PSO优化SVM的MEMS陀螺温度零偏补偿

针对微机械陀螺零偏受温度影响较大的问题, 提出一种粒子群优化(PSO)算法和支持向量机(SVM)相结合的陀螺零偏温度补偿方法。首先, 将平滑处理后的陀螺数据作为样本点, 采用基于径向基核函数的支持向量机方法构建漂移模型, 把数据从低维空间映射到高维空间, 并进行线性拟合, 保证泛化能力。然后, 利用粒子群算法对支持向量机的惩罚参数、核函数参数以及不敏感系数进行优化, 避免了人为选择参数的盲目性且提高了建立模型的精度。实验结果表明：经PSO调节支持向量机算法补偿后, 陀螺输出精度更高; 与最小二乘法、BP神经网络法相比, 陀螺输出数据方差分别减小了81.3%和57%, 最大误差分别减小54.7%和48.5%。

Abstract

Aiming at the problem that bias of MEMS gyroscope is severely affected by temperature, a temperature compensation method based on Particle Swarm Optimization (PSO) and Support Vector Machine (SVM) is proposed. Firstly, the smoothed gyroscope data is taken as the sample point, and the drift model is constructed by the SVM method based on radial basis kernel function. The data is mapped from low-dimensional space to high-dimensional space for linear fitting to ensure generalization ability. Then, the PSO algorithm is used to optimize the penalty parameters, kernel function parameters and bias parameters of the SVM, which avoids the blindness of artificial parameter choosing and improves the accuracy of the model. Experimental results show that gyro output accuracy is higher after PSO-adjusted SVM compensation. Compared with the least squares method and the BP neural network method, the variance of the gyro output data is reduced by 81.3% and 57% respectively, and the maximum error is reduced by 54.7% and 48.5% respectively.

参考文献

[1] WANG L, ZHANG W, ZHANG Z P, et al. Spinning frequency estimation algorithm of MEMS gyro's output signal based on FFT coefficient［J］.Microsystem Technologies, 2018, 24(4):1789-1793.

[2] KOURANI A, HEGAZI E, ISMAIL Y. Electronic frequency compensation of AlN-on-Si MEMS reference oscillators［J］. Microelectronics Journal, 2016, 54:72-84.

[3] WU X Z, LIU Z L, LI S Y. Influence factors and enhance-ment on property of micro-silicon gyroscopes［J］. Micronanoelectronic Technology, 2003, 7(8):274-277.

[4] WU X Z, LIU Z L,LI S Y. Influence factors and enhance-ment on property of micro-silicon gyroscopes［J］. Micronanoelectronic Technology, 2003, 7(8): 274-277.

[5] KUMAR P.Multilevel communication optimal least squares［C］//International Conference on Computational Science, Reykjavik, Iceland, 2015: 1838-1847.

[6] 陈辰, 吕跃勇, 马广富, 等. 基于神经网络的RLV再入段有限时间自适应姿态控制［J］.宇航学报,2017, 38(3):279-286.

[7] VAPNIK V N. The nature of statistical learning theory［M］. New York:Springer, 1999.

[8] 顾胜, 魏蛟龙, 皮德常. 一种粒子群模糊支持向量机的航天器参量预测方法［J］.宇航学报, 2014, 35(11):1270-1276.

[9] FRIEDRICHS F. Evolutionary tuning of multiple SVM parameters［J］. Neurocomputing, 2017, 64(2):107-117.

[10] 王娟, 刘明光. 基于粒子群算法-最小二乘支持向量机算法的磁化曲线拟合［J］. 电机与控制应用, 2017, 44(7):26-29.

[11] XAVIER A L, Jr, CELASCHI S. Groundwater monitoring of a hidric shortage crisis in Brazil based on LS-SVM forecasts for the city of S, o Paulo［J］.International Journal of Scientific & Engineering Research, 2017, 8(1): 1-9.

高策, 沈晓卫, 章彪, 胡豪杰. PSO优化SVM的MEMS陀螺温度零偏补偿[J]. 电光与控制, 2019, 26(6): 100. GAO Ce, SHEN Xiaowei, ZHANG Biao, HU Haojie. Temperature Compensation of MEMS-Gyro Based on Particle Swarm Optimization and Support Vector Machines[J]. Electronics Optics & Control, 2019, 26(6): 100.

PSO优化SVM的MEMS陀螺温度零偏补偿

关于本站 Cookie 的使用提示

全站搜索

PSO优化SVM的MEMS陀螺温度零偏补偿

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索