Pavement Roughness Prediction Based on Encoder-decoder Structure
CSTR:
Author:
Affiliation:

School of Civil Engineering, Tsinghua University, Beijing 100084, China

Clc Number:

U495

  • Article
  • | |
  • Metrics
  • |
  • Reference [30]
  • |
  • Related [20]
  • |
  • Cited by
  • | |
  • Comments
    Abstract:

    A pavement roughness prediction model based on encoder-decoder structure was proposed, and a comparative analysis of different layers was conducted. Then, the effect of the layer number, the number of hidden units and the time window length on the accuracy of the model was discussed. To train and evaluate the model, an international roughness index (IRI) dataset was constructed based on long-term pavement performance (LTPP) database published by the US Department of Transportation. The results show that the encoder-decoder structure with gated recurrent unit (GRU) layer has the highest accuracy, its performance is better than that of the machine learning model XGBoost and single long short-term memory (LSTM) network. The importance of different input features was evaluated by randomly shuffling features, and the results indicate that the road structure and temperature are important for pavement roughness prediction. Therefore, the road structure and temperature data should be attached great importance during the construction of pavement database.

    Reference
    [1] WANG Linbing, 王含笑, 赵千, 等. 智能路面发展与展望[J]. 中国公路学报, 2019,32(4):50.WANG Linbing, WANG Hanxiao, ZHAO Qian, et al. Development and prospect of intelligent pavement [J]. China Journal of Highway and Transport, 2019,32(4):50.
    [2] 于华洋, 马涛, 王大为, 等. 中国路面工程学术研究综述:2020[J]. 中国公路学报, 2020,33(10):1.YU Huayang, MA Tao, WANG Dawei, et al. Review on China’s pavement engineering research:2020 [J]. China Journal of Highway and Transport, 2020,33(10):1.
    [3] 殷晗宇. 高速公路沥青路面使用性能评价与预测决策研究[D]. 西安:长安大学, 2016.YIN Hanyu. Study on the performance evaluation and forecast decision-making of expressway asphalt pavement [D]. Xi’an: Chang’an University, 2016.
    [4] 孙立军, 刘喜平. 路面使用性能的标准衰变方程[J]. 同济大学学报(自然科学版), 1995(5):512.SUN Lijun, LIU Xiping. General deterioration equation for pavement performance [J]. Journal of Tongji University (Natural Science), 1995(5):512.
    [5] GUO F, GREGORY J, KIRCHAIN R. Incorporating cost uncertainty and path dependence into treatment selection for pavement networks[J]. Transportation Research, Part C: Emerging Technologies, 2020,110:40.
    [6] 周亮, 凌建明, 林小平. 考虑环境因素的沥青路面疲劳开裂预估模型[J]. 中国公路学报, 2013,26(6):47.ZHOU Liang, LING Jianming, LIN Xiaoping. Prediction model for fatigue crack of asphalt pavement with environmental factors considered [J]. China Journal of Highway and Transport, 2013,26(6):47.
    [7] BUTT A A, SHAHIN M Y, FEIGHAN K J, et al. Pavement performance prediction model using the Markov process[J]. Transportation Research Record, 1987(1123):12.
    [8] KARLAFTIS A G, BADR A. Predicting asphalt pavement crack initiation following rehabilitation treatments[J]. Transportation Research, Part C: Emerging Technologies, 2015,55:510.
    [9] GONG H, SUN Y, SHU X, et al. Use of random forests regression for predicting IRI of asphalt pavements[J]. Construction and Building Materials, 2018,189:890.
    [10] ALATOOM Y I, Al-SULEIMAN OBAIDAT T I. Development of pavement roughness models using artificial neural network (ANN)[J]. International Journal of Pavement Engineering, 2022,23(13):4622.
    [11] ZIARI H, MAGHREBI M, AYOUBINEJAD J, et al. Prediction of pavement performance: application of support vector regression with different kernels[J]. Transportation Research Record, 2016, 2589(1):135.
    [12] GUO R, FU D, SOLLAZZO G. An ensemble learning model for asphalt pavement performance prediction based on gradient boosting decision tree[J]. International Journal of Pavement Engineering, 2022,23(10):3633.
    [13] KALOOP M R, El-BADAWY S M, AHN J, et al. A hybrid wavelet-optimally-pruned extreme learning machine model for the estimation of international roughness index of rigid pavements[J]. International Journal of Pavement Engineering, 2022,23(3):862.
    [14] SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. [S.l.]: ACM, 2014:3104-3112.
    [15] MENG F, PEI H. Cyclic shear stress-strain prediction of saturated sand based on the unrolled seq2seq model and scheduled sampling[J]. Soil Dynamics and Earthquake Engineering, 2023, 165: 107665.
    [16] ZHANG Z, LI M, LIN X, et al. Multistep speed prediction on traffic networks: a deep learning approach considering spatio-temporal dependencies[J]. Transportation Research, Part C: Emerging Technologies, 2019, 105: 297.
    [17] 韩皓,谢天. 基于注意力Seq2Seq网络的高速公路交织区车辆变道轨迹预测[J]. 中国公路学报, 2020,33(6):106.HAN Hao, XIE Tian. Lane change trajectory prediction of vehicles in highway interweaving area using Seq2Seq-attention network[J]. China Journal of Highway and Transport, 2020, 33(6): 106.
    [18] GONG H, HUANG B, SHU X. Field performance evaluation of asphalt mixtures containing high percentage of RAP using LTPP data[J]. Construction and Building Materials, 2018,176:118.
    [19] GREFF K, SRIVASTAVA R K, KOUTNIK J, et al. LSTM: a search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017,28(10):2222.
    [20] HOU G, LI L, XU Z, et al. A BIM-based visual warning management system for structural health monitoring integrated with LSTM network[J]. KSCE Journal of Civil Engineering, 2021, 25(8): 2779.
    [21] LUO X, LI D, YANG Y, et al. Spatiotemporal traffic flow prediction with KNN and LSTM[J]. Journal of Advanced Transportation, 2019, 2019:537.
    [22] FRIEDRICH B, LüBBE C, HEIN A. Combining LSTM and CNN for mode of transportation classification from smartphone sensors[C]//Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers. [S.l.]: ACM, 2020: 305-310.
    [23] CHUNG J, GULCEHRE C, CHO K H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J/OL]. [2023-01-01]. arXiv:1412.3555.
    [24] WANG C, SONG L, FAN J. End-to-end structural analysis in civil engineering based on deep learning[J]. Automation in Construction, 2022, 138: 104255.
    [25] CUI J, YU G, ZHOU B, et al. Forecasting freeway on-ramp lane-changing behavior based on GRU[J]. Journal of Transportation Engineering, Part A: Systems, 2021, 147(12): 04021092.
    [26] 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. [S.l.]: ACM, 2017:6000-6100.
    [27] CUI X, WANG Q, DAI J, et al. Intelligent crack detection based on attention mechanism in convolution neural network[J]. Advances in Structural Engineering, 2021, 24(9): 1859.
    [28] CHEN T, FANG J, XU M, et al. Prediction of public bus passenger flow using spatial-temporal hybrid model of deep learning[J]. Journal of Transportation Engineering, Part A: Systems, 2022, 148(4): 04022007.
    [29] KINGMA D P, BA J. Adam: a method for stochastic optimization[J/OL]. [2023-01-01]. arXiv:1412.6980.
    [30] CHEN T, GUESTRIN C. XGBoost: a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. [S.l.]:ACM, 2016: 785-794.
    Cited by
Get Citation

GUO Runhua, YU Xiangqian. Pavement Roughness Prediction Based on Encoder-decoder Structure[J].同济大学学报(自然科学版),2023,51(8):1182~1190

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:May 20,2023
  • Online: August 28,2023
Article QR Code