• Optics and Precision Engineering
  • Vol. 31, Issue 6, 872 (2023)
Qingzhu LI, Zhining LI*, Zhiyong SHI, and Hongbo FAN
Author Affiliations
  • Shijiazhuang Campus, Army Engineering University of PLA, Shijiazhuang050003, China
  • show less
    DOI: 10.37188/OPE.20233106.0872 Cite this Article
    Qingzhu LI, Zhining LI, Zhiyong SHI, Hongbo FAN. Single heading-line survey of MGTS for magnetic target pattern recognition[J]. Optics and Precision Engineering, 2023, 31(6): 872 Copy Citation Text show less
    Structure of planar-cross MGTS
    Fig. 1. Structure of planar-cross MGTS
    Variation curves of magnetization offset sensitivity of attributes
    Fig. 2. Variation curves of magnetization offset sensitivity of attributes
    MGTS heading-line surveys for pattern recognition training
    Fig. 3. MGTS heading-line surveys for pattern recognition training
    SLFNs model of the ELM
    Fig. 4. SLFNs model of the ELM
    Flow chart of MGTS heading-line surveys for pattern recognition based on SSA-KELM
    Fig. 5. Flow chart of MGTS heading-line surveys for pattern recognition based on SSA-KELM
    Posture characteristics attributes gxx, gxy, gxz, gyy, gyz, ΔT, λ3, I2, cos θ measurement signal
    Fig. 6. Posture characteristics attributes gxxgxygxzgyygyzΔTλ3I2, cos θ measurement signal
    Dimensionless waveform feature fractal dimension of the posture characteristics attributes signal
    Fig. 7. Dimensionless waveform feature fractal dimension of the posture characteristics attributes signal
    Target posture characteristics recognition accuracy and feature visualization in PCA dimensionality reduction process
    Fig. 8. Target posture characteristics recognition accuracy and feature visualization in PCA dimensionality reduction process
    Target magnetization direction and shape recognition results
    Fig. 9. Target magnetization direction and shape recognition results
    Dimensional waveform features fractal dimension of shape characteristic attributes signal
    Fig. 10. Dimensional waveform features fractal dimension of shape characteristic attributes signal
    Target geometric shape recognition accuracy and feature visualization in PCA dimensionality reduction process
    Fig. 11. Target geometric shape recognition accuracy and feature visualization in PCA dimensionality reduction process
    Target single heading-line surveys training experiment and the magnets to be measured
    Fig. 12. Target single heading-line surveys training experiment and the magnets to be measured
    Measurement results of the posture characteristic attributes of the magnets three poses on the first route
    Fig. 13. Measurement results of the posture characteristic attributes of the magnets three poses on the first route
    Measurement results of the shape characteristic attributes of the magnets three shapes on the first route
    Fig. 14. Measurement results of the shape characteristic attributes of the magnets three shapes on the first route
    3D feature distribution of posture and shape characteristic attributes (the original 54D dataset was reduced to 3D by PCA)
    Fig. 15. 3D feature distribution of posture and shape characteristic attributes (the original 54D dataset was reduced to 3D by PCA)
    Recognition results of three labels for the pose and shape of the magnets in the experiment
    Fig. 16. Recognition results of three labels for the pose and shape of the magnets in the experiment
    特征符号特征描述计算公式
    Para1最大幅值maxsi
    Para2平均幅值1ni=1nsi
    Para3均方根值1ni=1nsi2
    Para4峭度1ni=1nsi4/Para34
    Para5偏度1ni=1nsi3/Para33
    Para6波形因子Para3/Para2
    Para7峰值因子maxsi-minsi/Para3
    Para8脉冲因子maxsi-minsi/Para2
    Para9裕度Para1/1ni=1nsi2
    Table 1. Statistical characteristic parameters of signal waveforms
    序号ID序号ID
    Dipole 1100Dipole 660200
    Dipole 22040Dipole 770240
    Dipole 33080Dipole 880280
    Dipole 440120Dipole 990320
    Dipole 550160---
    Table 2. Nine groups of magnetization directions of magnetic dipoles for recognition
    序号形状类别形状尺寸/mI/(°)D/(°)
    Object 1球体ϕ 0.6100
    Object 2ϕ 0.730160
    Object 3ϕ 0.83080
    Object 4ϕ 0.940120
    Object 5ϕ 1.050160
    Object 6长方体0.6×0.6×0.6900
    Object 71.0×0.4×0.470160
    Object 80.2×0.6×1.250280
    Object 90.4×0.6×1.030-30
    Object 100.6×1.2×0.210120
    Object 11水平圆柱体ϕ 0.6×1.0100
    Object 12ϕ 0.8×0.830160
    Object 13ϕ 1.0×0.650-80
    Object 14ϕ 1.2×0.470-30
    Object 15ϕ 1.4×0.290120
    Table 3. The 15 groups of shapes of uniformly magnetized geometry for recognition
    磁铁1磁铁2磁铁3
    尺寸/cmϕ2.0×2.010.0×3.0×1.06.0×4.0×1.0
    磁矩m /(A·m2(0.04,0.08,4.13)(-2.84, -0.27, 22.77)(-0.63, -0.81, 11.46)
    形状类别圆柱体长方体1长方体2
    姿态图正上
    正南
    正西
    Table 4. Size, magnetic moment, shape and posture category and posture diagram of magnets
    Qingzhu LI, Zhining LI, Zhiyong SHI, Hongbo FAN. Single heading-line survey of MGTS for magnetic target pattern recognition[J]. Optics and Precision Engineering, 2023, 31(6): 872
    Download Citation