Jia-ning, ZHONG Ying, LI Xing-fei
（State Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin 300072， China）
Abstract： To improve the prediction accuracy of micro-electromechanical systems (MEMS) gyroscope random drift series, a multi-scale prediction model based on empirical mode decomposition (EMD) and support vector regression (SVR) is proposed. Firstly, EMD is employed to decompose the raw drift series into a finite number of intrinsic mode functions (IMFs) with the frequency descending successively. Secondly, according to the time-frequency characteristic of each IMF, the corresponding SVR prediction model is established based on phase space reconstruction. Finally, the prediction results are obtained by adding up the prediction results of all IMFs with equal weight. The experimental results demonstrate the validity of the proposed model in random drift prediction of MEMS gyroscope. Compared with a single SVR model, the proposed model has higher prediction precision, which can provide the basis for drift error compensation of MEMS gyroscope.
Key words： random drift; MEMS gyroscope; empirical mode decomposition (EMD); support vector regression (SVR); phase space reconstruction; multi-scale prediction
CLD number： V241.5doi： 10.3969/j.issn.1674-8042.2020.03.013
References
［1］Li J, Zheng L G, Wang J Z. Error modeling and filtering for drift of MEMS gyroscope. Chinese Journal of Sensors and Actuators, 2017, 30(5): 731-734.
［2］Xiong B F, Tang C, Wang Q, et al. Research on the modeling of random drift error and filtering technology of low cost MEMS gyroscope. Modeling, Measurement and Control A, 2017, 90(1): 16-31.
［3］Song J L, Shi ZH Y, Wang L H, et al. Improved virtual gyroscope technology based on ARMA model. Micromachines, 2018, 9(7): 348-361.
［4］Gao G W, Xie Y. Application of RPF in MEMS gyro random drift filtering. In: IOP Conference Series: Earth and Environmental Science, Bristol, IOP Publishing, Britain, 2017: 012209.
［5］Li Z M, Duan F Y, Ma J Z. Random drift compensation of MEMS gyroscope based on support vector machine. Chinese Journal of Sensors and Actuators, 2012, 25(8): 1084-1087.
［6］Shen Q, Liu J Y, Wang Q, et al. Random drift compensation of MEMS gyros based on relevance vector machine. Chinese Journal of Sensors and Actuators, 2014, 27(5): 596-599.
［7］Xing H F, Hou B, Lin Z H, et al. Modeling and compensation of random drift of MEMS gyroscopes based on least squares support vector machine optimized by chaotic particle swarm optimization. Sensors, 2017, 17(10): 2335.
［8］Xu Y L, Wang Z S. Random drift modeling and composition for MEMS-based gyroscopes and its application in handwriting trajectory reconstruction. IEEE Access, 2019, 7: 17551-17560.
［9］Wang Z Y, Zhang L J. Predicting the random drift of MEMS gyroscope based on K-means clustering and OLS RBF neural network. In: Proceedings of the SPIE 10463, AOPC 2017: Space Optics and Earth Imaging and Space Navigation, Beijing, China, 2017: 104630C.
［10］Sun T C, Liu J Y. Predicting MEMS gyroscope’s random drifts using LSSVM optimized by modified PSO. In: 2016 IEEE Chinese Guidance, Navigation and Control Conference, Nanjing, China, 2016: 146-149.
［11］Sun T C, Liu J Y, Kang L, et al. Forecasting of MEMS gyroscope’s random drifts based on FIG-SVM. Electronics Optics & Control, 2016, 23(10): 54-58.
［12］Sheng G R, Gao G W, Zhang B Y. Application of improved wavelet thresholding method and an RBF network in the error compensating of an MEMS gyroscope. Micromachines, 2019, 10(9): 608.
［13］Yang H, Jiang H H, Ma X, et al. Application of improved wavelet thresholding method and extreme learning machine in MEMS gyro random errors compensation. Chinese Journal of Sensors and Actuators, 2018, 31(10): 1535-1538.
［14］Ren B, Li H. On forecast modeling of MEMS gyroscope random drift error. In: Proceedings of the 34th Chinese Control Conference, Hangzhou, China, 2015: 4563-4567.
［15］Song J L, Shi ZH Y, Du B H, et al. MEMS gyroscope wavelet de-noising method based on redundancy and sparse representation. Microelectronic Engineering, 2019, 217(15): 111112.
［16］Cai X W, Zhang C X, Gao S, et al. A novel method based on a high-dynamic hybrid forecasting model for fiber optic gyroscope drift. Sensors and Materials, 2017, 29(1): 1-13.
［17］Cui B B, Chen X Y. Study on multi-scale ensemble modeling of FOG temperature drift. Chinese Journal of Scientific Instrument, 2015, 36(2): 304-309.
［18］Wang W, Chen X Y. Modeling and compensation method of FOG temperature drift based on multi-scale and improved support vector machine. Journal of Chinese Inertial Technology, 2016, 24(6): 793-797.
［19］Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. In: Proceedings of the Royal Society A: Mathematical, Physical and Engineering Science, Royal Society, 1998: 903-995.
［20］Smola A J, Schoelkopf B. A tutorial on support vector regression. Statistics and Computing, 2004, 14(3): 199-222.
［21］Kim H S, Eykholt J D. Nonlinear dynamics, delay times, and embedding windows. Physica D: Nonlinear Phenomena, 1999, 127(1): 48-60.
基于EMD-SVR的MEMS陀螺仪随机漂移多尺度预测
何嘉宁， 钟莹， 李醒飞
（天津大学 精密测试技术及仪器国家重点实验室， 天津 300072）
摘要:为了提高MEMS陀螺仪随机漂移序列的预测精度， 提出了一种基于经验模态分解（EMD）和支撑向量回归（SVR）的多尺度预测模型。 首先， 通过EMD分解， 将原始漂移序列分解为有限个频率逐级递减的本征模函数（IMF）。 然后， 根据每个IMF的时频特性， 分别进行相空间重构并建立SVR预测模型。 最后， 将各IMF的预测结果等权相加得到最终预测结果。 实验结果表明， 提出的模型能够有效预测MEMS陀螺仪的随机漂移， 且相比于单一的SVR模型具有更高的预测精度， 可为MEMS陀螺仪漂移误差补偿提供依据。
关键词:随机漂移； MEMS陀螺仪； 经验模态分解； 支撑向量回归； 相空间重构； 多尺度预测
引用格式：HE Jia-ning, ZHONG Ying, LI Xing-fei. Multi-scale prediction of MEMS gyroscope random drift based on EMD-SVR. Journal of Measurement Science and Instrumentation, 2020, 11（3）： 290-296. ［doi： 10.3969／j.issn.1674-8042.2020.03.013］
[full text view]
