基于多元特征的建筑工程货运车辆行程时间预测-工程学研究-CSCIED科技核心评价数据库-手机版

基于多元特征的建筑工程货运车辆行程时间预测

Travel time prediction of construction freight vehicles based on multiple features

ES评分 0 浏览量：270 下载量：0

DOI	10.12208/j.jer.20250004
刊名	工程学研究 Journal of Engineering Research
年，卷(期)	2025, 4(1)
作者	杜江¹, 江泽浩², 宁朝阳¹, 王宇阳², 赵长龙¹,
作者单位	¹中海建筑有限公司贵州贵阳 ²华中科技大学土木与水利工程学院湖北武汉
摘要	目的建筑工程货运车辆行程时间预测对于项目管理至关重要。其在城市中行驶受到不同因素的影响，通过捕捉影响因素特征提高预测精度已成为当前亟需解决的问题。方法首先，使用图卷积网络（Graph convolution network, GCN）捕捉城市网格中行驶轨迹的空间特征；然后，借助转换器网络（Transformer）捕捉城市网格中行驶轨迹的时间特征；其次，将外部因素作为文本信息，通过嵌入模型提取属性特征；最后，构建基于多元特征的工程货运车辆行程时间预测模型。将武汉市内某一建设项目的2320条行驶轨迹作为实验数据，划分行驶区域为500×500、1000×1000和1500×1500m的网格序列，借助本文模型预测工程运输车辆行程时间，并与基线模型进行对比。结果研究结果表明：三种空间粒度下，本文模型预测结果的均方根误差分别为89.08、111.32和141.6；与基线模型相比，该模型的均方根误差分别平均降低了25.83%、26.43%和27%。结论研究成果为工程运输行业行程时间预测提供了新的思路，可为项目管理提供技术支撑。
Abstract	Objective The travel time prediction of construction freight vehicles is very important for project management. Its driving in the city is affected by different factors. It has become an urgent problem to improve the prediction accuracy by capturing the characteristics of influencing factors. Methods Firstly, the spatial features of travel tracks in the urban grid were captured using the Graph convolution network (GCN). Then, the Transformer network was used to capture the time characteristics of the driving trajectory in the urban grid; Secondly, the external factors were taken as text information, and the attribute features are extracted by embedding the model. Finally, the travel time prediction model of construction freight vehicles based on multiple features was constructed. 2320 driving tracks of a construction project in Wuhan were taken as experimental data and divided into grid sequences with driving areas of 500×500, 1000×1000 and 1500×1500m. The travel time of engineering transport vehicles was predicted by this model and compared with the baseline model. [Findings]The results show that the root-mean-square errors (RMSE) of the model prediction results are 89.08, 111.32 and 141.6, respectively. Compared with the baseline model, the RMSE of this model were reduced by an average of 25.83%, 28.43%, and 27%, respectively. Conclusions The research results provide a new idea for the travel time prediction of engineering transportation industry, and can provide technical support for project management.
关键词	交通运输系统工程；行程时间预测；工程货运车辆；图卷积网络；转换器模型
KeyWord	Transportation system engineering; Travel time prediction; Construction freight vehicle; Graph convolution network; Transformer model
基金项目
页码	25-33

参考文献
相关文献

[1] Moniruzzaman M, Maoh H, Anderson W. Short-term prediction of border crossing time and traffic volume for commercial trucks: A case study for the Ambassador Bridge
[J]. Transportation Research Part C: Emerging Technologies, 2016, 63: 182-194.

[2] Golob T F, Regan A C. Impacts of highway congestion on freight operations: perceptions of trucking industry managers
[J]. Transportation Research Part A: Policy and Practice, 2001, 35(7): 577-599.

[3] Theophilus O, Dulebenets M A, Pasha J, et al. Truck scheduling optimization at a cold-chain cross-docking terminal with product perishability considerations
[J]. Computers & Industrial Engineering, 2021, 156: 107240.

[4] Fathollahi-Fard A M, Ranjbar-Bourani M, Cheikhrouhou N, et al. Novel modifications of social engineering optimizer to solve a truck scheduling problem in a cross-docking system
[J]. Computers & Industrial Engineering, 2019, 137: 106103.

[5] Zhou M, Kong N, Zhao L, et al. Understanding urban delivery drivers’ intention to adopt electric trucks in China
[J]. Transportation Research Part D: Transport and Environment, 2019, 74: 65-81.

[6] Bai R, Xue N, Chen J, et al. A set-covering model for a bidirectional multi-shift full truckload vehicle routing problem
[J]. Transportation Research Part B: Methodological, 2015, 79: 134-148.

[7] 王九胜,戴许海,缪中岩,等.基于多元时空关系的公路交通流量时序预测模型
[J].公路交通科技,2023, 40(10): 175-182.WANG Jiu-sheng, DAI Xu-hai, MIU Zhong-yan, et al. A Model for Time Series Prediction on Highway Traffic Flow Based on Multivariate Spatio-temporal Relationship. Journal of Highway and Transportation Research and Development. 2023, 40(10): 175-182 https://doi.org/10.3969/j.issn.1002-0268.2023.10.020.

[8] Nadi A, Sharma S, Snelder M, et al. Short-term prediction of outbound truck traffic from the exchange of information in logistics hubs: A case study for the port of Rotterdam
[J]. Transportation Research Part C: Emerging Technologies, 2021, 127: 103111.

[9] Borowska-Stefańska M, Kowalski M, Kurzyk P, et al. Assessing the impacts of sunday trading restrictions on urban public transport: an example of a big city in central Poland
[J]. Journal of Public Transportation, 2023, 25: 100049.

[10] Scellato S, Musolesi M, Mascolo C, et al. Nextplace: a spatio-temporal prediction framework for pervasive systems
[C]//Pervasive Computing: 9th International Conference, Pervasive 2011, San Francisco, USA, June 12-15, 2011. Proceedings 9. Springer Berlin Heidelberg, 2011: 152-169.

[11] 胥帅,李博涵,许建秋,等.意图感知的社交网络用户城外移动行为预测
[J/OL].计算机学报:1-16
[2024-10-10].XU Shuai, LI Bo-han, XU Jian-qiu, et al. Intention-Aware Out-of-Town Mobility Prediction for Social Network Users. Chinese Journal of Computers. 2024-10-10: 1-16.

[12] Do T M T, Gatica-Perez D. Contextual conditional models for smartphone-based human mobility prediction
[C]//Proceedings of the 2012 ACM conference on ubiquitous computing. 2012: 163-172.

[13] Du N, Dai H, Trivedi R, et al. Recurrent marked temporal point processes: Embedding event history to vector
[C]//Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 2016: 1555-1564.

[14] Krishna K, Jain D, Mehta S V, et al. An lstm based system for prediction of human activities with durations
[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018, 1(4): 1-31.

[15] Chen C, Wang Y, Li L, et al. The retrieval of intra-day trend and its influence on traffic prediction
[J]. Transportation research part C: emerging technologies, 2012, 22: 103-118.

[16] YU B,LEE Y,SOHN K.Forecasting road traffic speeds by considering area-wide spatio-temporal dependencies based on a graph convolutional neural network (GCN)
[J]. Transportation Research Part C-Emerging Technologies, 2020, 114: 189-204.

[17] MOU L C,LU X Q,LI X L,et al.Nonlocal Graph Convolutional Networks for Hyperspectral Image Classification
[J]. Ieee Transactions on Geoscience and Remote Sensing, 2020, 58(12): 8246-57.

[18] 陈建忠,吕泽凯,蔺皓萌.基于生成对抗和图卷积网络的含缺失值交通流预测模型
[J].公路交通科技,2023, 40(09): 205-214.CHEN Jian-zhong, LV Ze-kai, LIN Hao-meng. A Prediction Model for Traffic Flow with Missing Values Based on Generative Adversarial and Graph Convolutional Networks. Journal of Highway and Transportation Research and Development. 2023, 40(9): 205-214 https://doi.org/10.3969/j.issn.1002-0268.2023.09.024.

[19] Zhou H, Zhang S, Peng J, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting
[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35(12): 11106-11115.

[20] Tang B, Matteson D S. Probabilistic transformer for time series analysis
[J]. Advances in Neural Information Processing Systems, 2021, 34: 23592-23608.

[21] 刘静, 关伟. 交通流预测方法综述. 公路交通科技. 2004, 21(3): 82-85.LIU Jing, GUAN Wei. A Summary of Traffic Flow Forecasting Methods. Journal of Highway and Transportation Research and Development. 2004, 21(3): 82-85.

[22] 王博文,王景升,朱茵,等.基于ARMA-SVR的短时交通流量预测模型研究
[J].公路交通科技,2021,38(11):126-133.WANG Bo-wen, WANG Jing-sheng, ZHU Yin, et al. Study on Short-term Traffic Volume Prediction Model Based on ARMA-SVR. Journal of Highway and Transportation Research and Development. 2021, 38(11): 126-133

[23] Wang X, Huang L, Huang H, et al. An Ensemble Learning Model for Short‐Term Passenger Flow Prediction
[J]. Complexity, 2020, 2020(1): 6694186.

[24] Wu Z, Pan S, Long G, et al. Graph wavenet for deep spatial-temporal graph modeling
[J]. arXiv preprint arXiv: 1906.00121, 2019.

引用本文

杜江, 江泽浩, 宁朝阳, 王宇阳, 赵长龙. 基于多元特征的建筑工程货运车辆行程时间预测 [J]. 工程学研究. 2025; 4; (1). 25 - 33.

文献评论

相关学者

相关机构