PSO-ASVR在三波长路面状态传感器定量标定中的应用

杨森; 田雨卉; 张厚庆

doi:10.5768/JAO202344.0103005

PSO-ASVR在三波长路面状态传感器定量标定中的应用

doi: 10.5768/JAO202344.0103005

东北林业大学机电工程学院，黑龙江哈尔滨 150040

基金项目: 中央高校基本科研业务费专项资金资助(2572019BF01)

详细信息

作者简介:
杨森（1987—），男，博士，讲师，主要从事路面状态检测、红外辐射测量和食品安全检测技术研究。E-mail：yangsen@nefu.edu.cn

张厚庆（1998—），男，硕士，主要从事路面状态检测和红外辐射测量等技术研究。E-mail：1695641968@qq.com

通讯作者:
田雨卉（1997—），女，硕士，主要从事路面状态检测和红外辐射测量等技术研究。E-mail：1620673814@qq.com

中图分类号: TN206
计量
- 文章访问数: 93
- HTML全文浏览量: 64
- PDF下载量: 5
- 被引次数: 0
出版历程
- 收稿日期: 2022-03-21
- 修回日期: 2022-07-04
- 网络出版日期: 2022-07-05
- 刊出日期: 2023-01-17

Application of PSO-ASVR in quantitative calibration of three-wavelength pavement state sensor

School of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China

摘要

摘要: 路面状态传感器是路面状态定性识别和定量测量的重要工具，其定量测量性能依赖于定量标定模型的准确性。为了解决路面状态传感器定量标定数据非线性和非均匀分布问题对定量测量的不利影响，提出基于PSO-ASVR(particle swarm optimization - adaptive support vector regression)的路面状态传感器定量标定模型。构建AP(adaptive preprocessing)流程进行标定数据最优化预处理,降低路面状态传感器非均匀分布问题影响下的标定数据处理误差。采用基于结构风险最小化的SVR(support vector regression)算法进行标定数据拟合，并利用PSO(particle swarm optimization)算法实现SVR中参数最优化，降低路面状态传感器标定数据非线性引入的数据拟合误差。不同路面状态条件下标定数据处理实验表明：新方法相比于传统方法在均方根误差RMSE上至少可减小63%，验证了其在提高定量标定模型精度上的有效性，实现了路面状态传感器定量标定误差的降低。
- 路面状态传感器 /
- 标定模型 /
- 数据拟合 /
- 误差分析
Abstract: Pavement state sensor is an important tool for qualitative identification and quantitative measurement of pavement state, and its quantitative measurement performance depends on the accuracy of quantitative calibration model. In order to solve the problem of nonlinearity and nonuniform distribution of quantitative calibration data of pavement state sensor, a quantitative calibration model of pavement state sensor based on particle swarm optimization-adaptive support vector regression (PSO-ASVR) was proposed. Firstly, the adaptive preprocessing (AP) process was constructed to optimize the pre-processing of the calibration data to reduce the calibration data processing error under the influence of the nonuniform distribution of the pavement state sensor. Then, the support vector regression (SVR) algorithm based on structural risk minimization was used to fit the calibration data, and the particle swarm optimization (PSO) algorithm was used to realize the parameter optimization in the SVR to reduce the data fitting error introduced by the nonlinear calibration data of the pavement state sensor. Experiments on calibration data processing under different pavement states show that the root-mean-square error (RMSE) of the new method can be reduced by at least 63% compared with that of the traditional method, which verifies the effectiveness of the new method in improving the accuracy of the quantitative calibration model and realizes the reduction of the quantitative calibration error of the pavement state sensor.
- pavement state sensor /
- calibration model /
- data fitting /
- error analysis

HTML全文

图 1 AP流程框图

Fig. 1 Block diagram of AP flow

下载: 全尺寸图片幻灯片

图 2 PSO-ASVR方法流程图

Fig. 2 Flow chart of PSO-ASVR method

下载: 全尺寸图片幻灯片

图 3 传感器结构框图

Fig. 3 Block diagram of sensor structure

下载: 全尺寸图片幻灯片

图 4 传感器和标准样本实物图

Fig. 4 Physical picture of sensor and standard samples

下载: 全尺寸图片幻灯片

图 5 标定数据

Fig. 5 Diagram of calibration data

下载: 全尺寸图片幻灯片

图 6 测试数据

Fig. 6 Diagram of test data

下载: 全尺寸图片幻灯片

图 7 最小二乘法得到的拟合误差$\delta $

Fig. 7 Fitting error $\delta $ obtained by least square method

下载: 全尺寸图片幻灯片

图 8 偏最小二乘法得到的拟合误差$\delta $

Fig. 8 Fitting error δ obtained by partial least square method

下载: 全尺寸图片幻灯片

图 9 粒子群优化自适应支持向量回归得到的拟合误差$\delta $

Fig. 9 Fitting error $\delta $ obtained by PSO-ASVR

下载: 全尺寸图片幻灯片

表 1 针对不同波长的RMSE

Table 1 RMSE for different wavelengths

波长/nm LS PLS PSO-ASVR

940 0.109 7 0.199 8 0.062 4
1 310 1.103 9 0.178 2 0.056 3
1 550 0.034 8 0.083 8 0.059 3

下载: 导出CSV

表 2 针对不同路面状态的RMSE

Table 2 RMSE for different pavement states

路面状态 LS PLS PSO-ASVR

雪 0.658 5 0.190 7 0.058 4
冰 0.890 5 0.194 2 0.080 6
水 0.072 3 0.068 1 0.025 9

下载: 导出CSV

表 3 针对不同方法的RMSE

Table 3 RMSE for different methods

方法 LS PLS PSO-ASVR

RMSE 0.640 8 0.162 0 0.059 4

下载: 导出CSV

参考文献(15)

[1]	汤筠筠, 郭忠印, 李长城, 等. 基于路面摩擦因数的冬季典型路面状态识别模型[J]. 中国公路学报,2014,27(11):25-30. doi: 10.3969/j.issn.1001-7372.2014.11.004 TANG Junjun, GUO Zhongyin, LI Changcheng, et al. Identification model of typical road state in winter based on road friction factor[J]. China Journal of Highway and Transport,2014,27(11):25-30. doi: 10.3969/j.issn.1001-7372.2014.11.004
[2]	SHEN Y C, WANG S. Condensation frosting detection and characterization using a capacitance sensing approach[J]. International Journal of Heat and Mass Transfer,2020,147:118968. doi: 10.1016/j.ijheatmasstransfer.2019.118968
[3]	HABIB T, MOHAMMED A. A novel concrete-based sensor for detection of ice and water on roads and bridges[J]. Sensors,2017,17(12):2912. doi: 10.3390/s17122912
[4]	翟子洋, 畅宏达, 董世浩, 等. 车路协同环境下基于路面湿滑状态识别的车辆安全预警导航系统[J]. 科学技术创新,2021(21):77-78. doi: 10.3969/j.issn.1673-1328.2021.21.033 ZHAI Ziyang, CHANG Hongda, DONG Shihao, et al. Vehicle safety early-warning navigation system based on road slippery state identification in vehicle-road cooperative environment[J]. Science and Technology Innovation,2021(21):77-78. doi: 10.3969/j.issn.1673-1328.2021.21.033
[5]	RUIZ-LLATA M, RODEIGUEZ-CORTINA M, MARTIN-MATEOS P, et al. LiDAR design for road condition measurement ahead of a moving vehicle[J]. IEEE , 2017(13): 1-3.
[6]	RUAN C, WANG Y, MA X, et al. Road meteorological condition sensor based on Multi-wavelength light detection[C]. Xi‘an: 3rd International Conference on Photonics and Optical Engineering, 2019: UNSP110521F.
[7]	LOVEN L, KARSISTO V, JARVINEN H, et al. Mobile road weather sensor calibration by sensor fusion and linear mixed models[J]. Plosone,2019,14(2):e0211702. doi: 10.1371/journal.pone.0211702
[8]	许一飞, 叶林, 许丹丹, 等. 基于多传感器技术的机场地面结冰检测系统[J]. 仪表技术与传感器,2012(9):36-38. doi: 10.3969/j.issn.1002-1841.2012.09.013 XU Yifei, YE Lin, XU Dandan, et al. Airport ground icing detection system based on multi-sensor technology[J]. Instrument Technique and Sensor,2012(9):36-38. doi: 10.3969/j.issn.1002-1841.2012.09.013
[9]	GUI K, YE L, GE J F, et al. Road surface condition detection utilizing resonance frequency and optical technologies[J]. Sensors and Actuators A:Physical,2019,297:111540. doi: 10.1016/j.sna.2019.111540
[10]	YANG S. Hybrid PSO-AMLS-based method for data fitting in the calibration of the infrared radiometer[J]. Infrared and Laser Engineering,2021,50(8):20200471. doi: 10.3788/IRLA20200471
[11]	于连栋, 常雅琪, 赵会宁, 等. 基于支持向量回归机的机器人定位精度提高[J]. 光学精密工程,2020,28(12):2646-2654. doi: 10.37188/OPE.20202812.2646 YU Liandong, CHANG Yaqi, ZHAO Huining, et al. Method for improving positioning accuracy of robot based on support vector regression[J]. Optics and Precision Engineering,2020,28(12):2646-2654. doi: 10.37188/OPE.20202812.2646
[12]	徐英, 谷雨, 彭冬亮, 等. 基于DRGAN和支持向量机的合成孔径雷达图像目标识别[J]. 光学精密工程,2020,28(3):727-735. doi: 10.3788/OPE.20202803.0727 XU Ying, GU Yu, PENG Dongliang, et al. SAR ATR based on disentangled representation learning generative adversarial networks and support vector machine[J]. Optics and Precision Engineering,2020,28(3):727-735. doi: 10.3788/OPE.20202803.0727
[13]	吴羽峰, 吴佳琛, 郝然, 等. 基于深度学习的粒子场数字全息成像研究进展[J]. 应用光学,2020,240(4):662-674. WU Yufeng, WU Jiachen, HAO Ran, et al. Research progress of particle field digital holography based on deep learning[J]. Journal of Applied Optics,2020,240(4):662-674.
[14]	廖宇铖, 伍世虔, 邓高旭, 等. 基于方向图变换的快速不连续相位展开[J]. 应用光学,2021,246,42(4):678-684. LIAO Yucheng, WU Shiqian, DENG Gaoxu, et al. Fast discontinuous phase unwrapping based on orientation diagram transformation[J]. Journal of Applied Optics,2021,246,42(4):678-684.
[15]	乔贵方, 吕仲艳, 张颖, 等. 基于BAS-PSO算法的机器人定位精度提升[J]. 光学精密工程,2021,29(4):763-771. doi: 10.37188/OPE.20212904.0763 QIAO Guifang, LYU Zhongyan, ZHANG Ying, et al. Improvement of robot kinematic accuracy based on BAS-PSO algorithm[J]. Optics and Precision Engineering,2021,29(4):763-771. doi: 10.37188/OPE.20212904.0763