Research on Construction Alignment Prediction of Continuous Rigid‑frame Bridges Based on Machine Learning

ZUO Hongpeng; WANG Bing; CHEN Peng; ZHANG Hongyan; WANG Li

doi:10.13409/j.cnki.jdpme.20250430099

您当前的位置：

首页 >

文章列表页 >

Research on Construction Alignment Prediction of Continuous Rigid‑frame Bridges Based on Machine Learning

更新时间：2026-01-07

- Research on Construction Alignment Prediction of Continuous Rigid‑frame Bridges Based on Machine Learning
- Journal of Disaster Prevention and Mitigation Engineering Vol. 45, Issue 6, Pages: 1411-1420(2025)
- 作者机构：
  
  1.山西交院试验检测有限公司，山西太原 030032
  2.兰州交通大学土木工程学院，甘肃兰州 730070
- 作者简介：
- 基金信息：
- DOI：10.13409/j.cnki.jdpme.20250430099
  CLC： TU443
- Received：30 April 2025，
  
  Revised：2025-06-17，
  
  Published：28 December 2025
- 稿件说明：
移动端阅览
左鸿鹏,王冰,陈朋等.基于机器学习的连续刚构桥施工线形预测研究[J].防灾减灾工程学报,2025,45(06):1411-1420.

ZUO Hongpeng,WANG Bing,CHEN Peng,et al.Research on Construction Alignment Prediction of Continuous Rigid‑frame Bridges Based on Machine Learning[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(06):1411-1420.
左鸿鹏,王冰,陈朋等.基于机器学习的连续刚构桥施工线形预测研究[J].防灾减灾工程学报,2025,45(06):1411-1420. DOI： 10.13409/j.cnki.jdpme.20250430099.

ZUO Hongpeng,WANG Bing,CHEN Peng,et al.Research on Construction Alignment Prediction of Continuous Rigid‑frame Bridges Based on Machine Learning[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(06):1411-1420. DOI： 10.13409/j.cnki.jdpme.20250430099.

摘要

针对连续刚构桥施工过程中因复杂环境因素引起的材料参数时变性问题，传统有限元分析方法受限于单一设计参数假设，难以准确模拟施工过程中影响参数的实际变化状态，从而导致桥梁施工期线形控制精度不足等关键技术难题。为此提出一种基于机器学习的连续刚构桥施工线形智能预测方法。首先通过参数化有限元建模，系统模拟多因素耦合作用下的施工挠度响应，构建完备的挠度预测样本数据库。分别基于支持向量机（SVM）、随机森林（RF）、长短期记忆网络（LSTM）以及粒子群优化反向传播神经网络（PSO‑BP）建立4种连续刚构桥施工线形机器学习预测模型，并对其预测精度进行对比分析。研究结果表明：RF和ELM模型的预测精度相对较低；LSTM模型预测精度较好，预测最大误差为1.2 mm；PSO‑BP模型则展现出最优的预测性能，其训练集和测试集的拟合优度分别达0.996和0.992，预测挠度绝对误差仅0.55 mm，相对误差均小于10%；采用PSO‑BP神经网络算法可实现连续刚构桥施工挠度的精准预测，有效提升该类桥施工线形控制水平，提高合龙精度，该研究成果可为桥梁工程智能化施工提供必要参考。

Abstract

Given the time-varying characteristics of material parameters caused by complex environmental factors during the construction of continuous rigid-frame bridges

the traditional finite element analysis method is limited by the assumption of a single design parameter

and it is difficult to accurately simulate the actual changing state of the influencing parameters during the construction process

which leads to key technical problems such as insufficient alignment control accuracy during bridge construction. Therefore

this study proposed an intelligent prediction method for construction alignment of continuous rigid-frame bridges based on machine learning. First

parametric finite element modeling was used to simulate the construction deflection response under the coupling of multiple factors

and a complete deflection prediction sample database was constructed. On this basis

four construction-alignment prediction models based on support vector machine (SVM)

random forest (RF)

long short-term memory network (LSTM)

and particle swarm optimization backpropagation neural network (PSO-BP) were established

and their prediction accuracy was compared and analyzed. The results showed that the prediction accuracy of RF and ELM models was relatively low. The LSTM model exhibited better prediction accuracy

with a maximum prediction error of 1.2 mm. The PSO-BP model showed the best prediction performance. Its R² values for the training set and the test set were 0.996 and 0.992

respectively. The absolute error of the predicted deflection was only 0.55 mm

and the relative error was less than 10%. The PSO-BP neural network enables accurate prediction of construction deflection

effectively improves the alignment control level of continuous rigid-frame bridge construction

and enhances the closure alignment accuracy of the bridge. The findings provide an important technical reference for the intelligent construction of bridge engineering.

关键词

Keywords

references

王衍英，冉文兴，吴奇峰 . 公路大跨度连续梁悬臂浇筑与现浇设计方案比较分析［J］. 公路， 2023 ， 68 （ 8 ）： 137 - 141 .

Wang Y Y ， Ran W X ， Wu Q F . Comparative analysis of cantilever casting and cast-in-place design schemes for long-span continuous beams on highways ［J］. Highway ， 2023 ， 68 （ 8 ）： 137 - 141 . （in Chinese）

Liu Y ， Zheng C M ， Ba H Q ， et al . Analysis on the influence factors of construction linear control of continuous rigid structure bridge ［J］. E3S Web of Conferences ， 2021 ， 237 ： 03020 .

Zheng X L ， Guan D . Study on construction monitoring and control of multi-span prestressed concrete continuous beam bridge ［J］. Stavební Obzor - Civil Engineering Journal ， 2024 ， 33 （ 1 ）： 65 - 77 .

Dehua L ， Xu D ， Kaiyue G ， et al . Research of construction monitoring technology of large-span variable cross-section prestressed concrete continuous box-girder bridge ［J］. Academic Journal of Architecture and Geotechnical Engineering ， 2022 ， 4 （ 3 ）： 31 - 36 .

胡斌，李庆择 . 灰色预测在大跨径刚构桥施工线形监控中的应用［J］. 铁道建筑， 2020 ， 60 （ 5 ）： 38 - 42 .

Hu B ， Li Q Z . Application of gray prediction method in construction controlling of long span rigid frame bridge ［J］. Railway Engineering ， 2020 ， 60 （ 5 ）： 38 - 42 . （in Chinese）

Wan L J ， Qiao J Q ， Sun Q S ， et al . Construction control of rigid frame-continuous girder bridge based on grey theory ［J］. Journal of Engineering and Applied Science ， 2024 ， 71 （ 1 ）： 171 .

宋晓东，颜永逸，李佳靖，等 . 基于子结构的大型桥梁有限元模型修正方法［J］. 桥梁建设， 2021 ， 51 （ 2 ）： 40 - 46 .

Song X D ， Yan Y Y ， Li J J ， et al . Substructure-based finite element model updating of long-span bridge ［J］. Bridge Construction ， 2021 ， 51 （ 2 ）： 40 - 46 . （in Chinese）

张建龙，赵东月，栗怡文，等 . 基于神经网络的桥梁健康监测与预警平台研究［J］. 计算机技术与发展， 2022 ， 32 （ 4 ）： 205 - 209 .

Zhang J L ， Zhao D Y ， Li Y W ， et al . Research on bridge health monitoring and alarming platform based on neural network ［J］. Computer Technology and Development ， 2022 ， 32 （ 4 ）： 205 - 209 . （in Chinese）

单德山，石磊，谭康熹 . 联合卷积神经网络与长短期记忆深度网络的桥梁损伤识别［J］. 桥梁建设， 2023 ， 53 （ 4 ）： 41 - 46 .

Shan D S ， Shi L ， Tan K X . Bridge damage identification based on joint CNN and LSTM deep network ［J］. Bridge Construction ， 2023 ， 53 （ 4 ）： 41 - 46 . （in Chinese）

石林泽，程斌，董华能，等 . 基于卷积神经网络的钢桥面板疲劳裂纹识别方法研究［J］. 桥梁建设， 2023 ， 53 （ 4 ）： 62 - 69 .

Shi L Z ， Cheng B ， Dong H N ， et al . Research on fatigue crack identification for steel bridge deck plates based on convolutional neural network ［J］. Bridge Construction ， 2023 ， 53 （ 4 ）： 62 - 69 . （in Chinese）

黄彩萍，谢鑫，周永康，等 . 基于改进掩码-区域卷积神经网络的混凝土病害实例分割［J］. 桥梁建设， 2023 ， 53 （ 6 ）： 63 - 70 .

Huang C P ， Xie X ， Zhou Y K ， et al . Instance segmentation of concrete defects based on improved mask-RCNN ［J］. Bridge Construction ， 2023 ， 53 （ 6 ）： 63 - 70 . （in Chinese）

冯琼，谢晓扬，王鹏辉，等 . 基于鲸鱼优化算法-反向传播神经网络的钢筋混凝土耐久性预测［J］. 吉林大学学报（工学版）， 2025 ， 55 （ 7 ）： 2276 - 2285 .

Feng Q ， Xie X Y ， Wang P H ， et al . Prediction of reinforced concrete durability based on whale optimization algorithm-back propagation neural network ［J］. Journal of Jilin University （Engineering and Technology Edition）， 2025 ， 55 （ 7 ）： 2276 - 2285 . （in Chinese）

林友勤，郑学善，余印根，等 . 基于BP神经网络的斜拉索损伤识别方法［J］. 南昌大学学报（工科版）， 2023 ， 45 （ 4 ）： 370 - 376 .

Lin Y Q ， Zheng X S ， Yu Y G ， et al . Damage identification method for stay cable based on BP neural network ［J］. Journal of Nanchang University （Engineering & Technology）， 2023 ， 45 （ 4 ）： 370 - 376 . （in Chinese）

Kaveh A . Applications of artificial neural networks and machine learning in civil engineering ［M］. Cham ： Springer Nature Switzerland ， 2024 .

Wang L ， Xiao Z ， Wang X . The application of BP neural network in continuous girder bridge construction control ［C］∥ Proceedings of the 30th Chinese Control Conference . Yantai， China ： IEEE ， 2011 ： 2661 - 2664 .

周双喜，邓芳明，韩震，等 . 基于优化极限学习机的大跨径连续桥梁施工线形预测［J］. 铁道学报， 2019 ， 41 （ 3 ）： 134 - 140 .

Zhou S X ， Deng F M ， Han Z ， et al . The construction linear prediction of long-span continuous girder based on improved extreme learning machine ［J］. Journal of the China Railway Society ， 2019 ， 41 （ 3 ）： 134 - 140 . （in Chinese）

Zheng H B ， Yu X L ， Hu J L ， et al . Parameter sensitivity analysis of vertical deflection for long-span continuous rigid-frame bridge ［J］. Advanced Materials Research ， 2010 ，（ 163-167 ）： 1500 - 1504 .

Ma Y R ， Chen H B ， Han Q W . Sensitivity analysis of factors affecting down deflection of long-span continuous rigid frame bridge ［J］. IOP Conference Series： Earth and Environmental Science ， 2021 ， 781 （ 2 ）： 022048 .

Tong Y L . The multivariate normal distribution ［M］. New York， NY ： Springer New York ， 1990 .

公路工程结构可靠度设计统一标准： TG 2120—2020 ［S］. 北京： MTPRC ， 2020 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Slope Stability Prediction Based on PSO‑LightGBM Model

Research Progress on Fire Resistance of Reinforced Concrete Structures

Prediction of Unsaturated Soil Water Characteristic Curve Based on Machine Learning Algorithms

Rapid Prediction Model for Seismic Damage in Mega Composite Frame Structures Based on IPOA Methods

Research on Prediction Method of Structural Seismic Response Based on Ensemble Learning

Related Author

ZHANG Ning

ZHANG Yu

ZHANG Shijie

GONG Junlin

XU Tiangui

WANG Yuzhuo

LIU Zejian

ZHANG Xiayang

Related Institution

Collega of Civil Engineering , Anhui Jianzhu University

Anhui Provincial Key Laboratory of Intelligent Construction and Disaster Prevention and Control of Geotechnical Engineering , Anhui Jianzhu University

School of Civil Engineering, Shandong Jianzhu University, Ji'nan

School of Civil Engineering, Southeast University

School of Civil Engineering and Transportation, South China University of Technology

⁰