基于BIM与增强约束方法的NSGA-Ⅱ算法的基坑支护结构多目标优化设计

doi:10.12066/j.issn.1007-2861.2702

摘要/Abstract

摘要： 随着建筑行业对环境可持续性的日益重视,大型建筑基坑支撑结构设计中的碳排放问题已成为一个不容忽视的关键问题.传统设计虽然强调成本效益,但往往缺乏对环境性能的考虑.提出了一种基于建筑信息模型(building information modeling,BIM)的增强约束方法,并将其集成至NSGA-Ⅱ框架,以实现基坑支护结构设计的多目标优化.首先,构建了基坑支护体系的碳排放计算准则,明确了计算的边界条件(涵盖建材的生产、运输、施工、拆除及回收等生命周期阶段);其次,在此基础上提出了一种增强约束方法,将设计规范转化为定量约束条件,并与NSGA-Ⅱ算法相结合,通过BIM平台提取结构信息,提升优化过程的精确性和可操作性;最后,针对2个典型基坑支护案例进行分析,以验证该方法的有效性和适用性.通过对2个基坑支护案例的研究分析可知,与传统设计相比该算法在成本和碳排放方面有明显改善,其设计在成本优化及碳性能优化设计的效率方面分别提高了40.9%和30.1%、25.3%和20.9%,为基坑支护结构设计提供了更加科学有效的优化方法.

关键词: NSGA-Ⅱ, 增强约束, 基坑支护, 多目标优化, BIM

Abstract: With increasing emphasis on environmental sustainability in the construction industry, carbon emissions in the design of large-scale foundation pit strut systems has become a critical issue that must be taken into account. While traditional designs prioritize cost-effectiveness, they often lack consideration of environmental performance. This paper proposes a building information modeling (BIM)-based enhanced constraint method and integrates it into the NSGA-Ⅱ framework to achieve multi-objective optimization of foundation pit strut design. First, carbon emission calculation criteria for foundation pit support systems are established, and the boundary conditions are defined, covering life-cycle stages including material production, transportation, construction, demolition, and recycling. On this basis, an enhanced constraint method is proposed to transform design codes into quantitative constraint conditions and combine them with the NSGA-Ⅱ algorithm. Structural information is extracted through a BIM platform to improve the accuracy and practicality of the optimization process. Finally, two typical foundation pit support cases are analyzed to verify the effectiveness and applicability of the proposed method. Compared with traditional designs, the optimization algorithm demonstrates significant improvements in both cost efficiency and carbon emission reduction. Specifically, cost optimization efficiency and carbon performance improve by 40.9% and 30.1%, and by 25.3% and 20.9%, respectively, in the two cases. This approach provides a more scientific and effective optimization methodology for foundation pit strut structural design.

Key words: NSGA-Ⅱ, enhanced constraint, foundation pit strut, multi-objective optimization, building information modeling (BIM)

中图分类号:

TU91

胡若帆, 舒展. 基于BIM与增强约束方法的NSGA-Ⅱ算法的基坑支护结构多目标优化设计[J]. 上海大学学报(自然科学版), 2026, 32(1): 130-141.

HU Ruofan, SHU Zhan. BIM-based multi-objective optimization of foundation pit strut structural design using NSGA-Ⅱ algorithm with enhanced constraints[J]. Journal of Shanghai University（Natural Science Edition）, 2026, 32(1): 130-141.

参考文献

[1] Admiraal H, Cornaro A. Why underground space should be included in urban planning policy|and how this will enhance an urban underground future [J]. Tunnelling and Underground Space Technology, 2016, 55: 214-220.
[2] Liu Y, Lai J, Wang W, et al. Low carbon optimization of deep foundation pit support in undulating strata [J]. Applied Sciences, 2023, 13(11): 6562.
[3] Sharghi M, Jeong H. The potential of recycling and reusing waste materials in underground construction: a review of sustainable practices and challenges [J]. Sustainability, 2024, 16(12): 4889.
[4] 陈芊茹, 彭阳, 余芳强. 基于BIM的低碳建筑研究与应用综述[J]. 建筑科学, 2024, 40(4): 66-74.
[5] Chen R J, Tsay Y S, Ni S W. An integrated framework for multi-objective optimization of building performance: carbon emissions, thermal comfort, and global cost [J]. Journal of Cleaner Production, 2022, 350: 131978.
[6] Zhang Y, Li Y J, Zhang Q, et al. Multi-objective optimization of building energy performance using a particle swarm optimizer with less control parameters [J]. Journal of Building Engineering, 2020, 32: 101505.
[7] 王竹君, 徐祖恩, 吴柯娴, 等. 基于全寿命环境成本的工程结构维护方案优化[J]. 建筑结构学报, 2019, 40(2): 227-237.
[8] 吴贤国, 冯宗宝, 刘俊, 等. 基于RF-NSGA-Ⅱ 的盾构施工地表沉降安全控制多目标优化[J]. 中国安全科学学报, 2022, 32(8): 45.
[9] Lin Y, Zhong S, Yang W, et al. Multi-objective design optimization on building integrated photovoltaic with Trombe wall and phase change material based on life cycle cost and thermal comfort [J]. Sustainable Energy Technologies and Assessments, 2021, 45: 101277.
[10] Wefki H, Elnahla M, Elbeltagi E. BIM-based schedule generation and optimization using genetic algorithms [J]. Automation in Construction, 2024, 164: 105476.
[11] Alothaimeen I, Arditi D, Turkak {n O H. Multi-objective optimization for LEED-new construction using BIM and genetic algorithms [J]. Automation in Construction, 2023, 149: 104807.
[12] Zhang Y Q, Hu J, Wang J, et al. Study on the mechanical behavior of a foundation pit retaining structure adjacent to the pile foundation of a subway station [J]. Environmental Earth Sciences, 2021, 80: 704.
[13] Zhang Y, Teoh B K, Zhang L. Multi-objective optimization for energy-e-cient building design considering urban heat island effects [J]. Applied Energy, 2024, 359: 124117.
[14] Gerhardt-Morsdorf J, Incer-Valverde J, Morosuk T, et al. Exergetic life cycle assessment for green hydrogen production [J]. Energy, 2024, 294: 131553.
[15] Xu A, Yang Q, Yang L, et al. Life cycle assessment and carbon footprint evaluation of a PEMFC system integrated with difierent hydrogen production routes [J]. Energy Conversion and Management, 2024, 308: 118586.
[16] 中华人民共和国住房和城乡建设部, 国家市场监督管理总局. 建筑碳排放计算标准: GB/T 51366|2019[S]. 北京: 中国建筑工业出版社, 2019.
[17] 路振伟, 袁帅, 阎俏. 基于全生命周期评价和能耗采集系统的建筑碳排放计算云平台的设计与实现 [J]. 建筑科学, 2024, 40(6): 17-25; 35.
[18] Lai K E, Rahiman N A, Othman N, et al. Quantification process of carbon emissions in the construction industry [J]. Energy and Buildings, 2023, 289: 113025.
[19] Hobbie J G, Gandomi A H, Rahimi I. A comparison of constraint handling techniques on NSGA-Ⅱ [J]. Archives of Computational Methods in Engineering, 2021, 28(3): 2033-2048.
[20] 中华人民共和国住房和城乡建设部. 建筑基坑支护技术规程: JGJ 120|2012[S]. 北京: 中国建筑工业出版社, 2012.
[21] 中华人民共和国住房和城乡建设部, 国家市场监督管理总局. 钢结构设计标准: GB 55006|2021[S]. 北京: 中国建筑工业出版社, 2021.
[22] Bossek J, Kerschke P, Trautmann H. A multi-objective perspective on performance assessment and automated selection of single-objective optimization algorithms [J]. Applied Soft Computing, 2019, 85: 105901.
[23] Allou L, Zouache D, Amroun K, et al. A novel epsilon-dominance Harris Hawks optimizer for multi-objective optimization in engineering design problems [J]. Neural Computing and Applications, 2022, 34(21): 19145-19170.