路面抗滑性能是路面使用性能的重要指标之一,是行车安全性的重要保障.依托RIOHTrack足尺试验环道的检测数据,选用足尺试验环道STR2、STR4、STR9和STR16 4种结构的357组路面抗滑性能检测数据,采用路面温度、累计标准轴载作用次数和路面磨耗次数3个主要影响因素作为自变量,路面摆值(BPN)指标作为因变量,选用300组检测数据作为训练样本,其余57组数据作为验证样本,构建了BPN的显示化和隐式化预测模型.基于温度对沥青路面抗滑性能具备一定影响范围的假定,构建了路面摆值的显示化预测模型,其模型的相关系数(R2)为0.625,模型预测平均相对误差为10.227%.同时,采用不同的隐含层神经元和训练函数,构建了BP神经网络预测模型(隐式化预测模型),模型的BPN预测值和真实值基本吻合,变化趋势一致,平均相对误差为4.484%.研究提高了路面抗滑性能指标预测的有效性和准确性,不同预测模型具备不同的应用前景,为路面抗滑性能的预测分析提供了参考和依据.
The pavement skid resistance performance index is one of the important indexes to ensure driving safety. Based on the test data of RIOHTrack full-scale test track, this paper selects 357 sets of test data of four structures as input variables, including STR2, STR4, STR9 and STR16. The three influence factors of temperature at pavement surface, equivalent single axle load times(ESALs)and pavement abrasion frequency as input variables, while the british pendulum number(BPN)was taken as output variable. The visualized and implicit prediction model of BPN value are constructed by using group data as samples. The 300 groups of data is taken as training samples, while the 57 groups of data is taken as the verifying samples. Based on the assumption that temperature has a certain influence range on the skid resistance performance of asphalt pavement, the visualized prediction model of BPN value is constructed. The correlation coefficient(R2)of this model is 0.625, while the average relative error is 10.227%. At the- DOI:10.3969/j.issn.1000-1565.2024.05.001足尺试验环道路面摆值变化趋势预测吴将丰,王旭东,关伟,肖倩(交通运输部公路科学研究院 基础研究创新中心,北京 100088)摘 要:路面抗滑性能是路面使用性能的重要指标之一,是行车安全性的重要保障.依托RIOHTrack足尺试验环道的检测数据,选用足尺试验环道STR2、STR4、STR9和STR16 4种结构的357组路面抗滑性能检测数据,采用路面温度、累计标准轴载作用次数和路面磨耗次数3个主要影响因素作为自变量,路面摆值(BPN)指标作为因变量,选用300组检测数据作为训练样本,其余57组数据作为验证样本,构建了BPN的显示化和隐式化预测模型.基于温度对沥青路面抗滑性能具备一定影响范围的假定,构建了路面摆值的显示化预测模型,其模型的相关系数(R2)为0.625,模型预测平均相对误差为10.227%.同时,采用不同的隐含层神经元和训练函数,构建了BP神经网络预测模型(隐式化预测模型),模型的BPN预测值和真实值基本吻合,变化趋势一致,平均相对误差为4.484%.研究提高了路面抗滑性能指标预测的有效性和准确性,不同预测模型具备不同的应用前景,为路面抗滑性能的预测分析提供了参考和依据.关键词:路面抗滑性能;BP神经网络;足尺试验环道;预测模型中图分类号:U416.2 文献标志码:A 文章编号:1000-1565(2024)05-0449-10Prediction of pavement BPN value based on RIOHTrack full-scale test trackWU Jiangfeng, WANG Xudong, GUAN Wei, XIAO Qian(Fundamental Research Innovation Center, Research Institute of Highway, Ministry of Transport, Beijing 100088, China)Abstract: The pavement skid resistance performance index is one of the important indexes to ensure driving safety. Based on the test data of RIOHTrack full-scale test track, this paper selects 357 sets of test data of four structures as input variables, including STR2, STR4, STR9 and STR16. The three influence factors of temperature at pavement surface, equivalent single axle load times(ESALs)and pavement abrasion frequency as input variables, while the british pendulum number(BPN)was taken as output variable. The visualized and implicit prediction model of BPN value are constructed by using group data as samples. The 300 groups of data is taken as training samples, while the 57 groups of data is taken as the verifying samples. Based on the assumption that temperature has a certain influence range on the skid resistance performance of asphalt pavement, the visualized prediction model of BPN value is constructed. The correlation coefficient(R2)of this model is 0.625, while the average relative error is 10.227%. At the- 收稿日期:2023-10-20;修回日期:2023-11-21 基金项目:科技基础资源调查专项资助项目(2022FY101400);交通运输部公路科学研究院交通强国试点攻关项目(QG2021-1-1) 第一作者:吴将丰(1988—),男,交通运输部公路科学研究所助理研究员,主要从事沥青路面长期服役性能研究.E-mail:jiangfeng.wu@rioh.cn 通信作者:王旭东(1968—),男,交通运输部公路科学研究所研究员,主要从事长寿命沥青路面结构与材料设计与建造技术的研究.E-mail:xd.wang@rioh.cn 第5期吴将丰等:足尺试验环道路面摆值变化趋势预测河北大学学报(自然科学版) 第44卷same time, different hidden layer neurons and training functions are adopted to construct BP neural network prediction model of BPN value. The predicted BPN value is basically consistent with the test value while the average relative error is 4.484%. Different prediction models have different application prospects. It improves the effectiveness and accuracy of pavement skid resistance performance index prediction, which provides reference for pavement skid resistance performance detection and analysis.
[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. DOI: 10.19721/j.cnki.1001-7372.2019.04.003.
[2] 傅荟璇,赵红.MATLAB神经网络应用设计[M].北京:机械工业出版社, 2010: 88-89.
[3] 张德丰.MATLAB神经网络编程[M].北京:化学工业出版社,2011.
[4] 何铁军,黄卫.模糊神经网络在沥青路面使用性能评价中的应用[J].公路交通科技, 2000, 17(4): 15-18. DOI: 10.3969/j.issn.1002-0268.2000.04.006.
[5] 季天剑,黄晓明,陈荣生.人工神经网络在路面使用性能分析中的应用[J].公路交通科技, 2002,19(4): 19-21. DOI: 10.3969/j.issn.1002-0268.2002.04.006.
[6] 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. DOI: 10.3969/j.issn.1005-0930.2013.05.009.
[7] 马士宾,魏连雨,孙维丰,等.路面使用性能综合预测物元模型及其应用[J].河北工业大学学报,2006,35(4): 44-48. DOI: 10.3969/j.issn.1007-2373.2006.04.010.
[8] 曾胜.径向基函数网络在沥青路面使用性能评价中的应用[J].公路交通科技,2008,25(3): 23-26. DOI: 10.3969/j.issn.1002-0268.2008.03.005.
[9] 宋俊敏,李明,范虎彪,等.基于BP神经网络的路面使用性能评价方法研究[J].公路,2008,53(12): 140-144.
[10] 喻小毛.基于BP神经网络的水泥混凝土路面抗滑性能分析[J].山西建筑,2012,38(17): 176-177. DOI: 10.3969/j.issn.1009-6825.2012.17.099.
[11] 范嫦娥,李德华.基于自组织特征映射神经网络的路面使用性能评价方法[J].重庆交通大学学报(自然科学版),2013,32(1): 80-82. DOI: 10.3969/j.issn.1674-0696.2013.01.18.
[12] 徐兆华.沥青路面抗滑性能神经网络预测模型研究[J].交通标准化,2013(10): 10-12.
[13] 中华人民共和国交通运输部.公路路基路面现场测试规程:JTG E60—2008[S].北京:人民交通出版社,2008.
[14] 王旭东.足尺路面试验环道路面结构与材料设计[J].公路交通科技,2017,34(6):30-37. DOI:10.3969/j.issn.1002-0268.2017.06.005.
[15] MAHMOUD E, MASAD E. Experimental methods for the evaluation of aggregate resistance to polishing abrasion and breakage[J]. Journal of Materials in Civil Engineering,ASCE,2007,19(11):977-985. DOI:10.1061/(ASCE)0899-1561(2007)19:11(977).
[16] 沙振勇,徐暘,关宏信,等.新建沥青混凝土路面抗滑性能预测方法[J].公路,2011,56(10): 251-254.
[17] SHA Z Y, XU Y, GUAN H X, et al. Prediction method for skid resistance of new asphalt concrete pavement[J]. Highway, 2011(10):251-254.
[18] PÉREZ-ACEBO H, GONZALO-ORDEN H, FINDLEY D J,et al. A skid resistance prediction model for an entire road network[J]. Constr Build Mater,2020,262: 120041. DOI: 10.1016/j.conbuildmat.2020.120041.
[19] XIE X G, LU G Y, LIU P F, et al. Influence of temperature on polishing behaviour of asphalt road surfaces[J]. Wear,2018,402/403: 49-56. DOI: 10.1016/j.wear.2018.02.002.
[20] WU J F, WANG X D,WANG L B,et al. Temperature correction and analysis of pavement skid resistance performance based on RIOHTrack full-scale track[J]. Coatings,2020,10(9): 832. DOI: 10.3390/coatings10090832.
[21] 谢小山.基于遗传算法和BP神经网络的铁路客运量预测研究[D].成都:西南交通大学,2010. (
