登录    |    注册

您好,欢迎来到中国测试科技资讯平台!

首页> 《中国测试》期刊 >本期导读>基于PSO-BP模型的扩散硅压力传感器温度补偿

基于PSO-BP模型的扩散硅压力传感器温度补偿

67    2019-11-28

¥0.00

全文售价

作者:崔萌洁, 卢文科, 左锋

作者单位:东华大学信息科学与技术学院, 上海 201620


关键词:半导体技术;压力传感器;温度补偿;粒子群算法;BP神经网络


摘要:

硅的电导率易受温度影响,导致扩散硅压力传感器的输出电压随温度变化产生漂移,需对该传感器进行温度补偿,针对该问题提出粒子群优化的BP神经网络算法(PSO-BP)。通过二维标定实验,利用温度传感器监测实验环境温度,得到扩散硅压力传感器在不同工作温度下的输入输出特性曲线,建立PSO-BP模型。该模型利用粒子群算法全局寻优的能力为BP神经网络算法初始权值和阈值选取最优解,弥补传统BP神经网络初始值随机选取的弊端,克服容易局部陷入极值的缺陷。实验结果表明,经过PSO-BP模型补偿后的输出零位温度系数和灵敏度温度系数均减小一个数量级,证实该模型能够有效降低温度对扩散硅压力传感器的影响。


Temperature compensation of diffused-silicon pressure sensor based on PSO-BP
CUI Mengjie, LU Wenke, ZUO Feng
College of Information Science and Technology, Donghua University, Shanghai 201620, China
Abstract: The conductivity of silicon is susceptible to temperature, which causes the output voltage of diffused silicon pressure sensor to drift with temperature. Therefore, temperature compensation of the sensor must be carried out. To solve this problem, a BP neural network algorithm based on particle swarm optimization (PSO-BP) is proposed. Through two-dimensional calibration experiment, the temperature sensor is used to monitor the experimental environment temperature, and the input and output characteristic curves of diffused silicon pressure sensor at different operating temperatures are obtained, and the PSO-BP model is established. The model uses the ability of particle swarm optimization to select the optimal solution for the initial weights and thresholds of BP neural network algorithm, which makes up for the shortcomings of random selection of the initial values of traditional BP neural network and overcomes the shortcomings of easily falling into local extremes. The experimental results show that the output zero temperature coefficient and sensitivity temperature coefficient are reduced by an order of magnitude after compensation by PSO-BP model, which proves that the model can effectively reduce the influence of temperature on diffused silicon pressure sensor.
Keywords: semiconductor technology;pressure transducer;temperature compensation;particle swarm optimization;BP neural network
2019, 45(11):95-100,125  收稿日期: 2018-12-20;收到修改稿日期: 2019-01-24
基金项目:
作者简介: 崔萌洁(1995-),女,新疆昌吉州人,硕士研究生,专业方向为传感器技术
参考文献
[1] 鲍玉军, 钱显毅, 何一鸣. 采用PID算法的高稳定恒流源设计[J]. 南京航空航天大学学报, 2013, 45(4):570-574
[2] 李仙丽, 陈洪敏.一种数字温度补偿系统及实现[C]//面向航空试验测试技术——2013年航空试验测试技术峰会暨学术交流会论文集, 2013.
[3] 欧阳承曦. 硅压阻式压力传感器高精度温度补偿技术研究[D]. 成都:电子科技大学,2015.
[4] LEE Y T, SEO H D, KAWAMURA A, et al.Compensation method of offset and it's temperature drift in silicon piezoresistive pressure sensor using double Wheatstone-bridge configuration[C]//Proceedings of the International Solid-State Sensors and Actuators Conference-TRANSDUCERS'95. IEEE, 1995.
[5] 王丰. 硅压力传感器研究现状[J]. 半导体情报, 1999(6):35-37
[6] 孟丹丹, 陈兵, 秦文. 扩散硅压力变送器的温度补偿方法[J]. 仪器仪表用户, 2016, 23(4):5-7
[7] ZHOU G, ZHAO Y, GUO F, et al. A smart high accuracy silicon piezoresistive pressure sensor temperature compensation system[J]. SENSORS, 2014, 14(7):12174-12190
[8] 徐广忠. 扩散硅压力传感器[J]. 水电厂自动化, 1995(1):56-60
[9] SINGH R, NGO L L, SENG H S, et al. A silicon piezoresistive pressure sensor[C]//IEEE International Workshop on Electronic Design. IEEE, 2002.
[10] 何崇杰. 桥臂电阻对惠斯通电桥灵敏度的影响[J]. 课程教育研究, 2014(34):157-158
[11] YANG B, CHENG L. Study of a new global optimization algorithm based on the standard PSO[J]. Journal of Optimization Theory & Applications, 2013, 158(3):935-944
[12] 李擎, 张超, 陈鹏, 等. 一种基于粒子群参数优化的改进蚁群算法[J]. 控制与决策, 2013(6):873-878
[13] 师洪涛, 杨静玲, 丁茂生, 等. 基于小波-BP神经网络的短期风电功率预测方法[J]. 电力系统自动化, 2011, 35(16):44-48
[14] ZHANG L, ZHAO J Q, ZHANG X N, et al. Study of a new improved PSO-BP neural network algorithm[J]. Journal of Harbin Institute of Technology, 2013, 20(5):106-112
[15] 魏凯斌. 一种扩散硅压力传感器温度补偿系统的设计与实现[J]. 制造业自动化, 2013, 35(9):117-119