- ISSN 0258-2724
- CN 51-1277/U
- EI Compendex
- Scopus
- Indexed by Core Journals of China, Chinese S&T Journal Citation Reports
- Chinese S&T Journal Citation Reports
- Chinese Science Citation Database
| Citation: | MENG Chuncheng, QU Daoyuan, DUAN Xiaochen. Nonlinear Prediction and Inversion of Civil Engineering Cost of Urban Rail Transit[J]. Journal of Southwest Jiaotong University. doi: 10.3969/j.issn.0258-2724.20230209
|
The traditional prediction model for the civil engineering cost of urban rail transit lacks decision-making credibility. To address this issue, First, critical factors affecting the civil engineering cost of urban rail transit were retrieved utilizing the feature selection and knowledge judgment methods, and an engineering case database was created. Then, similar cases were screened using the particle swarm optimization (PSO) clustering algorithm, and a nonlinear prediction model of civil engineering cost was established using the extreme learning machine (ELM) based on gray wolf optimizer (GWO), followed by a dual environment comparison experiment. Finally, Sobol’s global sensitivity analysis and curve fitting analysis were conducted to invert the model and validate its superiority by using the Chengdu Rail Transit Line 10 Phase 1 Project as an example. The results show that the prediction model’s mean absolute error and root mean square error are 0.113 9 and 0.127 4, respectively, and the mean absolute percentage error is 4.14%. The prediction effect of the nonlinear cost prediction model is better than that of the linear model, and the better prediction effect is obtained by simultaneously using the factor optimization and case clustering methods. The global sensitivity study reveals that the total sensitivity of the subterranean line length and the number of underground stations is much larger than the other factors, making them the major factors to be adjusted for the scheme optimization. The “black box” effect of intelligent predictive modeling mechanism based on machine learning is better understood by 33.70%–64.52% when curve fitting analysis is used.
| [1] |
张飞涟,梁秀峰. 基于GA-ELM的城市轨道交通工程投资估算方法研究[J]. 铁道科学与工程学报,2019,16(7): 1842-1848.
ZHANG Feilian, LIANG Xiufeng. Research on investment estimation method of urban rail transit project based on GA-ELM[J]. Journal of Railway Science and Engineering, 2019, 16(7): 1842-1848.
|
| [2] |
段晓晨,孟春成,施振东,等. 地铁车站建设投资智能预测与控制方法研究[J]. 铁道工程学报,2021,38(9): 106-111. doi: 10.3969/j.issn.1006-2106.2021.09.018
DUAN Xiaochen, MENG Chuncheng, SHI Zhendong, et al. Research on the intelligent forecast and control method of metro station construction investment[J]. Journal of Railway Engineering Society, 2021, 38(9): 106-111. doi: 10.3969/j.issn.1006-2106.2021.09.018
|
| [3] |
巫玲玲. 城市轨道交通经济指标统计及其影响因素分析[J]. 施工技术,2020,49(增1): 1432-1436.
WU Lingling. Economic index statistics of urban rail transit and its influencing factors[J]. Construction Technology, 2020, 49(S1): 1432-1436.
|
| [4] |
中华人民共和国住房和城乡建设部办公厅. 工程造价改革工作方案[EB/OL]. (2020-07-24) [2023-01-11]. https://www. mohurd. gov. cn/gongkai/fdzdgknr/tzgg/ 202007/20200729_246578. html.
|
| [5] |
段晓晨,陈雨欣,施振东,等. 地铁工程建设投资智能估算方法研究[J]. 铁道工程学报,2021,38(11): 109-114. doi: 10.3969/j.issn.1006-2106.2021.11.018
DUAN Xiaochen, CHEN Yuxin, SHI Zhendong, et al. Research on the intelligent estimation method of metro construction investment[J]. Journal of Railway Engineering Society, 2021, 38(11): 109-114. doi: 10.3969/j.issn.1006-2106.2021.11.018
|
| [6] |
赵欣. 基于BP神经网络的地铁土建工程造价估算方法研究[D]. 北京:北京交通大学,2008.
|
| [7] |
陈进杰. 城市轨道交通项目广义全寿命周期成本理论与应用研究[D]. 北京:北京交通大学,2011.
|
| [8] |
杨文成,王圆圆,孙军先. 基于KR-SVM的城市轨道交通建设成本估算评价模型研究[J]. 交通工程,2017,17(3): 40-46.
YANG Wencheng, WANG Yuanyuan, SUN Junxian. The research on evaluation model of urban rail transit construction cost based on KR-SVM[J]. Journal of Transportation Engineering, 2017, 17(3): 40-46.
|
| [9] |
ELMOUSALAMI H H. Artificial intelligence and parametric construction cost estimate modeling: state-of-the-art review[J]. Journal of Construction Engineering and Management, 2020, 146(1): 03119008.1-03119008.30.
|
| [10] |
陈政,郭春,谌桂舟,等. 基于MEC-BP高海拔隧道供氧浓度与劳动强度规律[J]. 西南交通大学学报,2023,58(3): 622-629.
CHEN Zheng, GUO Chun, CHEN Guizhou, et al. Oxygen supply concentration and labor intensity of high altitude tunnel based on MEC-BP[J]. Journal of Southwest Jiaotong University, 2023, 58(3): 622-629.
|
| [11] |
杨飞,郝晓莉,杨建,等. 基于多车型CNN-GRU性能预测模型的轨道状态评价[J]. 西南交通大学学报,2023,58(2): 322-331.
YANG Fei, HAO Xiaoli, YANG Jian, et al. Track condition evaluation for multi-vehicle performance prediction model based on convolutional neural network and gated recurrent unit[J]. Journal of Southwest Jiaotong University, 2023, 58(2): 322-331.
|
| [12] |
金辉,胡寅逍,葛红娟,等. 基于分段惩罚参数SVM算法的锂电池失效识别[J/OL]. 西南交通大学学报,2023:1-10. (2023-10-31). https://kns.cnki. net/kcms/detail/51.1277.U.20231031.1110.005.html.
JIN Hui, HU Yinxiao, GE Hongjuan, et al. Lithium-ion battery failure identification based on segmented penalty parameter SVM algorithm[J/OL]. Journal of Southwest Jiaotong University, 2023: 1-10. (2023-10-31). https://kns.cnki.net/kcms/detail/51.1277.U. 20231031.1110.005.html.
|
| [13] |
HUANG G B, ZHOU H M, DING X J, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics Part B, Cybernetics: a Publication of the IEEE Systems, Man, and Cybernetics Society, 2012, 42(2): 513-529. doi: 10.1109/TSMCB.2011.2168604
|
| [14] |
KARACA I, GRANSBERG D D, JEONG H D. Improving the accuracy of early cost estimates on transportation infrastructure projects[J]. Journal of Management in Engineering, 2020, 36(5): 04020063.1-04020063.11.
|
| [15] |
SOBOLÁ I M. Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates[J]. Mathematics and Computers in Simulation, 2001, 55(1/2/3): 271-280.
|
| [16] |
赵美玲. 基于SPA—Vague集的地铁TOC反馈快速投资估算方法研究[D]. 南昌:华东交通大学,2017.
|
| [17] |
刘丹. 城市轨道交通工程造价控制分析[J]. 铁道工程学报,2014,31(6): 104-108.
LIU Dan. Analysis of cost control of urban rail transportation construction[J]. Journal of Railway Engineering Society, 2014, 31(6): 104-108.
|
| [18] |
中华人民共和国住房和城乡建设部. 城市轨道交通岩土工程勘察规范:GB 50307—2012[S]. 北京:中国计划出版社,2012.
|
| [19] |
王芳英. 地铁工程综合造价指标解析[J]. 铁路工程造价管理,2012,27(5):33-36.
WANG Fangying. Analysis of subway engineering comprehensive cost index[J]. Railway Engineering Cost Management,2012,27(5):33-36.
|
| [20] |
中华人民共和国住房和城乡建设部. 地铁设计规范:GB 50157—2013[S]. 北京:中国建筑工业出版社,2013.
|
| [21] |
RAFIEI M H, ADELI H. Novel machine-learning model for estimating construction costs considering economic variables and indexes[J]. Journal of Construction Engineering and Management, 2018, 144(12): 04018106.1-04018106.9.
|
| [22] |
ROBNIK-ŠIKONJA M, KONONENKO I. Theoretical and empirical analysis of ReliefF and RReliefF[J]. Machine Learning, 2003, 53(1): 23-69.
|
| [23] |
段晓晨,孟春成,吴曼茜,等. 地铁车站土建工程施工进度三维动态优化控制[J]. 地下空间与工程学报,2022,18(5): 1678-1688.
DUAN Xiaochen, MENG Chuncheng, WU Manxi, et al. 3D dynamic optimal control of civil engineering construction schedule of metro station[J]. Chinese Journal of Underground Space and Engineering, 2022, 18(5): 1678-1688.
|
| [24] |
夏英,刘敏. 基于时空注意力卷积神经网络的交通流量预测[J]. 西南交通大学学报,2023,58(2): 340-347.
XIA Ying, LIU Min. Traffic flow prediction based on spatial-temporal attention convolutional neural network[J]. Journal of Southwest Jiaotong University, 2023, 58(2): 340-347.
|
| [25] |
梅瀚雨,王骑,廖海黎,等. 基于集成式神经网络的扁平箱梁颤振导数预测[J]. 西南交通大学学报,2022,57(4): 894-902.
MEI Hanyu, WANG Qi, LIAO Haili, et al. Flutter derivative prediction of flat box girder based on ensembled neural network[J]. Journal of Southwest Jiaotong University, 2022, 57(4): 894-902.
|
Figures(6) / Tables(3)
DownLoad:
