数据驱动下的城市更新片区公共服务设施布局优化算法研究与应用——以某大型产城融合混合社区为例-工程学研究-CSCIED科技核心评价数据库-手机版

数据驱动下的城市更新片区公共服务设施布局优化算法研究与应用——以某大型产城融合混合社区为例

Research and application of data-driven algorithm for optimizing the layout of public service facilities in urban renewal areas—a case study of a large-scale industry-city integration mixed community

ES评分 0 浏览量：104 下载量：0

全文阅读下载引用收藏

DOI	10.12208/j.jer.20260014
刊名	工程学研究 Journal of Engineering Research
年，卷(期)	2026, 5(1)
作者	杜明,
作者单位	同济大学建筑设计研究院（集团）有限公司，上海建筑数字建造工程技术研究中心上海
摘要	当前我国城市发展已从增量扩张转入存量提质的城市更新“新阶段”。面对既有城市片区空间局限性大、人口结构复杂、服务设施布局盲目等痛点，传统经验导向的规划方法难以满足精细化治理需求。本文提出一种基于CIM（城市信息模型）数字底座与非负加权图（Non-negative Weighted Graph）算法的公共服务设施布局优化模型。首先，利用无人机倾斜摄影与三维激光扫描技术构建高精度“空地一体”数字底座，解决现状数据缺失问题；其次，建立多目标优化数学模型，引入步行距离、日照环境及人群热力等多维约束，求解设施布局的最优解；最后，通过工程实证表明，该方法有效提升了设施服务覆盖率与空间利用效率，公共区域能耗降低约23%，为城市更新场景下的空间微改造提供了科学的量化决策支撑。
Abstract	My country's urban development has shifted from incremental expansion to a "new stage" of urban renewal that focuses on improving the quality of existing urban resources. Faced with challenges such as limited space, complex population structures, and haphazard layout of service facilities in existing urban areas, traditional experience-based planning methods are insufficient to meet the needs of refined governance. This paper proposes a public service facility layout optimization model based on a CIM (City Information Modeling) digital foundation and a non-negative weighted graph algorithm. First, a high-precision "air-ground integrated" digital foundation is constructed using UAV oblique photography and 3D laser scanning technology to address the problem of missing current data. Second, a multi-objective optimization mathematical model is established, incorporating multi-dimensional constraints such as walking distance, solar radiation, and population thermal dynamics to solve for the optimal solution for facility layout. Finally, engineering empirical studies demonstrate that this method effectively improves facility service coverage and space utilization efficiency, reducing public area energy consumption by approximately 23%, providing scientific quantitative decision-making support for spatial micro-transformation in urban renewal scenarios.
关键词	城市更新；公共设施布局；非负加权图；CIM；数字化规划
KeyWord	Urban renewal; Public facility layout; Non-negative weighted graph; CIM; Digital planning
基金项目
页码	64-67

参考文献
相关文献

[1] 吴志强. 城市规划新技术：人工智能与城市未来
[M]. 南京: 江苏凤凰科学技术出版社, 2019.

[2] 杨宝军. 实施城市更新行动，推进城市走向高质量发展
[R]. 住房和城乡建设部专题讲座, 2023.

[3] Wang X, et al. Identify different types of urban renewal implementations at the streetscape scale
[J]. International Journal of Geographical Information Science, 2025.

[4] Shabani A, AlWaer H, Taheri S. Artificial intelligence revolution in urban planning: a 30-year journey a review
[J]. Proceedings of the Institution of Civil Engineers - Urban Design and Planning, 2026, 179(1): 41-57.

[5] Brama H, Grinshpoun T, Landau O, et al. AI-Driven Recommendations for Strategic Urban Renewal
[C]// 30th International Conference of the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA). 2025: 91-100.

[6] Wardah W. Land Degradation Detection in Urban Areas Using Spatial Modelling and Semi-Automatic Classification of Satellite Imagery Data
[J]. Tropical Aquatic and Soil Pollution, 2025, 5(2): 110-124.

[7] He H, et al. Time-series land cover change detection using deep learning-based temporal semantic segmentation
[J]. Remote Sensing of Environment, 2024, 305: 114101.

[8] Qiao H, Jiang H, Yang G, et al. A Multi-Source Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building Footprint
[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 1-16.

[9] Wang X, Li X, Wu T, et al. Municipal and Urban Renewal Development Index System: A Data-Driven Digital Analysis Framework
[J]. Remote Sensing, 2024, 16(3): 456.

[10] Wang Y, Li C, Zhang H, et al. Research on Multi-Source Data Fusion Urban Functional Area Identification Method Based on Random Forest Model
[J]. Sustainability, 2025, 17(2): 515.

[11] 高峰,于滨.面向智慧城市管理巡查的可靠性无人机机巢选址优化方法
[J/OL].交通运输工程学报,1-16
[2026-03-02].

[12] Sheng Y, Zhou T, Wang J, et al. Data-Driven Assessment and Renewal Strategies for Public Space Vitality in Aged Residential Areas
[J]. Buildings, 2025, 15(23): 4299.

[13] 梁建青.多模态数据的判别度量学习研究
[D].天津大学,2019.

[14] Zhao Y, Li K, Zhang W. Digital Twin–Based Simulation and Decision-Making Framework for the Renewal Design of Urban Industrial Heritage Buildings and Environments: A Case Study of the Xi'an Old Steel Plant Industrial Park
[J]. Buildings, 2025, 15(23): 4367.

[15] 黄若鹏.老旧小区改造的居民合作行为的影响机理研究
[D].重庆大学, 2024.

[16] 吕志明,王霖青,赵珺,等.一种基于多代理模型的混合整数规划优化方法
[J].控制与决策,2019,34(02):362-368.

[17] 孙凯月.面向数字孪生的既有建筑内配电管线预测研究
[D].北京建筑大学,2023.

[18] 吴志强,周咪咪,刘琦,等.“跨代孪生”：映射城市的生命特征
[J].城市规划学刊,2024,(01):9-17.

[19] 吴志强,叶锺楠.基于百度地图热力图的城市空间结构研究——以上海中心城区为例
[J].城市规划,2016,40(04): 33-40.

[20] 董明泽,王冕,李婷娜.基于BIM与3DGIS集成的智慧园区规划与管理
[J].电子技术与软件工程,2021,(24):176-180.

[21] 胡亚辉.基于气候适应性的中观城市形态生成机理与方法
[D].东南大学,2021.

引用本文

杜明. 数据驱动下的城市更新片区公共服务设施布局优化算法研究与应用——以某大型产城融合混合社区为例 [J]. 工程学研究. 2026; 5; (1). 64 - 67.

文献评论

相关学者

相关机构