ZHANG Jia1， CHEN Yonglu2， ZHANG Li3， GONG Xiaoqing4
（1. School of Electronic Engineering, Xi’an Aeronautical University, Xi’an 710077， China；2. Chinese Flight Test Establishment, Xi’an 710089, China；3. Xi’an Yuanfang General Aviation Technology Development Co., Ltd., Xi’an 710089， China；4. Chinasoft International Technology Service Co., Ltd., Xi’an 710077， China）
Abstract： To solve the output signal drift of capacitive micro-electromechanical system (MEMS) shear stress sensor caused by the change of operation temperature, a sine cosine algorithm-support vector regression (SCA-SVR) for temperature compensation is proposed. The hyper-parameters of SVR are optimized based on the SCA. The proposed SCA-SVR temperature compensation algorithm is compared with the widely used partical swarm optimization-support vector regression (PSO-SVR) algorithm through experiments. The experimental results indicate that the temperature compensation algorithm based on the SCA-SVR can effectively compensate the output temperature drift of capacitive MEMS shear stress sensor. The correlation coefficient between the sensor output signal compensated by the SCA-SVR algorithm and the calibration value is increased to 0.999 6, and the root mean square error is reduced to 0.009 9 mV, which is smaller than the counterpart of PSO-SVR by an order of magnitude.
Key words： micro-electromechanical system (MEMS)； shear stress sensor； temperature compensation； sine cosine algorithm (SCA)； support vector regression (SVR)
References
［1］ DONG X S, HUANG Q W, XU W, et al. Research on temperature characteristic of parasitic capacitance in MEMS capacitive accelerometer. Sensors & Actuators: A. Physical, 2018, 285: 581-587.
［2］ AKTAKKA E E, NAJAFI K, A six-axis micro platform for in situ calibration of MEMS inertial sensors//29th International Conference on Micro Electro Mechanical Systems (MEMS), Jan. 24-28, 2016, Shanghai, China. New York: IEEE, 2016: 243-246.
［3］ MUTHARPAVALAR A, AHMED A Y, NOR N M, Design, modeling and simulation of MEMS resonator for humidity sensor application//IEEE Sensors Applications Symposium, Mar. 9-11, 2020, Kuala Lumpur, Malaysia. New York: IEEE, 2020: 1-6.
［4］ LAZARUS N, BEDAIR S, LO C, et al. CMOS-MEMS capacitive humidity sensor. Journal of Microelectromechanical Systems, 2010, 19(1), 183-191.
［5］ KANG R, LIU H F, WEI X L, et al. A high-resolution area-change-based capacitive MEMS tilt sensor. Sensors and Actuators: A. Physical, 2020, 313: 112191.
［6］ ZHAO L, YEATMAN E M. Micro capacitive tilt sensor for human body movement detection. IFMBE Proceedings, 2007, 13: 195-200.
［7］ SHIRHATTI V, KEDAMBAIMOOLE V, NUTHALAPATI S, et al. High-range noise immune supersensitive graphene-electrolyte capacitive strain sensor for biomedical applications. Nanotechnology, 2019, 30(47): 475502.
［8］ SUSTER M, GUO J, CHAIRMANONART N, et al. A high-performance MEMS capacitive strain sensing system. Journal of Microelectromechanical Systems, 2006, 15(5): 1069-1077.
［9］ LI J G, LONGTIN J P, TANKIEWICZ S, et al. Interdigital capacitive strain gauges fabricated by direct-write thermal spray and ultrafast laser micromachining. Sensors & Actuators: A. Physical, 2006, 133(1): 1-8.
［10］ ARAGHI G, LANDRY R J. Temperature compensation model of MEMS inertial sensors based on neural network//IEEE/ION Position, Location and Navigation Symposium, Apr. 23-26, 2018, Monterey, USA. New York: IEEE, 2018, 301-309.
［11］ CUONG D, SESHIA A A. Active temperature compensation for MEMS capacitive sensor. IEEE Sensors Journal, 2021, 21(17): 18588-18592.
［12］ FRAN C. ASM ready reference: thermal properties of metals. Novelty: ASM International, 2002.
［13］ WATANABE H, YAMADA N, OKAJI M. Linear thermal expansion coefficient of silicon from 293 to 1 000 K. International Journal of Thermophysics, 2004, 25(1): 221-236.
［14］ GUO W, Geng L, YAN W, et al. Application of least squares-support vector machine in system-level temperature compensation of ring laser gyroscope. Measurement, 2011, 44(10): 1898-1903.
［15］ LI S K, LIU Y, LIU Y F, et al. MEMS gyroscope temperature drift compensation for SVR optimized by artificial bee colony//Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery. Berlin:Springer, 2021.
［16］ LI S, FANG H J, LIU X Y. Parameter optimization of support vector regression based on sine cosine algorithm. Expert Systems with Applications, 2018, 91: 63-77.
［17］ AHMAD M S, ADNAN S M, ZAIDI S, et al. A novel support vector regression (SVR) model for the prediction of splice strength of the unconfined beam specimens. Construction and Building Materials, 2020, 248: 118475.
［18］ MIRJALILI S. SCA: a sine cosine algorithm for solving optimization problems. Knowledge-Based Systems, 2016, 96: 120-133.
［19］ LYU F, FAN X Y, DING F X, et al. Prediction of the axial compressive strength of circular concrete-filled steel tube columns using sine cosine algorithm-support vector regression. Composite Structures, 2021, 273: 114282.
正弦余弦算法支持向量回归在MEMS剪应力传感器温度补偿中的应用
张佳1， 陈永禄2， 张莉3， 宫小清4
（1. 西安航空学院 电子工程学院， 陕西 西安 710077； 2. 中国飞行试验研究院， 陕西 西安 710089； 3. 西安远方航空技术发展总公司， 陕西 西安 710089； 4. 中软国际科技服务有限公司， 陕西 西安 710077）
摘要：为解决电容式微机电系统（Micro-electromechanical system, MEMS）剪应力传感器输出信号随工作环境温度变化产生漂移的问题， 提出了基于正弦余弦算法的支持向量回归（Sine cosine algorithm-support vector regression, SCA-SVR）温度补偿算法。 首先， 利用SVR对传感器温漂进行补偿； 其次， 基于SCA对SVR的超参数进行优化； 最后， 将所提出的SCA-SVR温度补偿算法与广泛应用的粒子群支持向量回归（Partical swarm optimization-support vector regression, PSO-SVR）算法进行实物实验对比。 结果表明， 基于SCA-SVR的温度补偿算法能够有效地对电容式MEMS剪应力传感器的输出温漂进行补偿， SCA-SVR算法补偿后的传感器输出信号与整定值间的相关系数提高至0.999 6， 均方根误差降低至0.009 9 mV， 比PSO-SVR算法补偿后的结果降低了一个数量级。
关键词：微机电系统； 剪应力传感器； 温度补偿； 正弦余弦算法； 支持向量回归
引用格式：ZHANG Jia, CHEN Yonglu, ZHANG Li, et al． Application of sine cosine algorithm-support vector regression on temperature compensation of MEMS shear stress sensor． Journal of Measurement Science and Instrumentation， 2023， 14（3）： 263-269. DOI： 10．3969／j．issn．1674-8042．2023．03．002
[full text view]
