Chinese Optics, Volume. 18, Issue 3, 596(2025)

Magnetic field reconstruction at test mass using the multi-stage bias correction model

Ye LIU1,2, Xing-jian SHI1, Zhi-ming CAI1, Wen-zhe YANG1, and Hua-wang LI1、*
Author Affiliations
  • 1Innovation Academy for Microsatellites of Chinese Academy of Sciences, Shanghai 201304, China
  • 2University of Chinese Academy of Sciences, Beijing 100049, China
  • show less
    Figures & Tables(12)
    Distribution of magnetic sources, magnetometers, and test mass in the space gravitational wave detection spacecraft
    The basic structure of the neural network based magnetic field reconstruction method
    Structure of the Multi-Stage Bias Correction Model (MSBCM)
    Training and testing of MSBCM on the LISA Pathfinder dataset
    Training and testing of MSBCM on the eLISA dataset
    Thermal maps of the magnetic field surrounding Taiji-2 TM1 reconstructed by different methods
    Reconstruction of magnetic field fluctuations and gradient acceleration noise along the sensitive axes of TM1 and TM2 using different methods
    • Table 1. Magnetic field reconstruction results for LISA Pathfinder

      View table
      View in Article

      Table 1. Magnetic field reconstruction results for LISA Pathfinder

      方法${\bar \varepsilon _{\boldsymbol{B}}}$/%${\varepsilon _{{\boldsymbol{B}},{\mathrm{max}}}}$/%
      |B|BxByBz|B|BxByBz
      TM1Taylor89.25518.92564.37694.502745.34573610.11604412.842461076.40
      WD126.26646.60637.91798.673767.01477011.43739996.092450750.40
      Multipole85.51523.51524.85647.883452.78467206.45759302.881998534.80
      DWME113.38616.28663.83723.733645.20451613.531097369.801873063.70
      XGBoost86.30755.93884.031378.015161.49440535.35617789.703250015.40
      MSBCM26.57201.07231.66212.581055.81131405.62325384.40327050.17
      TM2Taylor206.231477.861385.792117.366337.632501042.401602870.806981814.10
      WD270.931749.381998.341929.935561.222664887.903045968.803634591.40
      Multipole203.871434.701624.281774.255552.771994890.202521400.004399474.20
      DWME249.191627.781920.931561.215248.442215714.602922788.101403577.60
      XGBoost19.29210.34255.02203.201305.22438854.54217929.15279339.43
      MSBCM18.32220.39215.91200.621418.04612493.07140519.40412914.94
    • Table 2. Magnetic field reconstruction results for eLISA

      View table
      View in Article

      Table 2. Magnetic field reconstruction results for eLISA

      方法${\bar \varepsilon _{\boldsymbol{B}}}$/%${\varepsilon _{{\boldsymbol{B}},{\mathrm{max}}}}$/%
      |B|BxByBz|B|BxByBz
      Taylor0.842.503.183.546.851590.3913222.555296.21
      WD0.842.503.183.546.851590.3913222.555296.21
      Multipole1.012.983.133.646.751766.278960.395552.00
      DWME1.012.983.133.646.751766.278960.395552.00
      XGBoost1.218.6810.658.6525.0010906.8722410.274816.18
      MSBCM0.181.531.302.423.491177.872822.872453.91
    • Table 3. Magnetic field reconstruction results for Taiji-2

      View table
      View in Article

      Table 3. Magnetic field reconstruction results for Taiji-2

      方法${\bar \varepsilon _{\boldsymbol{B}}}$/%${\varepsilon _{{\boldsymbol{B}},{\mathrm{max}}}}$/%
      |B|BxByBz|B|BxByBz
      TM1Taylor15.1184.79123.55207.12887.4433066.1448781.65425602.34
      WD8.8348.0699.05158.43743.9029353.6445913.87282891.87
      Multipole11.7455.34111.75185.63706.0215681.8952423.43362661.43
      DWME15.6179.26123.28201.891025.8733688.5762955.00374511.89
      XGBoost3.4229.9224.3837.60181.2819632.5722803.73104671.03
      MSBCM1.3512.8710.8214.38145.247294.006317.0830633.32
      TM2Taylor15.33115.74142.19153.31442.41108830.68185920.57155773.28
      WD8.7173.17104.46115.51216.97104259.11107441.8992245.70
      Multipole11.8274.48123.59134.94341.0944944.78118690.82131479.33
      DWME15.69113.35133.23147.43371.9388090.07153712.76144410.41
      XGBoost2.9422.8123.3823.0155.468802.7516855.7737746.41
      MSBCM1.1013.8511.7712.4823.7719169.0629637.8013418.15
    • Table 4. RMSE of magnetic field fluctuations and magnetic gradient fluctuations using different methods

      View table
      View in Article

      Table 4. RMSE of magnetic field fluctuations and magnetic gradient fluctuations using different methods

      方法RMSE (${\mathrm{m}}\cdot {\mathrm{s}}^{-2}{\mathrm{Hz}}^{-\tfrac{1}{2}} $)
      $\delta {a_{\delta {B_x}}}$$\delta {a_{\delta \nabla {B_x}}}$
      TM1Taylor3.47×10−176.42×10−17
      WD2.74×10−171.28×10−16
      Multipole9.17×10−171.10×10−16
      DWME5.98×10−175.83×10−17
      XGBoost4.63×10−157.48×10−14
      MSBCM1.68×10-174.00×10-17
      TM2Taylor3.02×10−163.47×10−16
      WD9.39×10-172.42×10-16
      Multipole4.06×10−168.97×10−16
      DWME4.47×10−161.02×10−15
      XGBoost4.49×10−157.41×10−14
      MSBCM1.72×10−162.93×10−16
    • Table 5. Ablation study

      View table
      View in Article

      Table 5. Ablation study

      方法弱预测模型${\bar \varepsilon _{\boldsymbol{B}}}$/%
      Bx (TM1)Bx (TM2)
      MSBCMStMLP20.7624.01
      StMLP19.6822.41
      ReMLP16.0114.58
      ReMLP13.8512.87
      模型一StMLP20.7624.01
      StMLP19.6822.41
      StMLP-LM15.2414.92
      StMLP-LM13.4914.44
      模型二StMLP20.7624.01
      StMLP19.6822.41
      StMLP17.2117.48
      StMLP15.5514.35
    Tools

    Get Citation

    Copy Citation Text

    Ye LIU, Xing-jian SHI, Zhi-ming CAI, Wen-zhe YANG, Hua-wang LI. Magnetic field reconstruction at test mass using the multi-stage bias correction model[J]. Chinese Optics, 2025, 18(3): 596

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Special Column on Space-based Gravitational Wave Detection

    Received: Oct. 5, 2024

    Accepted: Jan. 21, 2025

    Published Online: Jun. 16, 2025

    The Author Email:

    DOI:10.37188/CO.2024-0181

    Topics