Please wait a minute...
浙江大学学报(工学版)  2021, Vol. 55 Issue (4): 684-694    DOI: 10.3785/j.issn.1008-973X.2021.04.010
土木工程     
基于宏微观纹理特征融合的路面摩擦性能预测
战友1,2(),李强3,马啸天1,王郴平3,邱延峻1,2
1. 西南交通大学 土木工程学院,四川 成都 610031
2. 道路工程四川省重点实验室,四川 成都 610031
3. 俄克拉荷马州立大学 土木与环境工程学院,俄克拉荷马州 静水 74078
Macro and micro texture based prediction of pavement surface friction
You ZHAN1,2(),Qiang LI3,Xiao-tian MA1,Chen-ping WANG3,Yan-jun QIU1,2
1. School of Civil Engineering, Southwest Jiaotong University, Chengdu 610031, China
2. Highway Engineering Key Laboratory of Sichuan Province, Chengdu 610031, China
3. School of Civil and Environmental Engineering, Oklahoma State University, Stillwater 74078, USA
 全文: PDF(1256 KB)   HTML
摘要:

通过非接触式三维激光表面测试、机器学习,开展基于宏微观纹理特征融合的路面摩擦性能智能预测模型研究. 来自俄克拉荷马州的45个测试站点被选取作现场测试平台. 利用三维激光检测车和GripTester,分别获取行车道轮迹带路面摩擦数据、宏观纹理;利用LS-40三维激光表面分析仪获取集料表面三维微观纹理数据,测算4类微观纹理参数. 利用机器学习算法,将路面摩擦与宏微观纹理特征建立联系. 综合模型训练与测试,评价路面摩擦性能预测模型的准确率. 模型的测试标准差为0.047,测试集R2为0.865. 研究结果表明,86.5%的测试数据适用于所建立的机器学习预测模型,开发的评价指标及预测模型能够较好地预测路面摩擦性能.

关键词: 道路工程路面摩擦路面宏观纹理集料表观特性机器学习    
Abstract:

The pavement skid resistance prediction model was analyzed based on macro and micro texture fusion using non-contact three-dimensional laser detection and machine learning. 45 pavement sites in Oklahoma were identified as the testing beds. Pavement skid resistance and surface macro-texture data were collected in parallel at highway speeds using a grip tester and three-dimensional (3D) laser dection vehicle. Four types of 3D aggregate parameters were calculated to characterize the micro-texture of aggregate surface using LS-40 3D laser imaging scanner. Relationship between pavement surface friction and texture was analyzed using machine learning model. The accuracy of the developed model was verified by model training and testing. The standard deviation of the model was 0.047, and the R squared value of the model was 0.865. 86.5% of the testing data fit the proposed friction model. Results show that the developed texture parameters and proposed friction prediction model can predict the pavement surface friction well.

Key words: road engineering    pavement friction    pavement macro-texture    aggregate surface characteristics    machine learning
收稿日期: 2020-07-16 出版日期: 2021-05-07
CLC:  U 416  
基金资助: 国家自然科学基金资助项目(52008354);中国博士后科学基金资助项目(2019M663557);中央高校基本科研业务费专项资金资助项目(2682020CX65)
作者简介: 战友(1989?),男,助理研究员,博士后,从事道路基础设施智能化检测与评估研究. orcid.org/0000-0002-9874-1100.E-mail: zhanyou@swjtu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
战友
李强
马啸天
王郴平
邱延峻

引用本文:

战友,李强,马啸天,王郴平,邱延峻. 基于宏微观纹理特征融合的路面摩擦性能预测[J]. 浙江大学学报(工学版), 2021, 55(4): 684-694.

You ZHAN,Qiang LI,Xiao-tian MA,Chen-ping WANG,Yan-jun QIU. Macro and micro texture based prediction of pavement surface friction. Journal of ZheJiang University (Engineering Science), 2021, 55(4): 684-694.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2021.04.010        http://www.zjujournals.com/eng/CN/Y2021/V55/I4/684

图 1  路面-轮胎耦合摩擦力的形成机理
图 2  室外数据测试点
站点ID 处治类型 集料种类 AADT A0 /a 站点ID 处治类型 集料种类 AADT A0 /a
1 碎石封层 石灰岩 30 5.7 24 Novachip 花岗岩 5185 3.8
2 碎石封层 石灰岩 550 3.2 25 Novachip 流纹岩 23439 2.3
3 碎石封层 石灰岩 1063 5.2 26 Novachip 流纹岩 2030 1.6
4 碎石封层 石灰岩 1063 5.2 27 Novachip 流纹岩 4412 7.2
5 碎石封层 石灰岩 1063 5.2 28 Novachip 石灰岩 18075 6.7
6 微表处 花岗岩 2776 2.8 29 Novachip 砂岩 9283 5.7
7 微表处 Mine Chat 2322 15.5 30 Novachip 砂岩 3200 3.5
8 微表处 花岗岩 1126 5.3 31 高抗滑 铝土矿 10672 2.1
9 微表处 花岗岩 8234 6.3 32 高抗滑 铝土矿 10672 2.1
10 薄层罩面 白云石 4930 6.9 33 高抗滑 铝土矿 25155 2.1
11 薄层罩面 白云石 2313 2.8 34 高抗滑 Mine Chat 195 2.1
12 薄层罩面 白云石 3200 3.4 35 高抗滑 Mine Chat 195 2.1
13 薄层罩面 白云石 4200 5.4 36 高抗滑 铝土矿 195 3.8
14 薄层罩面 花岗岩 470 4.7 37 高抗滑 铝土矿 195 3.8
15 薄层罩面 流纹岩 1650 4.9 38 高抗滑 铝土矿 195 3.8
16 薄层罩面 流纹岩 16006 4.2 39 高抗滑 铝土矿 195 3.8
17 薄层罩面 流纹岩 1150 3.9 40 温拌 流纹岩 2685 2.5
18 薄层罩面 花岗岩 11037 6.8 41 温拌 流纹岩 2685 2.5
19 薄层罩面 石灰岩 900 6.8 42 温拌 流纹岩 2685 2.5
20 薄层罩面 石灰岩 215 3.4 43 温拌 流纹岩 2685 2.5
21 薄层罩面 石灰岩 1128 5.8 44 温拌 流纹岩 2685 2.5
22 薄层罩面 砂岩 2912 3.8 45 温拌 流纹岩 2685 2.5
23 薄层罩面 砂岩 2800 6.5 ? ? ? ? ?
表 1  测试站点信息
图 3  三维激光检测车
图 4  摩擦系数测试设备
图 5  便携式三维激光表面测试仪
图 6  高抗滑测试站点数据预处理分析
图 7  路面摩擦系数与MPD之间的相关性分析
图 8  集料表面三维纹理参数及获取流程
变量类型 参数类型 参数 参数解释
输出变量 摩擦性能 F 路面摩擦系数
输入变量 路表处治 Treatment 高抗滑表面处理、温拌沥青测试点、碎石封层、
微表处技术、薄层罩面、Novachip超薄磨耗层
输入变量 区域气候 T 温度
输入变量 交通特性 AADT 年平均日交通量
输入变量 交通特性 V 累计交通量(AADT × A
输入变量 路面服役龄期 A 自路表处治实施以来使用年数
输入变量 路表特性 MPD 构造深度
输入变量 路表特性 IRI 路面平整度
输入变量 路表特性 R 车辙深度
输入变量 集料特性 Type 集料类型
输入变量 集料特性 Textural Parameters 纹理参数:Entropy(T)、Energy(E)、Homogeneity(H)、SalStrStd
输入变量 集料特性 Feature Parameters 特征参数:SpdSpcS5pS5vS10zSdaShaSdvShv
输入变量 集料特性 Height Parameters 高度参数:SpSvSzSaSqSskSku
输入变量 集料特性 Material Ratio & Volume Parameters 材料比与体积参数:SmrSmcSxpVvVmVmpVmcVvcVvv
表 2  机器学习预测模型输入参数
图 9  路面摩擦性能机器学习方法的预测流程
图 10  随机森林示意图
图 11  路面摩擦性能RF预测模型测试
模型 R2 模型 R2
文献[23]模型 0.78 文献[42]模型 0.66
文献[24]模型 0.55 本文模型 0.86
表 3  摩擦性能预测模型的比较
参数类型 评价指标 重要性 重要性总和 重要性等级
交通特性 V 0.40 0.40 1
集料表面微观纹理特性 Str 0.17 0.32 2
集料表面微观纹理特性 H 0.15 0.32 2
路表特性 IRI 0.07 0.12 3
路表特性 MPD 0.03 0.12 3
路表特性 R 0.02 0.12 3
温度 T 0.10 0.10 4
路面服役龄期 A 0.06 0.06 5
表 4  路面摩擦性能RF预测模型
1 黄晓明, 郑彬双 沥青路面抗滑性能研究现状与展望[J]. 中国公路学报, 2019, 32 (4): 32- 49
HUANG Xiao-ming, ZHENG Bin-shuang Research status and progress for skid resistance of asphalt pavements[J]. China Journal of Highway and Transport, 2019, 32 (4): 32- 49
2 MATAEI B, ZAKERI H, ZAHEDI M, et al Pavement friction and skid resistance measurement methods: a literature review[J]. Open Journal of Civil Engineering, 2016, 6 (4): 537- 565
doi: 10.4236/ojce.2016.64046
3 HENRY J J. Evaluation of pavement friction characteristics: a synthesis of highway practice [R]. Washington D. C.: Transportation Research Board, National Research Council, 2000.
4 BIJSTERVELD W V, VAL M A Towards quantification of seasonal variations in skid resistance measurements[J]. Road Materials and Pavement Design, 2015, 17 (2): 477- 486
5 HALL J W. NCHRP web document 108: guide for pavement friction [R]. Washington D. C.: Transportation Research Board, National Research Council, 2009.
6 李菁若, 吴卓科, 陈小莉, 等 沥青混合料抗滑性能评价指标与抗滑寿命预估方法研究[J]. 重庆交通大学学报: 自然科学版, 2019, 38 (12): 69- 75
LI Jing-ruo, WU Zhuo-ke, CHEN Xiao-li, et al Evaluation indexes for anti-sliding performance and evaluation method of anti-sliding life of asphalt pavement[J]. Journal of Chongqing Jiaotong University: Natural Science, 2019, 38 (12): 69- 75
doi: 10.3969/j.issn.1674-0696.2019.12.10
7 MEEGODA J N, GAO S Evaluation of pavement skid resistance using high speed texture measurement[J]. Journal of Traffic and Transportation Engineering: English Edition, 2015, 2 (6): 382- 390
doi: 10.1016/j.jtte.2015.09.001
8 IZEPPI E, FLINTSCH G, MCGHEE K. Field performance of high friction surfaces [R]. North America: Virginia Center for Transportation Innovation and Research, 2010.
9 KARGAH-OSTADI N, HOWARD A Monitoring pavement surface macro-texture and friction[J]. Transportation Research Record Journal of the Transportation Research Board, 2014, 2525: 111- 117
10 LI S, ZHU K, NOURELDIN S Evaluation of friction performance of coarse aggregates and hot-mix asphalt pavements[J]. Journal of Testing and Evaluation, 2007, 35 (6): 1- 7
11 刘清泉 路用石料的摩擦特性分析[J]. 中国公路学报, 2004, 17 (3): 16- 19
LIU Qing-quan Analysis of tribological property of pavement stone[J]. China Journal of Highway and Transport, 2004, 17 (3): 16- 19
doi: 10.3321/j.issn:1001-7372.2004.03.004
12 陈先华, 陈胜霞, 黄晓明, 等 沥青路面的磨光研究: 从宏观到微观尺度[J]. 中外公路, 2013, 33 (2): 45- 50
CHEN Xian-hua, CHEN Sheng-xia, HUANG Xiao-ming, et al Research on asphalt pavement polishing: from macro to micro scale[J]. Journal of China and Foreign Highway, 2013, 33 (2): 45- 50
doi: 10.3969/j.issn.1671-2579.2013.02.012
13 PRADHAN M. Evaluate the use of FPGA Soc for real time data acquisition and aggregate micro-texture measurement using laser sensors [D]. Arlington TX: University of Texas at Arlington, 2016.
14 MAERZ N H. Aggregate sizing and shape determination using digital image processing [C] // Center for Aggregates Research 6th Annual Symposium. St. Louis: [s.n.], 1998: 195-203.
15 FLORKOVá Z, JAMBOR M Quantification of aggregate surface texture based on three dimensional microscope measurement[J]. Procedia Engineering, 2017, 192: 195- 200
doi: 10.1016/j.proeng.2017.06.034
16 苗英豪, 曹东伟, 刘清泉 沥青路面表面宏观构造与抗滑性能间的关系[J]. 北京工业大学学报, 2011, 37 (4): 547- 553
MIAO Ying-hao, CAO Dong-wei, LIU Qing-quan Relationship between surface macrotexture and skid resistance of asphalt pavement[J]. Journal of Beijing University of Technology, 2011, 37 (4): 547- 553
17 王维锋, 严新平, 肖旺新, 等 路面纹理的多重分形特征描述与识别方法[J]. 交通运输工程学报, 2013, 13 (3): 15- 21
WANG Wei-feng, YAN Xin-ping, XIAO Wang-xin, et al Approach of multifractal feature description and recognition for pavement texture[J]. Journal of Traffic and Transportation Engineering, 2013, 13 (3): 15- 21
doi: 10.3969/j.issn.1671-1637.2013.03.003
18 钱振东, 薛永超, 张令刚 沥青路面三维纹理分形维数及其抗滑性能[J]. 中南大学学报: 自然科学版, 2016, 47 (10): 3590- 3596
QIAN Zhen-dong, XUE Yong-chao, ZHANG Ling-gang 3-D textural fractal dimension and skid resistance of asphalt pavement[J]. Journal of Central South University: Science and Technology, 2016, 47 (10): 3590- 3596
19 冉茂平, 周兴林, 肖神清 路表纹理包络轮廓计算及其对抗滑性能的影响[J]. 长安大学学报: 自然科学版, 2019, 39 (5): 11- 19
RAN Mao-ping, ZHOU Xing-lin, XIAO Shen-qing Pavement enveloped texture profile calculation and its impact on skid resistance[J]. Journal of Chang’an University: Natural Science Edition, 2019, 39 (5): 11- 19
doi: 10.3969/j.issn.1673-2049.2019.05.002
20 ZHAN Y, LI Q, YANG G, et al. Performance monitoring of pavement surface characteristics with 3D surface data [C] // Airfield and Highway Pavements. Philadelphia: ASCE, 2017.
21 WANG K C, LI Q, YANG G, et al Network level pavement evaluation with 1 mm 3D survey system[J]. Journal of Traffic and Transportation Engineering: English Edition, 2015, 2 (6): 391- 398
doi: 10.1016/j.jtte.2015.10.005
22 汪海年, 李磊, 尤占平 基于细观结构特征的沥青混合料空隙三维分布特征研究[J]. 武汉理工大学学报, 2012, 34 (8): 61- 67
WANG Hai-nian, LI Lei, YOU Zhan-ping Characterization on the 3D air void spatial distribution based on the microtexture of asphalt mixture[J]. Journal of Wuhan University of Technology, 2012, 34 (8): 61- 67
doi: 10.3963/j.issn.1671-4431.2012.08.013
23 LI Q, ZHAN Y, YANG G, et al Pavement skid resistance as a function of pavement surface and aggregate texture properties[J]. International Journal of Pavement Engineering, 2018, (2): 1- 11
24 LI Q, YANG G, WANG K, et al Novel macro- and microtexture indicators for pavement friction by using high-resolution three-dimensional surface data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2017, 2641: 164- 176
doi: 10.3141/2641-19
25 YANG, LI Q, ZHAN Y, et al Wavelet based macro-texture analysis for pavement friction prediction[J]. KSCE Journal of Civil Engineering, 2017, 22 (1): 117- 124
26 KANAFI M M, KUOSMANEN A, PELLINEN T K, et al Macro- and micro-texture evolution of road pavements and correlation with friction[J]. International Journal of Pavement Engineering, 2014, 16 (2): 168- 179
27 UECKERMANN A, WANG D, OESER M, et al Calculation of skid resistance from texture measurements[J]. Journal of Traffic and Transportation Engineering, 2015, 2 (1): 3- 16
28 刘亚敏, 韩森, 徐鸥明 基于遗传算法的SMA路面抗滑性能预测模型[J]. 应用基础与工程科学学报, 2013, 21 (5): 890- 898
LIU Ya-min, HAN Sen, XU Ou-ming Prediction model of surface skid resistance of SMA pavement based on genetic algorithm[J]. Journal of Basic Science and Engineering, 2013, 21 (5): 890- 898
doi: 10.3969/j.issn.1005-0930.2013.05.009
29 KRIZHEVSKY A, SUTSKEVER I, HINTON G E Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60 (6): 84- 90
doi: 10.1145/3065386
30 RUSSAKOVSKY O, DENG J, SU H, et al Imagenet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115 (3): 211- 252
doi: 10.1007/s11263-015-0816-y
31 SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S. l.]: IEEE, 2015: 1-9.
32 MOAVENI M, MAHMOUD E, ORTIZ E M, et al Use of advanced aggregate imaging systems to evaluate aggregate resistance to breakage, abrasion, and polishing[J]. Transportation Research Record: Journal of the Transportation Research Board, 2014, 2401 (1): 1- 10
doi: 10.3141/2401-01
33 DUNFORD A, PARRY A, SHIPWAY P, et al Three-dimensional characterization of surface texture for road stones undergoing simulated traffic wear[J]. Wear, 2012, 292-293: 188- 196
doi: 10.1016/j.wear.2012.05.010
34 BESSA I S, BRANCO V T, SOARES J B Evaluation of polishing and degradation resistance of natural aggregates and steel slag using the aggregate image measurement system[J]. Road Materials and Pavement Design, 2014, 15 (2): 385- 405
doi: 10.1080/14680629.2014.883323
35 HENRY J J. NCHRP synthesis of highway practice 291: evaluation of pavement friction characteristics [R]. Washington D. C.: Transportation Research Board, National Research Council, 2000.
36 MASAD E. Relationship of aggregate texture to asphalt pavement skid resistance using image analysis of aggregate shape [R]. Washington D. C.: Transportation Research Board of the National Academies, 2007.
37 REZAEI A, MASAD E, CHOWDHURY A, et al Predicting asphalt mixture skid resistance by aggregate characteristics and gradation[J]. Transportation Research Record: Journal of the Transportation Research Board, 2009, 2104: 24- 33
doi: 10.3141/2104-03
38 ARTYUSHKOVA K, CORNEJO A, SANTORO C, et al Relationship between surface chemistry, biofilm structure, and electron transfer in Shewanella Anodes[J]. American Vacuum Society, 2015, 10 (1): 57- 64
39 OLANIYI E O, ADEKUNLE A, ODEKUOYE T, et al Automatic system for grading banana using GLCM texture feature extraction and neural network arbitrations[J]. Journal of Food Process Engineering, 2017, 40 (6): e12575.1- e12575.10
40 BEYENAL H, DONOVAN C, LEWANDOWSKI Z, et al Three-dimensional biofilm structure quantification[J]. Journal of Microbiological Methods, 2004, 59 (3): 395- 413
doi: 10.1016/j.mimet.2004.08.003
41 ISO/TS CD 25178-2. Geometrical product specification (GPS)-surface texture: areal-Part 2. terms, definitions and surface texture parameters [S]. Geneva: ISO, 2012.
42 YANG G, YU W, LI Q, et al Random forest-based pavement surface friction prediction using high- resolution 3D image data[J]. Journal of Testing and Evaluation, 2019, 49 (2): 20180937
43 王奕森, 夏树涛 集成学习之随机森林算法综述[J]. 信息通信技术, 2018, 12 (1): 49- 55
WANG Yi-sen, XIA Shu-tao A survey of random forests algorithms[J]. Journal of Information and Communication Technology, 2018, 12 (1): 49- 55
doi: 10.3969/j.issn.1674-1285.2018.01.009
[1] 于勇,薛静远,戴晟,鲍强伟,赵罡. 机加零件质量预测与工艺参数优化方法[J]. 浙江大学学报(工学版), 2021, 55(3): 441-447.
[2] 张勤玲,黄志义. 高温高湿盐环境下SBS改性沥青胶浆的高温性能[J]. 浙江大学学报(工学版), 2021, 55(1): 38-45.
[3] 陈巧红,陈翊,李文书,贾宇波. 多尺度SE-Xception服装图像分类[J]. 浙江大学学报(工学版), 2020, 54(9): 1727-1735.
[4] 王慧芳,张晨宇. 采用极限梯度提升算法的电力系统电压稳定裕度预测[J]. 浙江大学学报(工学版), 2020, 54(3): 606-613.
[5] 谢乐,衡熙丹,刘洋,蒋启龙,刘东. 基于线性判别分析和分步机器学习的变压器故障诊断[J]. 浙江大学学报(工学版), 2020, 54(11): 2266-2272.
[6] 万志远,陶嘉恒,梁家坤,才振功,苌程,乔林,周巧妮. Stack Overflow上机器学习相关问题的大规模实证研究[J]. 浙江大学学报(工学版), 2019, 53(5): 819-828.
[7] 柯懂湘,潘丽敏,罗森林,张寒青. 基于随机森林算法的Android恶意行为识别与分类方法[J]. 浙江大学学报(工学版), 2019, 53(10): 2013-2023.
[8] 忽丽莎, 王素贞, 陈益强, 高晨龙, 胡春雨, 蒋鑫龙, 陈振宇, 高兴宇. 基于可穿戴设备的跌倒检测算法综述[J]. 浙江大学学报(工学版), 2018, 52(9): 1717-1728.
[9] 王洪凯, 陈中华, 周纵苇, 李迎辞, 陆佩欧, 王文志, 刘宛予, 于丽娟. 机器学习算法诊断PET/CT纵膈淋巴结性能评估[J]. 浙江大学学报(工学版), 2018, 52(4): 788-797.
[10] 万晨光, 申爱琴, 郭寅川. 桥面铺装调平层与沥青面层层间剪切行为[J]. 浙江大学学报(工学版), 2017, 51(7): 1355-1360.
[11] 陈德, 韩森, 苏谦, 韩霄. 基于抗滑降噪性能的沥青路面表面构造评价指标[J]. 浙江大学学报(工学版), 2017, 51(5): 896-903.
[12] 黄志义, 胡晓宇, 王金昌, 章俊屾. 高黏沥青中高温感温性评价方法的适用性[J]. 浙江大学学报(工学版), 2015, 49(8): 1448-1454.
[13] 吴鹏洲,于慧敏,曾雄. 基于正则化风险最小化的目标计数[J]. 浙江大学学报(工学版), 2014, 48(7): 1226-1233.
[14] 王新飞, 黄志义, 刘卓, 朱兴一, 徐伟. Delaunay三角网格的沥青混合料粗集料分布特性[J]. J4, 2012, 46(2): 263-268.
[15] 宓云軿 王晓萍 金鑫. 基于机器学习的水质COD预测方法[J]. J4, 2008, 42(5): 790-793.