Piezoelectrics & Acoustooptics, Volume. 45, Issue 4, 629(2023)

MEMS Temperature Drift Compensation Method Based on GSA-SVR Algorithm

MEI Fangyu1, GU Shengchuang2, and QIU Haitao1
Author Affiliations
  • 1[in Chinese]
  • 2[in Chinese]
  • show less

    Aiming at the problem that the zero bias of MEMS instrument is greatly affected by temperature change, this paper proposes a compensation method for MEMS zero bias temperature drift based on the gravitational search algorithm-support vector regression (GSA-SVR). Firstly, the output signals of MEMS gyro and MEMS accelerometer are preprocessed by wavelet transform, and then the temperature of MEMS under different working conditions is modeled and compensated by GSA-SVR algorithm. The experimental results show that in the stable working stage, compared with before compensation, the output standard deviation of accelerometer and gyro after compensation has been reduced by 90% and 85%, respectively. Compared with traditional SVR, the proposed method is more accurate and practical. The GSA-SVR algorithm reduces the standard deviation of accelerometer and gyro outputs by 6% and 10%, respectively.


    Get Citation

    Copy Citation Text

    MEI Fangyu, GU Shengchuang, QIU Haitao. MEMS Temperature Drift Compensation Method Based on GSA-SVR Algorithm[J]. Piezoelectrics & Acoustooptics, 2023, 45(4): 629

    Download Citation

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

    Special Issue:

    Received: May. 1, 2023

    Accepted: --

    Published Online: May. 9, 2024

    The Author Email: