/tee.23143
     [Google Scholar]
  29. LiuH LiJ YangY LanJ XueY Automatic process parameters tuning and surface roughness estimation for laser cleaning.IEEE Access20208209041910.1109/ACCESS.2020.2970086
     [Google Scholar]
  30. PanH GaoP ZhouH MaR YangJ ZhangX Roughness analysis of sea surface from visible images by texture.IEEE Access20208464485810.1109/ACCESS.2020.2978638
     [Google Scholar]
  31. GeJ. LiuH. YangS. LanJ. Laser cleaning surface roughness estimation using enhanced glcm feature and IPSO-SVR.Photonics20229851010.3390/photonics9080510
     [Google Scholar]
  32. ChenS.T. HuH.F. ZhangC. Surface roughness modeling based on laser speckle imaging.Wuli Xuebao201564239
     [Google Scholar]
  33. HuaianY.I. JianL.I.U. EnhuiL.U. PengA.O. Measuring grinding surface roughness based on the sharpness evaluation of colour images.Meas. Sci. Technol.201627202540410.1088/0957‑0233/27/2/025404
     [Google Scholar]
  34. GuJ. WangZ. KuenJ. Recent advances in convolutional neural networks.Pattern Recognit.20187735437710.1016/j.patcog.2017.10.013
     [Google Scholar]
  35. WangZ. YangJ. JiangH. FanX. CNN training with twenty samples for crack detection via data augmentation.Sensors20202017484910.3390/s20174849 32867223
     [Google Scholar]
  36. TaoX. ZhangD. MaW. LiuX. XuD. Automatic metallic surface defect detection and recognition with convolutional neural networks.Appl. Sci.201889157510.3390/app8091575
     [Google Scholar]
  37. AlqahtaniH. BharadwajS. RayA. Classification of fatigue crack damage in polycrystalline alloy structures using convolutional neural networks.Eng. Fail. Anal.2020119510490810.1016/j.engfailanal.2020.104908
     [Google Scholar]
  38. TabernikD. ŠelaS. Skvarč J, Skočaj D. Segmentation-based deep-learning approach for surface-defect detection.J. Intell. Manuf.202031375977610.1007/s10845‑019‑01476‑x
     [Google Scholar]
  39. SimonyanK ZissermanA Very deep convolutional networks for large-scale image recognition.CoRR2014abs./1409.155610.48550/arXiv.1409.1556
     [Google Scholar]
  40. HeK ZhangX RenS SunJ Deep residual learning for image recognition.IEEE conference on Computer Vision and Pattern Recognition, 2016, Las Vegas, NV, USA2016pp. 770810.48550/arXiv.1512.03385
     [Google Scholar]
  41. HuangG LiuZ LaurensV WeinbergerKQ Densely connected convolutional networks. IEEE conference on Computer Vision and Pattern Recognition, Honolulu, HT,U.S.A.20172261910.48550/arXiv.1608.06993
     [Google Scholar]
  42. SzegedyC LiuW JiaY SermanetP RabinovichA Going deeper with convolutions.2015 IEEE conference on computer vision and pattern recognition (CVPR), Los Vegas,NV,U.S.A.2014pp. 19
     [Google Scholar]
  43. SzegedyC. VanhouckeV. IoffeS. ShlensJ. WojnaZ.J.I. Rethinking the inception architecture for computer vision.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Los Vegas, NV, USA20162818-2610.1109/CVPR.2016.308
     [Google Scholar]
  44. GaoY. MosalamK.M. Deep transfer learning for image-based structural damage recognition.Comput. Aided Civ. Infrastruct. Eng.201833974876810.1111/mice.12363
     [Google Scholar]
  45. ApostolopoulosI.D. MpesianaT.A. Covid-19: Automatic detection from X-ray images utilizing transfer learning with convolutional neural networks.Physic Eng Sci Medic202043263564010.1007/s13246‑020‑00865‑4 32524445
     [Google Scholar]
  46. KermanyD.S. GoldbaumM. CaiW. Identifying medical diagnoses and treatable diseases by image-based deep learning.Cell201817251122113110.1016/j.cell.2018.02.010 29474911
     [Google Scholar]
  47. PanS.J. YangQ. A survey on transfer learning.IEEE Trans. Knowl. Data Eng.201022101345135910.1109/TKDE.2009.191
     [Google Scholar]
  48. ShinH.C. RothH.R. GaoM. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning.IEEE Trans. Med. Imaging20163551285129810.1109/TMI.2016.2528162 26886976
     [Google Scholar]
  49. WhitehouseD.J. Surface metrology.Meas. Sci. Technol.19978995597210.1088/0957‑0233/8/9/002
     [Google Scholar]
  50. HanH. Surface Parameter.CIRP Encyclopedia of Production Engineering201714
     [Google Scholar]
  51. PimenovD.Y. BustilloA. MikolajczykT. Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth.J. Intell. Manuf.20182951045106110.1007/s10845‑017‑1381‑8
     [Google Scholar]
  52. CN-GB, Geometrical product specifications (GPS) - Surface texture: Profile method - Surface roughness parameters and their values.2009GB/T 12472-2003: 3
     [Google Scholar]
  53. JurkovicZ. CukorG. BrezocnikM. BrajkovicT. A comparison of machine learning methods for cutting parameters prediction in high speed turning process.J. Intell. Manuf.20182981683169310.1007/s10845‑016‑1206‑1
     [Google Scholar]
  54. AichU. BanerjeeS. Modeling of EDM responses by support vector machine regression with parameters selected by particle swarm optimization.Appl. Math. Model.20143811-122800281810.1016/j.apm.2013.10.073
     [Google Scholar]
  55. GuptaM.K. MiaM. PruncuC.I. Parametric optimization and process capability analysis for machining of nickel-based superalloy.Int. J. Adv. Manuf. Technol.20191029-123995400910.1007/s00170‑019‑03453‑3
     [Google Scholar]
  56. RonnebergerO. FischerP. BroxT. U-Net: Convolutional networks for biomedical image segmentation.18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) Munich, GERMANY.2015; Oct 05-09: pp. 234-41.
     [Google Scholar]
  57. LiX. ZhangW. DingQ. SunJ.Q. Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation.J. Intell. Manuf.202031243345210.1007/s10845‑018‑1456‑1
     [Google Scholar]
  58. CirilloMD AbramianD EklundA In what is the best data augmentation for 3d brain tumor segmentation? IEEE international conference on image processing (ICIP) Sep 19-222021pp. 3640
     [Google Scholar]
  59. KongW. DongZ.Y. HillD.J. LuoF. XuY. Short-term residential load forecasting based on resident behaviour levelarning.IEEE Transact. Power Sys.20173311087108810.1109/TPWRS.2017.2688178
     [Google Scholar]
  60. KetkarN. Deep learning with python.A Hands-on Introduction2017xvii, 226.10.1007/978‑1‑4842‑2766‑4
     [Google Scholar]
  61. ShoreJ. Johnson RJITITo. Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy.Information Theory IEEE Transact1980261263710.1109/TIT.1980.1056144
     [Google Scholar]
  62. GolikP. DoetschP. NeyH. In cross-entropy vs. squared error training: A theoretical and experimental comparison.14th annual conference of the international-speechcommunication association (INTERSPEECH 2013) Lyon,FRANCE.Aug 25 2013; 29: pp.1755-9.10.21437/Interspeech.2013‑436
     [Google Scholar]
  63. KingmaD. BaJ.J.C.S. Adam: A method for stochastic optimization.arxiv:1414210.48550/arXiv.1412.6980
     [Google Scholar]
  64. ChangZ. ZhangY. ChenW. Electricity price prediction based on hybrid model of ADAM optimized LSTM neural network and wavelet transform.Energy201918711580410.1016/j.energy.2019.07.134
     [Google Scholar]
  65. OuM. WeiH. ZhangY. TanJ. A dynamic adam based deep neural network for fault diagnosis of oil-immersed power transformers.Energies201912699510.3390/en12060995
     [Google Scholar]
  66. YiD. AhnJ. JiS. An effective optimization method for machine learning based on ADAM.Appl. Sci.2020103107310.3390/app10031073
     [Google Scholar]
  67. IdeH KuritaT Improvement of learning for CNN with ReLU activation by sparse regularization. In international joint conference on neural networks (IJCNN) anchorage, AK2017May141926849110.1109/IJCNN.2017.7966185
     [Google Scholar]
  68. WangG. GiannakisG.B. ChenJ. Learning ReLU networks on linearly separable data: algorithm, optimality, and generalization.IEEE Trans. Signal Process.20196792357237010.1109/TSP.2019.2904921
     [Google Scholar]
  69. WangS.H. MuhammadK. HongJ. SangaiahA.K. ZhangY.D. Alcoholism identification viaconvolutional neural network based on parametric ReLU, dropout, and batch normalization.Neural Comput. Appl.202032366568010.1007/s00521‑018‑3924‑0
     [Google Scholar]
  70. AbadiM. AgarwalA. BarhamP. Tensor Flow: Large-scale machine learning on heterogeneous distributed systems.ArXiv201616030446710.48550/arXiv.1603.04467
     [Google Scholar]
  71. WittenD. In an introduction to statistical learning: With applications in R.2013
     [Google Scholar]
  72. SinghP. SinghN. SingK.K. Diagnosing of disease using machine learning.Machine Learning and the Internet of Medical Things in Healthcare20218911110.1016/B978‑0‑12‑821229‑5.00003‑3
     [Google Scholar]
  73. Donna Katzman Making MJMD. Analyzing a portion of the roc curve.Mach. Learn.1989919019510.1177/0272989X8900900307 2668680
     [Google Scholar]
  74. HandD.J. TillR.J. A simple generalisation of the area under the roc curve for multiple class classification problems.Mach. Learn.200145217118610.1023/A:1010920819831
     [Google Scholar]
  75. HuiFang TamG.K-L. BorgoR. Visualizing natural image statistics.IEEE Trans. Vis. Comput. Graph.20131971228124110.1109/TVCG.2012.312 23661013
     [Google Scholar]
  76. ZalamaE. Gómez-GarcíaB.J. MedinaR. LlamasJ. Road crack detection using visual features extracted by gabor filters.Comput. Aided Civ. Infrastruct. Eng.201429534235810.1111/mice.12042
     [Google Scholar]
  77. HuaB.O. Fu-LongM.A. JiaoL.C. Research on computation of GLCM of image texture.Tien Tzu Hsueh Pao200611155158
     [Google Scholar]
  78. GuoZ. ZhangL. ZhangD. Rotation invariant texture classification using LBP variance (LBPV) with global matching.Pattern Recognit.201043370671910.1016/j.patcog.2009.08.017
     [Google Scholar]
  79. de VazelhesW. CareyC.J. TangY. VauquierN. BelletA. Metric-learn: Metric learning algorithms in python.J. Mach. Learn. Res.2020216
     [Google Scholar]
/content/journals/cms/10.2174/2666145416666230420093435
Loading
A Convolution Neural Network-based Approach for Metal Surface Roughness Evaluation
Current Materials Science 17, 148 (2024); https://doi.org/10.2174/2666145416666230420093435
/content/journals/cms/10.2174/2666145416666230420093435
/content/journals/cms/10.2174/2666145416666230420093435
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): convolutional neural network; data augmentation; deep learning; Product quality control; surface roughness evaluation; transfer learning approach

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test