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NSGA-Ⅱ&BP的应变片式压力传感器温度补偿研究

基于NSGA-Ⅱ&BP的应变片式压力传感器温度补偿研究

190    2020-06-22

¥0.50

全文售价

作者:郭志君, 卢文科, 左锋, 张珏, 丁勇

作者单位:东华大学信息科学与技术学院, 上海 201620


关键词:应变片式压力传感器;温度补偿;带精英策略的快速非排序遗传算法;BP神经网络


摘要:

应变片式压力传感器容易受到温度的影响,需要对该传感器进行温度补偿,针对该问题提出一种带精英策略的快速非排序遗传算法(NSGA-Ⅱ)与BP神经网络相结合的软件补偿模型。该模型将BP神经网络中2个输出值与期望值误差作为NSGA-Ⅱ同时寻求最小的2个目标,对BP神经网络初始权值和阈值进行优化,克服单一BP神经易陷入局部极小值的缺陷。通过该算法模型对不同温度下压力传感器的输出值进行数据融合,研究结果表明,补偿后的传感器零位温度系数(α0)和灵敏度温度系数(αs)均提高两个数量级,从而证明NSGA-Ⅱ&BP算法的温度补偿模型可以有效提高该传感器的温度稳定性。


Temperature compensation of strain gauge pressure sensor based on NSGA-Ⅱ&BP
GUO Zhijun, LU Wenke, ZUO Feng, ZHANG Jue, DING Yong
College of Information Science and Technology, Donghua University, Shanghai 201620, China
Abstract: The strain gauge pressure sensor is easily affected by temperature, so it needs to be compensated. To solve this problem, a software compensation model with NSGA-Ⅱ and BP neural network is proposed. The model optimizes the initial weights and thresholds of the BP neural network by taking two output and expected value error of the BP as two targets of the NSGA-Ⅱ to seek the minimum simultaneously, which overcomes the defect that the single BP is easy to fall into the local minimum. The output values of pressure sensors at different temperatures were fused by the algorithm model, the results show that the α0 and the αs of the sensor are increased by two orders of magnitude, which proves that the temperature compensation model of NSGA-Ⅱ & BP algorithm can effectively improve the temperature stability of the sensor.
Keywords: strain gauge pressure sensor;temperature compensation;fast and elitist non-dominated sorting genetic algorithm;BP neural network
2020, 46(6):72-77  收稿日期: 2019-11-26;收到修改稿日期: 2020-02-18
基金项目: 国家自然科学基金项目(61274078)
作者简介: 郭志君(1995-),男,河北沧州市人,硕士研究生,专业方向为传感器技术
参考文献
[1] 盛文军. 压力传感器发展现状综述[J]. 科技经济导刊, 2018, 26(18): 54
[2] 游江辉. 快速称重传感器弹性体结构参数优化及试验研究[D]. 长沙: 中南林业科技大学, 2019.
[3] 王彪, 刘腾, 徐敬龙, 等. 金属粘贴式电阻应变计应变传递分析[J]. 中国测试, 2016, 42(8): 1-6
[4] 许艺青, 杨晓翔, 韦铁平, 等. 电阻应变片敏感栅结构参数对应变传递的影响研究[J]. 机电工程, 2018, 35(4): 352-357
[5] ZAMANI N, KHAMESEE M B, KHAN M I. Novel laser processed shape memory alloy actuator design with an embedded strain gauge sensor using dual resistance measurements. Part I: Fabrication and model-based position estimation[J]. Sensors & Actuators: A. Physical, 2017, 263: 234-245
[6] BEDNARZ E T, ZHU W, SMITH S A. Identifying magnitudes and locations of multiple loads and the resultant of a distributed load on a slender beam using strain gage based methods[J]. Experimental Techniques, 2016, 40(1): 15-25
[7] LI J, HU G, ZHOU Y, et al. A temperature compensation method for piezo-resistive pressure sensor utilizing chaotic ions motion algorithm optimized hybrid kernel LSSVM[J]. Sensors, 2016, 16(10): 1707
[8] ZHU C, ZHANG J, LIU Y, et al. Comparison of GA-BP and PSO-BP neural network models with initial BP model for rainfall-induced landslides risk assessment in regional scale: a case study in Sichuan, China[J]. Natural Hazards, 2020, 100(1): 173-204
[9] LI Y, LI J, HUANG J, et al. Fitting analysis and research of measured data of SAW micro-pressure sensor based on BP neural network[J/OL]. Measurement, 2020,155:107533. DOI: 10.1016/j.measurement.2020.107533.
[10] 郭修豪. 改进遗传算法在多目标问题上的应用研究[D]. 重庆: 重庆师范大学, 2016.
[11] 袁明. 电阻应变式传感器误差原因以及补偿方法[J]. 电子技术与软件工程, 2019(9): 227
[12] BI X, WANG C. An improved NSGA-III algorithm based on elimination operator for many-objective optimization[J]. Memetic Computing, 2017, 9(4): 361-383
[13] LI Q, WANG X, ZHANG X. A scheduling method based on NSGA2 for steelmaking and continuous casting production process[J]. IFAC PapersOnLine, 2018, 51(18): 174-179
[14] 崔萌洁, 卢文科, 左锋. 基于PSO-BP模型的扩散硅压力传感器温度补偿[J]. 中国测试, 2019, 45(11): 95-100
[15] 范厚明, 徐振林, 李阳, 等. 混合遗传算法求解多中心联合配送路径问题[J]. 上海交通大学学报, 2019, 53(8): 1000-1009