• Laser & Optoelectronics Progress
  • Vol. 57, Issue 21, 211407 (2020)
Tian Chongxin1、2, Li Shaoxia1、2, Yu Gang1、2, He Xiuli1、2, and Wang Xu1、2
Author Affiliations
  • 1中国科学院力学研究所, 北京 100190
  • 2中国科学院大学工程科学学院, 北京 100049
  • show less
    DOI: 10.3788/LOP57.211407 Cite this Article Set citation alerts
    Tian Chongxin, Li Shaoxia, Yu Gang, He Xiuli, Wang Xu. Rapid Detection of Laser Surface Modification Quality Based on Machine Vision[J]. Laser & Optoelectronics Progress, 2020, 57(21): 211407 Copy Citation Text show less
    Laser surface modification system and modified specimen. (a) Modification system; (b) specimen before modification; (c) modified specimen; (d) section image of modified specimen
    Fig. 1. Laser surface modification system and modified specimen. (a) Modification system; (b) specimen before modification; (c) modified specimen; (d) section image of modified specimen
    Surface morphology of specimens. (a) Original specimen; (b) modified sample with low energy; (c) modified specimen with appropriate energy; (d) modified sample with high energy
    Fig. 2. Surface morphology of specimens. (a) Original specimen; (b) modified sample with low energy; (c) modified specimen with appropriate energy; (d) modified sample with high energy
    Binary images of different specimens. (a) Original specimen; (b) modified specimen with low energy; (c) modified specimen with appropriate energy; (d) modified specimen with high energy
    Fig. 3. Binary images of different specimens. (a) Original specimen; (b) modified specimen with low energy; (c) modified specimen with appropriate energy; (d) modified specimen with high energy
    Optimization of process parameters
    Fig. 4. Optimization of process parameters
    Surface morphology of specimens. (a) Low energy; (b) experiment 1; (c) experiment 2; (d) high energy; (e) experiment 3
    Fig. 5. Surface morphology of specimens. (a) Low energy; (b) experiment 1; (c) experiment 2; (d) high energy; (e) experiment 3
    ParameterAreaOrientationOblatenessSymmetryAccumulationDensityEntropy
    Meansmθmompmam
    Standard deviationssθsospsasnae
    Table 1. Parameters for region texture features
    Power /WSpeed /(mm·min-1)Spot diameter /mmStep /mmRa /μmRemelting depth /μm
    0---0.90
    35080000.090.082.4~5
    50080000.090.085.9~50
    60080000.090.0813.2~200
    Table 2. Modification parameters
    AlgorithmTrainingtime /sPredictiontime /sTrainingaccuracy /%Predictionaccuracy /%Accuracy(rotate 90°) /%Accuracy(double scale) /%
    LBP+SVM250.1010098.231.237.2
    GLCM+SVM1650.0510097.064.266.5
    Moments+SVM1700.0375.365.255.457.2
    Our450.0110097.086.280.2
    Table 3. Detection results of classification algorithms
    Experiment numberPower /WSpeed /(mm·min-1)Spot diameter /mmStep /mmStatus
    135020000.090.082
    242020000.090.083
    360080000.250.083
    Table 4. Process parameters
    Tian Chongxin, Li Shaoxia, Yu Gang, He Xiuli, Wang Xu. Rapid Detection of Laser Surface Modification Quality Based on Machine Vision[J]. Laser & Optoelectronics Progress, 2020, 57(21): 211407
    Download Citation