[1]张文武,李江峰,龙关旭,等.区域桥梁退化特征和绿色低碳管养决策[J].长安大学学报(自然科学版),2026,46(01):108-117.[doi:10.19721/j.cnki.1671-8879.2026.01.008]
　ZHANG Wen-wu,LI Jiang-feng,LONG Guan-xu,et al.Degradation characteristics of regional bridges and green low-carbon management and maintenance decision[J].Journal of Chang’an University (Natural Science Edition),2026,46(01):108-117.[doi:10.19721/j.cnki.1671-8879.2026.01.008]
点击复制

区域桥梁退化特征和绿色低碳管养决策()
分享到：

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
第46卷
期数:
2026年01期
页码:
108-117
栏目:
桥梁与隧道工程
出版日期:
2026-01-31

文章信息/Info

Title:
Degradation characteristics of regional bridges and green low-carbon management and maintenance decision
文章编号:
1671-8879(2026)01-0108-10
作者:
张文武1; 李江峰2; 龙关旭3; 高欣凯4; 夏烨2*
(1. 山东高速集团有限公司,山东 济南 250098; 2. 同济大学 土木工程学院,上海 200092; 3. 山东高速集团有限公司 创新研究院,山东 济南 250098; 4. 山东高速工程检测有限公司,山东 济南 250002)
Author(s):
ZHANG Wen-wu1;  LI Jiang-feng2;  LONG Guan-xu3;  GAO Xin-kai4;  XIA Ye2*
(1. Shandong Hi-Speed Group Co., Ltd., Jinan 250098, Shandong, China; 2. College of Civil Engineering,Tongji University, Shanghai 200092, China; 3. Innovation Research Institute, Shandong Hi-Speed Group Co., Ltd., Jinan 250098, Shandong, China; 4. Shandong Hi-Speed Engineering Consulting Group Co., Ltd., Jinan 250002, Shandong, China)
关键词:
桥梁工程;  NSGA-Ⅲ;  退化模型;  养护决策;  绿色低碳
Keywords:
bridge engineering;  NSGA-Ⅲ;  deterioration model;  maintenance decision;  green low-carbon
分类号:
U445.7
DOI:
10.19721/j.cnki.1671-8879.2026.01.008
文献标志码:
A
摘要:
为使桥梁养护适应当前可持续发展要求,构建了一个融合桥梁退化预测、成本控制与绿色低碳目标的管养决策模型; 通过调研和机理探究,选取桥梁位置、设计时速、路基宽度、交通量、桥龄、桥型等作为特征列,基于反向传播(BP)神经网络构建了桥梁退化预测模型,将桥梁总体、上部、下部及桥面状态划分为5个等级; 提出了桥梁养护碳排放计算框架,包括维修工程和延误交通两部分,系统搜集并整理了材料生产与运输、能源及施工机械等环节计算时所需碳排放因子,根据二氧化碳在大气中随时间衰减的情况引入动态碳排放因子,以反映衰减效应,并从单桥单次维修、单桥多次维修逐步推出多桥多次维修的计算方法; 在此基础上,通过非支配排序遗传算法-Ⅲ(NSGA-Ⅲ)构建了基于养护费用、安全评级、二氧化碳排放量这3个目标函数的多目标优化模型; 以山东高速公路网为例,选取1 362座桥梁的7 225组数据进行模型训练和验证,通过设定不同的代价系数,调整BP神经网络模型层数,以准确率为评价指标测试了不同神经网络参数的退化模型的性能,并选取了最优模型; 进一步将该退化模型与NSGA-Ⅲ结合,通过非支配排序给出了Pareto前沿解集,设置了不同区分点,得到了不同偏重指标的养护策略。研究结果表明:在4层隐藏网络结构和对低等级状态预测错误设置更高惩罚权重的代价系数条件下,退化模型取得的分类准确率为76.5%,相较于网络结构相同但仅考虑均等错误代价的基线模型(分类准确率为67.2%)有明显提升,表明采用的代价敏感学习策略能改善模型对关键状态的预测性能; 结合NSGA-Ⅲ和较优的退化预测模型得到的Pareto解集包含了费用、均衡、安全与绿色方案,每个方案都无法在不损失其他指标的前提下提高某个指标,是局部最优解,而多种差异化方案能够满足桥梁养护的多样需求。
Abstract:
To adapt bridge maintenance to current sustainable development requirements, a management and maintenance decision model integrating the bridge deterioration prediction, cost control, and green low-carbon objectives was constructed. Through the investigation and mechanism analysis, bridge location, design speed, subgrade width, traffic volume, bridge age, and bridge type were selected as the characteristic columns. A bridge deterioration prediction model was developed based on the back propagation(BP)neural network. The overall, superstructure, substructure, and deck conditions of bridges were classified into five grades. A calculation framework for bridge maintenance carbon emissions was proposed, including two parts: maintenance work and traffic delay. Carbon emission factors required for calculation in material production and transportation, energy, and construction machinery phases were systematically collected and organized. The dynamic carbon emission factor was introduced based on the decay of carbon dioxide in the atmosphere over time to reflect the attenuation effect. The calculation method was progressively derived from a single bridge with a single maintenance, to a single bridge with multiple maintenances, and finally to multiple bridges with multiple maintenances. On this basis, a multi-objective optimization model with three objective functions, such as the maintenance cost, safety rating, and carbon dioxide emission, was constructed using the non-dominated sorting genetic algorithm-Ⅲ(NSGA-Ⅲ). Taking the Shandong Expressway Network as an example, 7 225 sets of data from 1 362 bridges were selected for model training and validation. By setting different cost coefficients and adjusting the number of layers in the BP neural network model, the properties of deterioration models with different neural network parameters were tested using accuracy as the evaluation indicator, and the optimal model was selected. This deterioration model was further combined with NSGA-Ⅲ. The Pareto front solution sets were obtained through non-dominated sorting, and by setting different differentiation points, maintenance strategies with different emphases on indicators were derived. The research results show that under the conditions of a 4-layer hidden network structure and adopting a cost coefficient with a higher penalty weight to prediction errors for lower condition grades, the deterioration model achieves a classification accuracy of 76.5%, showing a clear improvement compared to the baseline model with the same network structure but considering only equal error costs(the classification accuracy is 67.2%). This indicates that the adopted cost-sensitive learning strategy can improve the model's prediction property for critical conditions. The Pareto solution set obtained by combining the relatively optimal deterioration prediction model with NSGA-Ⅲ includes the cost-oriented, balanced, safety-oriented, and green-oriented solutions. Each solution cannot improve one indicator without sacrificing others, making them local optimal solutions. While these diverse solutions can meet the varied needs in bridge maintenance.6 tabs, 8 figs, 30 refs.

参考文献/References:

[1] 张 洪,左 勤,辛景舟,等.桥梁退化模型及养护时机研究综述[J].科学技术与工程,2022,22(8):2993-3001.
ZHANG Hong, ZUO Qin, XIN Jing-zhou, et al. Review of research on bridge degradation model and maintenance timing[J]. Science Technology and Engineering, 2022, 22(8): 2993-3001.
[2]夏 烨,张宸鸿,杨国强,等.基于病害数据治理的网级桥梁退化模型[J].中国公路学报,2025,38(11):151-163.
XIA Ye, ZHANG Chen-hong, YANG Guo-qiang, et al. Network-level bridge degradation model based on data restoration of defects[J]. China Journal of Highway and Transport, 2025, 38(11): 151-163.
[3]张精卫,李 博.基于生成对抗网络模型的光线不良情形桥梁裂缝检测算法研究[J].桥梁建设,2025,55(5):98-104.
ZHANG Jing-wei, LI Bo. Bridge crack detection algorithm in in poor lighting conditions based on CycleGAN[J]. Bridge Construction, 2025, 55(5): 98-104.
[4]王晓明,李鹏飞,吴润涵,等.考虑加固时间区间的在役混凝土桥梁运维策略分析[J].华南理工大学学报(自然科学版),2025,53(6):34-43.
WANG Xiao-ming, LI Peng-fei, WU Run-han, et al. Analysis of operation and maintenance strategy of existing concrete bridge considering reinforcement time interval[J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(6): 34-43.
[5]王晓明,汪 帆,翟 岸,等.退化RC桥梁检测-维护规划的贝叶斯决策方法[J].交通运输工程学报,2025,25(3):130-143.
WANG Xiao-ming, WANG Fan, ZHAI An, et al. Bayesian decision method of inspection and maintenance planning for deteriorating RC bridges[J]. Journal of Traffic and Transportation Engineering, 2025, 25(3): 130-143.
[6]王晓明,贺耀北,贺拴海.考虑不确定性的既有桥梁网络管养对策优化[J].长安大学学报(自然科学版),2015,35(6):71-78.
WANG Xiao-ming, HE Yao-bei, HE Shuan-hai. Maintenance strategy optimization of existing bridge network with consideration of uncertainty[J]. Journal of Chang'an University(Natural Science Edition), 2015, 35(6): 71-78.
[7]彭邦文,郑闳方,朱 磊,等.中国工业碳排放网络结构演化特征与链路预测[J].中国环境科学,2024,44(3):1718-1731.
PENG Bang-wen, ZHENG Hong-fang, ZHU Lei, et al. Evolution characteristics and link prediction of China's industrial carbon emission network structure[J]. China Environmental Science, 2024, 44(3): 1718-1731.
[8]RAEISI F, ALGOHI B, MUFTI A, et al. Reducing carbon dioxide emissions through structural health monitoring of bridges[J]. Journal of Civil Structural Health Monitoring, 2021, 11(3): 679-689.
[9]中国建筑节能协会.中国建筑能耗研究报告2020[J].建筑节能(中英文),2021,49(2):1-6.
China Association of Building Energy Efficiency. China building energy consumption research annual report 2020[J]. Building Energy Efficiency, 2021, 49(2): 1-6.
[10]熊斌斌,徐水太,徐丝美,等.中国省域建筑业碳排放效率与减排潜力的互动关系[J/OL].环境科学,(2025-11-05)[2025-12-02].https://doi.org/10.13227/j.
hjkx.202505017.
XIONG Bin-bin, XU Shui-tai, XU Si-mei, et al. Interactive mechanism of carbon emission efficiency and emission reduction potential in Chinese provincial construction industry[J/OL]. Environmental Science,(2025-11-05)[2025-12-02]. https://doi.org/10.13227/j.
hjkx.202505017.
[11]SOBANJO J O. A neural network approach to modeling bridge deterioration[C]//TERSEA A. Computing in Civil Engineering. Reston: ASCE, 1997: 623-626.
[12]TOKDEMIR O B, AYVALIK C, MOHAMMADI J. Prediction of highway bridge performance by artificial neural networks and genetic algorithms[C]//WANG M T. Proceedings of the 17th IAARC/CIB/IEEE/IFR International Symposium on Automation and Robotics in Construction. Taipei: National Taiwan University, 2000: 1091-1098.
[13]XIE H B, WU W J, WANG Y F. Life-time reliability based optimization of bridge maintenance strategy considering LCA and LCC[J]. Journal of Cleaner Production, 2018, 176: 36-45.
[14]王 鹏.中小跨径桥梁结构健康监测与网级评估[D].上海:同济大学,2019.
WANG Peng. Structural health monitoring and network-level assessment of small- and medium-span bridges[D]. Shanghai: Tongji University, 2019.
[15]戴理朝,康 哲,陈 瑞,等.基于NSGA-Ⅲ的桥梁网络多目标维修决策优化研究[J].土木工程学报,2024,57(5):41-52.
DAI Li-zhao, KANG Zhe, CHEN Rui, et al. Study on multi-objective maintenance decision optimization for bridge networks based on NSGA-Ⅲ[J]. China Civil Engineering Journal, 2024, 57(5): 41-52.
[16]陶 洁,王沛霖,王 辉,等.基于A-NSGA-Ⅲ的引江济淮工程河南段水资源优化配置研究[J].水利水电科技进展,2023,43(6):111-119.
TAO Jie, WANG Pei-lin, WANG Hui, et al. Research on water resources optimal allocation in Henan Section of Yangtze River to Huaihe River Water Diversion Project based on A-NSGA-Ⅲ algorithm[J]. Advances in Science and Technology of Water Resources, 2023, 43(6): 111-119.
[17]夏 烨,雷晓鸣,王 鹏,等.针对网级评估的区域桥梁退化建模与演绎应用[J].中南大学学报(自然科学版),2021,52(3):828-838.
XIA Ye, LEI Xiao-ming, WANG Peng, et al. Degradation modeling and application of regional bridges for network-level assessment[J]. Journal of Central South University(Science and Technology), 2021, 52(3): 828-838.
[18]王海涛,栾治军,黄明利,等.基于碳排放评价的桥梁路基建设方案比选优化研究[J].公路,2023,68(4):275-281.
WANG Hai-tao, LUAN Zhi-jun, HUANG Ming-li, et al. Study on comparison and optimization of bridge subgrade construction schemes based on carbon emission assessment[J]. Highway, 2023, 68(4): 275-281.
[19]RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323: 533-536.
[20]崔 猛,孙一城,李卫华,等.基于历史桥检数据的既有桥梁技术状况退化模型更新[J/OL].工程力学,(2024-06-27)[2025-12-02].https://link.cnki.net/urlid/11.2595.o3.20240626.1240.002.
CUI Meng, SUN Yi-cheng, LI Wei-hua, et al. Bayesian updating of bridge condition deterioration model using historic inspection data[J/OL]. Engineering Mechanics,(2024-06-27)[2025-12-02]. https://link.cnki.net/urlid/11.2595.o3.20240626.1240.002.
[21]齐锡晶,唐 梁,康伟鑫,等.高速公路桥梁桥面板养护方案多目标决策方法[J].东北大学学报(自然科学版),2020,41(7):1033-1040.
QI Xi-jing, TANG Liang, KANG Wei-xin, et al. Multi-objective decision-making method for bridge deck maintenance scheme for highway[J]. Journal of Northeastern University(Natural Science), 2020, 41(7): 1033-1040.
[22]吴柯娴,金伟良,何晓宇,等.混凝土桥梁结构全寿命可持续性成本量化模型[J].同济大学学报(自然科学版),2024,52(10):1527-1536.
WU Ke-xian, JIN Wei-liang, HE Xiao-yu, et al. Quantitative models for life-cycle sustainability cost of concrete bridge structures[J]. Journal of Tongji University(Natural Science), 2024, 52(10): 1527-1536.
[23]孙晓燕,董伟伟,王海龙,等.考虑生命周期碳补偿成本的桥梁维修优化决策[J].浙江大学学报(工学版),2012,46(11):2013-2019.
SUN Xiao-yan, DONG Wei-wei, WANG Hai-long, et al. Bridge maintenance optimization based on life cycle carbon offset cost analysis[J]. Journal of Zhejiang University(Engineering Science), 2012, 46(11): 2013-2019.
[24]宋泰宇,邓青儿.桥梁工程碳排量计算和低碳性能评价研究进展与展望[J].桥梁建设,2025,55(1):33-40.
SONG Tai-yu, DENG Qing-er. Research progress and prospects of carbon emission calculation and low-carbon performance evaluation of bridge engineering[J]. Bridge Construction, 2025, 55(1): 33-40.
[25]张春霞,章蓓蓓,黄有亮,等.建筑物能源碳排放因子选择方法研究[J].建筑经济,2010(10):106-109.
ZHANG Chun-xia, ZHANG Bei-bei, HUANG You-liang, et al. Study on choice method of energy's carbon emission factors for buildings[J]. Construction Economy, 2010(10): 106-109.
[26]GB/T 51366—2019,建筑碳排放计算标准[S].
GB/T 51366—2019, Standard for building carbon emission calculation[S].
[27]SHINE K P, BERNTSEN T K, FUGLESTVEDT J S, et al. Comparing the climate effect of emissions of short- and long-lived climate agents[J]. Philosophical Transactions Series A, Mathematical, Physical, and Engineering Sciences, 2007, 365(1856): 1903-1914.
[28]DEB K, JAIN H. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, Part Ⅰ: Solving problems with box constraints[J]. IEEE Transactions on Evolutionary Computation, 2014, 18(4): 577-601.
[29]MORCOUS G, LOUNIS Z, MIRZA M S. Identification of environmental categories for Markovian deterioration models of bridge decks[J]. Journal of Bridge Engineering, 2003, 8(6): 353-361.
[30]吴雨茜,王俊丽,杨 丽,等.代价敏感深度学习方法研究综述[J].计算机科学,2019,46(5):1-12.
WU Yu-xi, WANG Jun-li, YANG Li, et al. Survey on cost-sensitive deep learning methods[J]. Computer Science, 2019, 46(5): 1-12.

相似文献/References:

[1]李宇,朱晞,杨庆山,等.高墩大跨桥梁结构的脆弱性分析[J].长安大学学报(自然科学版),2012,32(01):0.
[2]高亮,刘健新,张丹,等.桁架桥主梁三分力系数试验[J].长安大学学报(自然科学版),2012,32(01):0.
[3]刘旭政,王丰平,黄平明,等.斜拉桥各构件校验系数的常值范围[J].长安大学学报(自然科学版),2012,32(01):0.
[4]尚维波,张春宁.高墩刚构桥系梁抗震分析[J].长安大学学报(自然科学版),2012,32(01):0.
[5]邬晓光,李冀弘,宋伟伟.基于改进响应面法的在役PC桥梁承载力可靠性[J].长安大学学报(自然科学版),2012,32(03):53.
　WU Xiao-guang,LI Ji-hong,SONG Wei-wei.Reliability of existing PC bridge based on improved response surface method[J].Journal of Chang’an University (Natural Science Edition),2012,32(01):53.
[6]石雄伟,袁卓亚,马毓泉,等.钢板-混凝土组合加固预应力混凝土箱梁[J].长安大学学报(自然科学版),2012,32(03):58.
　SHI Xiong-wei,YUAN Zhuo-ya,MA Yu-quan,et al.Prestressed concrete box girder strengthened with comsposition of steel plate and concrete[J].Journal of Chang’an University (Natural Science Edition),2012,32(01):58.
[7]李传习,陶 伟,董创文.斜交墩截面刚度与弯曲正应力[J].长安大学学报(自然科学版),2012,32(03):63.
　LI Chuan-xi,TAO Wei,DONG Chuang-wen.Sectional stiffness and bending normal stress of oblique pier[J].Journal of Chang’an University (Natural Science Edition),2012,32(01):63.
[8]邓继华,邵旭东.带铰平面梁元几何非线性有限元分析[J].长安大学学报(自然科学版),2012,32(03):68.
　DENG Ji-hua,SHAO Xu-dong.Geometric nonlinear finite element analysis of plane beam element with hinge[J].Journal of Chang’an University (Natural Science Edition),2012,32(01):68.
[9]蒲广宁,赵 煜,宋一凡.减梁增肋法加固空心板桥的力学性能[J].长安大学学报(自然科学版),2012,32(06):38.
　PU Guang-ning,ZHAO Yu,SONG Yi-fan.Mechanical properties of strengthening hollow slab bridge based on beam-reduction and rib-addition method[J].Journal of Chang’an University (Natural Science Edition),2012,32(01):38.
[10]党 栋,贺拴海,周勇军,等.基于车辆统计数据的汽车荷载标准值取值与评估[J].长安大学学报(自然科学版),2012,32(06):44.
　DANG Dong,HE Shuan-hai,ZHOU Yong-jun,et al.Choosing and assessment for the standard of vehicle load based on vehicle statistical data[J].Journal of Chang’an University (Natural Science Edition),2012,32(01):44.

备注/Memo

备注/Memo:
收稿日期:2025-07-22
基金项目:国家自然科学基金项目(52278313); 山东省交通运输厅科技计划项目(2021B51)
作者简介:张文武(1981-),男,山东济宁人,高级工程师,从事区域桥梁群智能监测与安全风险监控研究,E-mail:147849246@qq.com。
通信作者:夏 烨(1983-),男,湖南永州人,副教授,工学博士,E-mail:yxia@tongji.edu.cn。
更新日期/Last Update: 2026-02-20