Indian Journal of Engineering & Materials Sciences

Open Access Open Access  Restricted Access Subscription Access

Synthesis of the Artificial Intelligence and Model-Based and Statistical Algorithms in the Classification of the Metal Surface Defects


Affiliations
1 Department for production engineering, Faculty of Engineering, University of Kragujevac, Kragujevac 34000, Serbia
2 Department for electrical engineering, Faculty of Engineering, University of Kragujevac, Kragujevac 34000, India
 

Steel has played an indispensable role in numerous industries, particularly in architecture, aerospace, and the automotive sector, and has been one of the most crucial components in manufacturing. The possibility of defects in the steelmaking process has had a substantial impact on the quality and service life of the final product. With the objective of ensuring a timely response in steel production, this paper has presented a model for the classification, detection of defect regions, and visualization of spatial defects. The model has been founded on the synthesis of convolutional neural network, snake algorithms, and algorithms for generating spatial defects based on images. The convolutional neural network has been trained using images from the NEU Surface Defect database, and model evaluation has been carried out on previously unseen samples that have not been included in the training data. The convolutional neural network has achieved an overall accuracy of 88.4% with unseen samples from the NEU Surface Defect database, with predictive abilities ranging from 72.7% to 97.7%. Following the classification, a spatial representation of the damage has been generated, and defect segmentation on the material has been executed. The application of this model in modern industry has the potential to significantly enhance the performance and quality of high-risk manufacturing processes, mitigate unnecessary losses, and enable informed decision-making about future steps in a more insightful manner.

Keywords

Convolutional Neural Network, Active Contours, Steel, Defects, Spatial defect shape.
User
Notifications
Font Size

  • Wang J, Ma Y, Zhang L, Gao R X & Wu D, J Manuf Syst, 48 (2018) 144

  • Jung W-K, Kim D-R, Lee H, Lee T-H, Yang I, Youn B D, Zontar D, Brockmann M, Brecher C & Ahn S-H, Int J Precis Eng and Manuf, 22 (2021) 201.

  • Essien A & Giannetti C, IEEE Trans Industr Inform, 16(9) (2020), 6069.

  • Dave V, Singh S & Vakhaira V, Indian J Eng Mater Sci, 27 (2020) 878.

  • Kandavel T K, Kumar T A & Varamban E, Indian J Eng Mater Sci, 27 (2020) 503.

  • Svinth C N, Walace S, Stephenson D B, Kim D, Shin K, Kim H-Y, Lee S W & Kim T-G, Int J Precis Eng and Manuf, 23 (2022) 609.

  • Lee S Y, Tama B A, Moon S J & Lee S, Appl Sci, 9(24) (2019) 5449.

  • Hao R, Lu B, Cheng Y, Li X & Huang B, J Intell Manuf, 32 (2021) 1833.

  • Luo Q, Fang X, Liu L & Sun Y, IEEE Trans Instrum Meas, 69(3) (2020), 626.

  • Czimmerann T, Ciuti G, Milazzo M, Chiurazzi M, Roccella S, Oddo C M & Dario P, Sensors, 20(5) (2020) 1459.

  • Tao X, Zhang D, Ma W, Liu X & Xu D, Appl Sci, 8(9) (2018) 1575.

  • Albawi S, Bayat O, Al-Azawi S & Ucan O N, Comput Intell Neurosci, 2018 (2018) 6973103.

  • O’Shea K & Nash R, Neural and Evolutionary Computing, (2015) 1511.08458.

  • Gur S, Wolf L, Golgher L & Blinder P, Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network, in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, 10721.

  • Wang L, Chang Y, Wang H, Wu Z, Pu J & Yang X, Inf Sci, 418-419 (2017) 61.

  • He Y, Song K, Meng Q & Yan Y, IEEE Trans Instrum Meas, 69(4) (2020) 1493.

  • Lv X, Duan F, Jiang J-J, Fu X & Gan L, Sensors, 20(6) (2020) 1562.

  • Wang S, Xia X, Ye L & Yang B, Metals, 11(3) (2021) 388.

  • Deshpande A M, Minai A A & Kumar M, Procedia Manuf, 48 (2020) 1064.

  • Bumrungkun P, J Phys Conf Ser, 1195(1) (2018) .


Abstract Views: 97

PDF Views: 57




  • Synthesis of the Artificial Intelligence and Model-Based and Statistical Algorithms in the Classification of the Metal Surface Defects

Abstract Views: 97  |  PDF Views: 57

Authors

Suzana Petrovic Savic
Department for production engineering, Faculty of Engineering, University of Kragujevac, Kragujevac 34000, Serbia
Nikola Mijailovic
Department for electrical engineering, Faculty of Engineering, University of Kragujevac, Kragujevac 34000, India
Dragan Dzunic
Department for production engineering, Faculty of Engineering, University of Kragujevac, Kragujevac 34000, Serbia
Vladimir Kocovic
Department for production engineering, Faculty of Engineering, University of Kragujevac, Kragujevac 34000, Serbia
Goran Devedzic
Department for production engineering, Faculty of Engineering, University of Kragujevac, Kragujevac 34000, Serbia

Abstract


Steel has played an indispensable role in numerous industries, particularly in architecture, aerospace, and the automotive sector, and has been one of the most crucial components in manufacturing. The possibility of defects in the steelmaking process has had a substantial impact on the quality and service life of the final product. With the objective of ensuring a timely response in steel production, this paper has presented a model for the classification, detection of defect regions, and visualization of spatial defects. The model has been founded on the synthesis of convolutional neural network, snake algorithms, and algorithms for generating spatial defects based on images. The convolutional neural network has been trained using images from the NEU Surface Defect database, and model evaluation has been carried out on previously unseen samples that have not been included in the training data. The convolutional neural network has achieved an overall accuracy of 88.4% with unseen samples from the NEU Surface Defect database, with predictive abilities ranging from 72.7% to 97.7%. Following the classification, a spatial representation of the damage has been generated, and defect segmentation on the material has been executed. The application of this model in modern industry has the potential to significantly enhance the performance and quality of high-risk manufacturing processes, mitigate unnecessary losses, and enable informed decision-making about future steps in a more insightful manner.

Keywords


Convolutional Neural Network, Active Contours, Steel, Defects, Spatial defect shape.

References