Modeling and compensation of MEMS gyroscope output data based on support vector machine

被引：29

作者：

Zhang, Yan-shun ^{[1
]}

Yang, Tao ^{[1
]}

机构：

[1] Beihang Univ, Sch Instrumentat & Optoelect Engn, Beijing 100191, Peoples R China

来源：

MEASUREMENT | 2012年 / 45卷 / 05期

基金：

中国国家自然科学基金;

关键词：

MEMS gyro; Dynamic error; Support vector machine; Error compensation; CLASSIFICATION;

D O I：

10.1016/j.measurement.2012.02.001

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

The modeling and compensation method of the angular rate error of MEMS gyro MG31-300. based on support vector machine, is described in this paper. Reference angular rates were generated by the single-axis rate turntable. The output data of MG31-300 under different input angular rates were collected and analyzed. Considering the nonlinear and random characteristics of the angular rate error, the support vector machine model is established, which uses the output voltage of gyro as the input and provides angular rate error as the output. The resolution of the angular rate error is improved by this modeling method. The result shows that the fitting error of the model was 0.0701 degrees/s (1 sigma). Finally, within MG31-300 measuring range (-300 degrees/s to 300 degrees/s), some testing points besides the training samples were selected to testify and verify the model. The results indicate that, the support vector machine model has high precision and good generalization ability. (C) 2012 Elsevier Ltd. All rights reserved.

引用

页码：922 / 926

页数：5

共 27 条

[1] Automated people-counting by using low-resolution infrared and visual cameras [J].

Amin, I. J. ;

Taylor, A. J. ;

Junejo, F. ;

Al-Habaibeh, A. ;

Parkin, R. M. .

MEASUREMENT, 2008, 41 (06) :589-599

[2] Motor oil classification by base stock and viscosity based on near infrared (NIR) spectroscopy data [J].

Balabin, Roman M. ;

Safieva, Ravilya Z. .

FUEL, 2008, 87 (12) :2745-2752

[3] Gasoline classification by source and type based on near infrared (NIR) spectroscopy data [J].

Balabin, Roman M. ;

Safieva, Ravilya Z. .

FUEL, 2008, 87 (07) :1096-1101

[4] Support vector machine regression (LS-SVM)-an alternative to artificial neural networks (ANNs) for the analysis of quantum chemistry data? [J].

Balabin, Roman M. ;

Lomakina, Ekaterina I. .

PHYSICAL CHEMISTRY CHEMICAL PHYSICS, 2011, 13 (24) :11710-11718

[5] Variable selection in near-infrared spectroscopy: Benchmarking of feature selection methods on biodiesel data [J].

Balabin, Roman M. ;

Smirnov, Sergey V. .

ANALYTICA CHIMICA ACTA, 2011, 692 (1-2) :63-72

[6] Support vector machine regression (SVR/LS-SVM)-an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy data [J].

Balabin, Roman M. ;

Lomakina, Ekaterina I. .

ANALYST, 2011, 136 (08) :1703-1712

[7] Near-infrared (NIR) spectroscopy for motor oil classification: From discriminant analysis to support vector machines [J].

Balabin, Roman M. ;

Safieva, Ravilya Z. ;

Lomakina, Ekaterina I. .

MICROCHEMICAL JOURNAL, 2011, 98 (01) :121-128

[8] Neural network approach to quantum-chemistry data: Accurate prediction of density functional theory energies [J].

Balabin, Roman M. ;

Lomakina, Ekaterina I. .

JOURNAL OF CHEMICAL PHYSICS, 2009, 131 (07)

[9] Calibration of a Novel MEMS Inertial Reference Unit [J].

Bekkeng, Jan K. .

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2009, 58 (06) :1967-1974

[10] ANN based demodulator for UNITS signal measurements [J].

Carni, Domenico Luca ;

Grimaldi, Domenico .

MEASUREMENT, 2006, 39 (10) :877-883

← 1 2 3 →