基于GRU-模拟退火的公共建筑自校准客流仿真及空间优化研究

doi:10.16182/j.issn1004731x.joss.24-0704

摘要/Abstract

摘要：

实时、精准的客流仿真为公共建筑设施资源的优化配置及空间布局的合理性提供了重要的数据支撑。提出了一种基于GRU-SA算法的公共建筑自校准客流仿真与空间优化方法。使用Anylogic构建包含空间结构与流线的仿真模型。基于GRU-SA算法设计了一种自校准的公共建筑客流仿真方法，并应用于上海市某医院门诊部的客流仿真，通过与实际数据的对比验证了该方法的有效性。针对仿真过程中发现的客流拥堵问题，提出了空间布局优化方案，并对优化结果进行了可视化展示，构建了优化指标体系以评价优化效果。实际应用表明：该方法能够有效识别公共建筑空间设施布局中的瓶颈问题。在实施有针对性的布局优化方案后，排队时间减少了24.14%，设施的服务水平得到显著提升，客流密度降低了58.93%，有效缓解了客流聚集风险，降低了整体感染隐患。

关键词: 公共建筑, 客流仿真, 空间布局优化, 自校准, 模拟退火, GRU神经网络

Abstract:

Real-time and precise passenger flow simulation provides critical data support for the optimal allocation of resources in public building facilities and the rational design of spatial layouts. This study proposed a self-calibrating passenger flow simulation and spatial optimization method for public buildings based on the GRU-simulated annealing algorithm. A simulation model incorporating spatial structures and flow lines was constructed using Anylogic. A self-calibrating passenger flow simulation method for public buildingswas designed based on the GRU-simulated annealing algorithm and applied to the outpatient department of a hospital in Shanghai for passenger flow simulation. The effectiveness of the method was validated by comparing the simulation results with actual data. Spatial layout optimization schemes were proposed to address passenger flow congestion issues observed during the simulation, and the optimization results were visualized. An optimization metric systemwas developed to assess the effectiveness of the optimization. Practical application demonstrates that this method can effectively identify bottlenecks in the spatial layout of public building facilities. After implementing targeted layout optimization schemes, queuing time is reduced by 24.14%; the service level of the facilities is significantly improved, and passenger density is decreased by 58.93%, thereby mitigating passenger gathering risks and reducing overall infection hazards.

Key words: public building, passenger flow simulation, spatial layout optimization, self-calibrating, simulated annealing, GRU neural network

中图分类号:

TP391.9

许璟琳,陈芊茹,彭阳等 . 基于GRU-模拟退火的公共建筑自校准客流仿真及空间优化研究[J]. 系统仿真学报, 2025, 37(11): 2826-2838.

Xu Jinglin,Chen Qianru,Peng Yang,et al . Self-calibrating Passenger Flow Simulation and Spatial Optimization for Public Building Based on GRU-SA[J]. Journal of System Simulation, 2025, 37(11): 2826-2838.

图/表 16

图1

图2

图3

图4

表1

入口客流监测数据

出入口名	设备编号	客流数量 $N j$ /人	采集间隔时间 $t j$ /min	到达率 $λ j$
出入口1	3381	60	5	12
出入口2	1471	8	5	1.6

表1

表2

业务环节数据

业务环节区域	业务处理时长 $t K$	事件概率 $P K$
挂号窗口	5	(0,1)
缴费/取报告自助服务设施	5	(0,2)
取药窗口	5	(0,1)
抽血检查	16	(0,1)

表2

表3

图5

图6

图7

图8

表4

图9

图10

图11

图12

参考文献 20

[1]	Jamali N, Leung R K, Verderber S. A Review of Computerized Hospital Layout Modelling Techniques and Their Ethical Implications[J]. Frontiers of Architectural Research, 2020, 9(3): 498-513.
[2]	高枫. 超大型综合医院医疗体系设计研究[J]. 建筑学报, 2010(10): 96-99.
	Gao Feng. Study on Medical System Design for Super Large Comprehensive Hospital[J]. Architectural Journal, 2010(10): 96-99.
[3]	Mohiuddin S, Busby J, Savović Jelena, et al. Patient Flow Within UK Emergency Departments: A Systematic Review of the Use of Computer Simulation Modelling Methods[J]. BMJ Open, 2017, 7(5): e015007.
[4]	Wu Wenming, Fan Lubin, Liu Ligang, et al. MIQP-based Layout Design for Building Interiors[J]. Computer Graphics Forum, 2018, 37(2): 511-521.
[5]	Rodrigues Eugénio, Adélio Rodrigues Gaspar, Gomes Álvaro. An Approach to the Multi-level Space Allocation Problem in Architecture Using a Hybrid Evolutionary Technique[J]. Automation in Construction, 2013, 35: 482-498.
[6]	汪云峰. 基于空间认知智能体的医院流线结构评价[J]. 系统仿真学报, 2019, 31(2): 181-188.
	Wang Yunfeng. Evaluation of Flow Line Structure of Hospital with Spatial Cognitive Agent[J]. Journal of System Simulation, 2019, 31(2): 181-188.
[7]	Helber Stefan, Böhme Daniel, Oucherif Farid, et al. A Hierarchical Facility Layout Planning Approach for Large and Complex Hospitals[J]. Flexible Services and Manufacturing Journal, 2016, 28(1): 5-29.
[8]	Rismanchian Farhood, Hoon Lee Young. Process Mining-based Method of Designing and Optimizing the Layouts of Emergency Departments in Hospitals[J]. HERD: Health Environments Research & Design Journal, 2017, 10(4): 105-120.
[9]	Hoon Lee Young, Rismanchian Farhood. Optimizing Hospital Facility Layout Planning Through Process Mining of Clinical Pathways[J]. Annals of Optimization Theory and Practice, 2018, 1(1): 1-9.
[10]	Rys M J. Study on the Effect of Different Arrival Patterns on an Emergency Department's Capacity Using Discrete Event Simulation[J]. International Journal of Industrial Engineering: Theory, Applications and Practice, 2011, 18(1): 40-50.
[11]	Bhattacharjee Papiya, Pradip Kumar Ray. Patient Flow Modelling and Performance Analysis of Healthcare Delivery Processes in Hospitals: A Review and Reflections[J]. Computers & Industrial Engineering, 2014, 78: 299-312.
[12]	陈雷钰, 张汝华, 马明迪. 基于AnyLogic的轨道交通车站大客流瓶颈识别与疏散组织优化[J]. 上海大学学报(自然科学版), 2023, 29(4): 694-704.
	Chen Leiyu, Zhang Ruhua, Ma Mingdi. Anylogic-based Bottleneck Identification and Evacuation Organization Optimization of Large Passenger Flow in Rail Transit Stations[J]. Journal of Shanghai University(Natural Science Edition), 2023, 29(4): 694-704.
[13]	周雨阳, 何姗姗, 赵忞赫, 等. 轨道交通换乘站楼梯异质客流仿真[J]. 计算机仿真, 2023, 40(2): 203-207, 274.
	Zhou Yuyang, He Shanshan, Zhao Minhe, et al. Simulation of Heterogeneous Passenger Flow on Stairs of Rail Transit Transfer Station[J]. Computer Simulation, 2023, 40(2): 203-207, 274.
[14]	Wang Yingping, Yuan Rui, Tong Xueying, et al. Towards Simulation Optimization of Subway Station Considering Refined Passenger Behaviors[J]. PLoS One, 2024, 19(6): e0304081.
[15]	杨天阳, 朱志国. 基于Anylogic的地铁车站通道设施设备规模与布局分析[J]. 交通运输工程与信息学报, 2017, 15(1): 115-121.
	Yang Tianyang, Zhu Zhiguo. Scale and Layout Analyses of Subway Station Facilities Based on Anylogic Software[J]. Journal of Transportation Engineering and Information, 2017, 15(1): 115-121.
[16]	薛聪聪, 王冰冰. 基于Anylogic仿真法的门诊采血区设施配置与布局优化研究 -以中日友好医院为例[J]. 中国医院建筑与装备, 2020, 21(8): 52-55.
	Xue Congcong, Wang Bingbing. Research on the Optimization of the Facility Configuration and Layout of Outpatient Blood Collection Area Based on Anylogic Simulation-taking the China-Japan Friendship Hospital as an Example[J]. Chinese Hospital Architecture & Equipment, 2020, 21(8): 52-55.
[17]	郭海湘, 曾杨, 陈卫明. 基于社会力模型的多出口室内应急疏散仿真研究[J]. 系统仿真学报, 2021, 33(3): 721-731.
	Guo Haixiang, Zeng Yang, Chen Weiming. Research on Indoor Emergency Evacuation Simulation of Multi-exit Based on social Force Model[J]. Journal of System Simulation, 2021, 33(3): 721-731.
[18]	孙剑, 李克平. 行人运动建模及仿真研究综述[J]. 计算机仿真, 2008, 25(12): 12-16.
	Sun Jian, Li Keping. A Review of Pedestrian Modeling and Simulation[J]. Computer Simulation, 2008, 25(12): 12-16.
[19]	颜楷. 医院门诊流程再造与系统仿真优化建构研究[D]. 北京: 清华大学, 2019.
	Yan Kai. Simulation Optimization Paradigm Research For Hospital Outpatient Process Reengineering[D]. Beijing: Tsinghua University, 2019.
[20]	中华人民共和国住房和城乡建设部. 建筑智能化系统运行维护技术规范: [S]. 北京: 中国建筑工业出版社, 2017: 1-11.
	Ministry of Housing and Urban Rural Development of the People's Republic of China. Technical Code for Building Intelligent System Operation and Maintenance: [S]. Beijing: China Architecture & Building Press, 2017: 1-11.

编号	业务环节区域K	仿真客流密度	实际客流密度
1	抽血检查	0.157	0.230
2	挂号窗口	0.417	0.327
3	缴费/取报告自助服务设施	0.560	0.640
4	取药窗口	0.230	0.188

算法	客流密度最优误差	计算时长/s
SA	0.08	32.718
GRU-SA	0.07	9.3118