Abstract
The friction performance of road surfaces is an important indicator of highway safety，which is closely related to road texture.In this paper，a set of three-dimensional denoising methods for road texture data with different noise levels was proposed，which could effectively remove noise while preserving local texture features.In addition，a skid resistance prediction model named Friction- 1D Transformer was developed based on the design concept of Vision Transformer （VIT） for skid resistance evaluation of asphalt pavements.Unlike traditional convolutional neural networks，the Friction- 1D Transformer utilized positional encoding structures and multi-head attention mechanisms to extract global features from one-dimensional （1D） texture signals along the direction of vehicle movement，thus accurately predicting the friction performance of road surfaces.Comparative analysis with four other models，namely random forest （RF），k-nearest neighbor （k-NN），residual neural network （Resnet），and VIT，shows that Friction- 1D Transformer has higher accuracy and faster training speed，with only 3 915 914 parameters.This research validates the feasibility of using raw texture data for training and skid resistance prediction，and the proposed model structure may facilitate the development of the testing technology for skid resistance of road surfaces.
Publication Date
12-17-2024
DOI
10.14048/j.issn.1671-2579.2024.06.005
First Page
51
Last Page
58
Submission Date
February 2025
Recommended Citation
Feifei, PEI; Zilong, NIE; G uomin, XU; You, ZHAN; Xianqi, GONG; Changfa, AI; Yuan, DENG; Zhengyun, JI; and Shifa, WANG
(2024)
"Friction‑ 1D Transformer ： A 1D Vision Transformer Hybrid Model for Skid Resistance Prediction on Asphalt Pavements,"
Journal of China & Foreign Highway: Vol. 44:
Iss.
6, Article 5.
DOI: 10.14048/j.issn.1671-2579.2024.06.005
Available at:
https://zwgl1980.csust.edu.cn/journal/vol44/iss6/5
Reference
[1]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.
[2]陈占权 .沥青路面表面纹理的检测方法及其精准度分析[J].中外公路 ，2023 ,43(6)：74-78.CHEN Zhanquan .Detection method and accuracy analysis of asphalt pavement surface texture [J].Journal of China & Foreign Highway ,2023，43(6):74-78.
[3]江照伟，韦金城，刘航，等.基于撒布磨耗料的 SMA沥青路面早期抗滑性能改善研究 [J].中外公路 ，2023 ,43(3)：56-60.JIANG Zhaowei ，WEI Jincheng ，LIU Hang ，et al.Study on improvement of early skid resistance of SMA asphalt pavement based on spreading grit [J].Journal of China & Foreign Highway ,2023，43(3):56-60.
[4]LI S ,ZHU K R ,NOURELDIN S ,et al .Identifying friction variations with the standard smooth tire for network pavement inventory friction testing [J].Transportation Research Record : Journal of the Transportation Research Board ,2005 ,1905 (1): 157-165.
[5]任瑞波，尹利洋，徐强，等.RAP掺量对温再生沥青混合料力学性能和路用性能的影响规律研究 [J].中外公路 ，2024 ,44(1)：66-75.REN Ruibo ,YIN Liyang ,XU Qiang ,et al.Influence of RAP content on mechanical properties and pavement performance of warm recycled asphalt mixture [J].Journal of China & Foreign Highway ,2024，44(1):66-75.
[6]陈德 ,韩森 ,苏谦 ,等.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.CHEN De ,HAN Sen ,SU Qian ,et al.Evaluation indicator of surface texture of asphalt pavement based onskid-resistance and noise reduction performance [J].Journal of Zhejiang University (Engineering Science ),2017 ,51(5): 896-903.
[7]隋正 .路面摩擦系数测量仪测量系统的设计 [D].西安 : 长安大学 ,2014 .SUI Zheng .The design of measurement system for pavement friction coefficient measuring instrument [D].Xi’an: Chang’an University ,2014 .
[8]ZUNIGA GARCIA N .Predicting friction with improved texture characterization [D].Austin，TX，USA : The University of Texas at Austin ,2017 .
[9]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 Xiaoming ,ZHENG Binshuang .Research status and progress for skid resistance performance of asphalt pavements [J].China Journal of Highway and Transport ,2019 ,32(4): 32-49.
[10]KOUCHAKI S ,ROSHANI H ,PROZZI J A ,et al .Field investigation of relationship between pavement surface texture and friction [J].Transportation Research Record : Journal of the Transportation Research Board ,2018 ,2672(40):395-407.
[11]YANG G W ,LI Q J ,ZHAN Y ,et al .Convolutional neural network-based friction model using pavement texture data[J].Journal of Computing in Civil Engineering ,2018 ,32(6): 04018052 .
[12]LIU C ,ZHAN Y ,DENG Q S ,et al.An improved differential box counting method to measure fractal dimensions for pavement surface skid resistance evaluation [J].Measurement ,2021 ,178:109376 .
[13]DENG Q S ,ZHAN Y ,LIU C ,et al .Multiscale power spectrum analysis of 3D surface texture for prediction of asphalt pavement friction [J].Construction and Building Materials ,2021 ,293: 123506 .
[14]NAJAFI S ,FLINTSCH G W ,KHALEGHIAN S .Pavement friction management-artificial neural network approach [J].International Journal of Pavement Engineering ,2019 ,20(2): 125-135.
[15]PANAHANDEH G ,EK E ,MOHAMMADIHA N .Road friction estimation for connected vehicles using supervised machine learning [C]//2017 IEEE Intelligent Vehicles Symposium (Ⅳ).Los Angeles ,CA,USA .IEEE ,2017 : 1262 -1267 .
[16]ZHAN Y ,LIU C ,DENG Q S ,et al .Integrated FFT and XGBoost framework to predict pavement skid resistance using automatic 3D texture measurement [J].Measurement ,2022 ,188: 110638 .
[17]LECUN Y ,BENGIO Y ,HINTON G .Deep learning [J].Nature ,2015 ,521: 436-444.
[18]ZHAN Y ,LI J Q ,LIU C ,et al.Effect of aggregate properties on asphalt pavement friction based on random forest analysis [J].Construction and Building Materials ,2021 ,292: 123467 .
[19]SZEGEDY C ,LIU W ,JIA Y Q ,et al .Going deeper with convolutions [C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR ).Boston ,MA,USA .IEEE ,2015 : 1-9.
[20]VASWANI A ,SHAZEER N ,PARMAR N ,et al.Attention is all you need [C]//Proceedings of the 31st International Conference on Neural Information Processing Systems .December 4-9,2017 ,Long Beach ,California ,USA .ACM ,2017 : 6000 -6010 .
[21]DOSOVITSKIY A ,BEYER L ,KOLESNIKOV A ,et al .An image is worth 16x16 words :Transformers for image recognition at scale [EB/OL ].2020 :arXiv :2010 .11929 .http://arxiv .org/abs/ 2010 .11929 .pdf
[22]BROWN T B ,MANN B ,RYDER N ,et al .Language models are few-shot learners [J].Advances in neural information processing systems ,2020 ,33: 1877 -1901 .
[23]LEPIKHIN D ,LEE H ,XU Y Z ,et al .GShard :Scaling giant models with conditional computation and automatic sharding [EB/OL ].2020 :arXiv :2006 .16668 .http://arxiv .org/abs/2006 .16668 .pdf
[24]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.
[25]LI Y X ,SHEN L L .A deep residual inception network for HEp- 2 cell classification [C]//International Workshop on Deep Learning in Medical Image Analysis ,International Workshop on Multimodal Learning for Clinical Decision Support .Cham : Springer ,2017 :12-20.