基于小波神经网络的多楼层疏散模型

doi:10.16182/j.issn1004731x.joss.20-0718

系统仿真学报 ›› 2022, Vol. 34 ›› Issue (2): 269-277.doi: 10.16182/j.issn1004731x.joss.20-0718

基于小波神经网络的多楼层疏散模型

魏娟^1,²(), 游磊³, 郭阳勇^1,², 唐志海¹

^1.成都师范学院计算机科学学院, 四川成都 611130
^2.成都师范学院室内空间布局优化与安全保障四川省高校重点实验室, 四川成都 611130
^3.成都大学计算机学院, 四川成都 610106

收稿日期:2020-09-18 修回日期:2020-12-21 出版日期:2022-02-18 发布日期:2022-02-23
作者简介:魏娟(1983-)，女，硕士，副研究员，研究方向为智能交通。Email：weijuan0905@126.com
基金资助:
国家自然科学基金面上项目(51978089);四川省科技厅应用基础项目(2019YJ0306);成都师范学院科研创新团队(CSCXTD2020B09)

Multi-floor Evacuation Model Based on Wavelet Neural Network

Juan Wei^1,²(), Lei You³, Yangyong Guo^1,², Zhihai Tang¹

^1.School of Computer Science, Chengdu Normal University, Chengdu 611130, China
^2.Key Laboratory of Interior Layout Optimization and Security, Institutions of Higher Education of Sichuan Province, Chengdu Normal University, Chengdu 611130, China
^3.College of Computer Science, Chengdu University, Chengdu 610106, China

Received:2020-09-18 Revised:2020-12-21 Online:2022-02-18 Published:2022-02-23

摘要/Abstract

摘要：

多楼层环境下室内人群疏散问题是社会关注的热点，而传统的社会力模型在模拟多楼层环境时容易出现停滞等待现象。基于小波神经网络来改进社会力模型，建立一种新的多楼层疏散模型。该模型利用场域模型来获得行人的运动方向，以此作为社会力模型中行人的自驱力方向。同时给出了多楼层环境下出口拥挤度、路径拥挤度和平均速度的评价指标，并利用小波神经网络建立疏散优化

方法

。利用搭建的仿真平台和上述改进模型模拟了多楼层疏散过程，深入分析了影响该模型的关键因素。该环境下疏散结果表明：适当提高行人的疏散速度有利于提高疏散效率，但是速度过大会使行人快速聚集在楼道处，反而不利于疏散；此外疏散时间随楼梯宽度的增加呈现递减趋势直至平稳，当楼梯宽度达到8 m时，再增加楼梯宽度也不能降低疏散时间。

关键词: 多楼层, 人群疏散, 社会力模型, 场域, 小波神经网络

Abstract:

Crowd evacuation in a multi-floor environment is a popular social concern, while the stagnation phenomenon easily occurs when simulating a multi-floor complex environment with the traditional social force model. Therefore, An improved social force model is proposed by a wavelet neural network, and a new multi-floor evacuation model is built. In the model, a pedestrian's direction of movement is obtained by the field model, which is used as the self-driving direction of the social force model. Meanwhile, the evaluation indexes of the exit congestion degree, path congestion degree, and average velocity in a multi-floor environment are given, and a wavelet neural network is employed to develop an evacuation optimization method. The evacuation process is simulated by the platform and the improved model, and the key factors in this model are studied. The results show that properly increasing the evacuation velocity of pedestrians can improve evacuation efficiency, but if the velocity is too high, pedestrians will gather in the corridor quickly, which is not conducive to evacuation. In addition, the evacuation time shows a decreasing trend with the increase in the staircase width before becoming stable, and when the staircase width reaches 8 m, further growth of the staircase width will not reduce the evacuation time.

Key words: multi-floor, crowd evacuation, social force model, field, wavelet neural network

中图分类号:

X913

魏娟, 游磊, 郭阳勇, 唐志海. 基于小波神经网络的多楼层疏散模型[J]. 系统仿真学报, 2022, 34(2): 269-277.

Juan Wei, Lei You, Yangyong Guo, Zhihai Tang. Multi-floor Evacuation Model Based on Wavelet Neural Network[J]. Journal of System Simulation, 2022, 34(2): 269-277.

图/表 11

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

参考文献 21

1	Helbing D, Farkas I, Vicsek T. Simulating Dynamical Features of Escape Panic[J]. Nature(S0028-0836), 2000, 407: 4282-4286.
2	Xu Mingliang, Wu Yunpeng, Lü Pei, et al. miSFM: on Combination of Mutual Information and Social Force Model Towards Simulating Crowd Evacuation[J]. Neurocomputing(S0925-2312), 2015, 168: 529-537.
3	Jiang Yanqun, Chen Bokui, Li Xi, et al. Dynamic Navigation Field in the Social Force Model for Pedestrian Evacuation[J]. Applied Mathematical Modelling(S0307-904X), 2020, 80: 815-826.
4	Liu Qian. A Social Force Model for the Crowd Evacuation in a Terrorist Attack[J]. Physica A(S0378-4371), 2018, 502: 315-330.
5	董力耘, 陈立, 段晓茵. 基于教室人群疏散实验的行人流建模和模拟[J]. 物理学报, 2015, 64(22): 220505.
	Dong Liyun, Chen Li, Duan Xiaoyin. Modeling and Simulation of Pedestrian Evacuation from a Single-exit Classroom based on Experimental Features[J]. Acta Physica Sinica, 2015, 64(22): 220505.
6	李明华, 袁振洲, 许琰, 等. 基于改进格子气模型的对向行人流分层现象的随机性研究[J]. 物理学报, 2015, 64(1): 018903.
	Li Minghua, Yuan Zhenzhou, Xu Yan, et al. Randomness Analysis of Lane Formation in Pedestrian Counter Flow based on Improved Lattice Gas Model[J]. Acta Physica Sinica, 2015, 64(1): 018903.
7	杨灿, 陈群, 陈璐. 考虑在能见度受限下行人跟随行为特性的建模与模拟[J]. 物理学报, 2019, 68(24): 240504.
	Yang Can, Chen Qun, Chen Lu. Modeling and Simulation of Following Behaviors of Pedestrians under Limited Visibility[J]. Acta Physica Sinica, 2019, 68(24): 240504.
8	Tao Y Z, Dong L Y. A Cellular Automaton Model for Pedestrian Counter Flow with Swapping[J]. Physica A(S0378-4371), 2017, 475: 155-168.
9	Luo Lin, Fu Zhijian, Cheng Han, et al. Update Schemes of Multi-velocity Floor Field Cellular Automaton for Pedestrian Dynamics[J]. Physica A(S0378-4371), 2018, 491: 946-963.
10	金辉, 郭仁拥. 基于元胞传输模型的楼梯区域行人运动[J]. 物理学报, 2019, 68(2): 020501.
	Jin Hui, Guo Renyong. Study of Pedestrian Flow on Stairs with a Cellular Transmission Model[J]. Acta Physica Sinica, 2019, 68(2): 020501.
11	岳昊, 何栋梁, 张滨雅, 等. 行人步行设施空间疏散特征指标[J]. 哈尔滨工业大学学报, 2017, 49(9): 17-24.
	Yue Hao, He Dongliang, Zhang Binya, et al. Spatial Characteristics Indexes of Pedestrian walking Facilities for Evacuation[J]. Journal of Harbin Institute of Technology, 2017, 49(9): 17-24.
12	Ma J, Lo S M, Song W G. Cellular Automaton Modeling Approach for Optimum Ultra High-rise Building Evacuation Design[J]. Fire Safety Journal(S0379-7112), 2012, 54: 57-66.
13	Kretz T, Grünebohm A, Kessel A, et al. Upstairs Walking Speed Distributions on a Long Stairway[J]. Safety Science, (S0925-7535), 2008, 46(1): 72-78.
14	Zhang Hao, Liu Hong, Qin Xin, et al. Modified Two-layer Social Force Model for Emergency Earthquake Evacuation[J]. Physica A(S0378-4371), 2018, 492: 1107-1119.
15	Takashi N. Four Species CA Model for Facing Pedestrian Traffic at Rush Hour[J]. Applied Mathematical Modelling(S0307-904X), 2012, 36(2): 702-711.
16	Song Weiguo, Yu Yanfei, Wang Binghong, et al. Evacuation Behaviors at Exit in CA Model with Force Essentials: A Comparison with Social Force Model[J]. Physica A(S0378-4371), 2006, 371: 658-666.
17	Sticco I M, Frank G A, Cornes F E, et al. A Re-examination of the Role of Friction in the Original Social Force Model[J]. Safety Science(S0925-7535), 2020, 121: 42-53.
18	Fang Zhiming, Song Weiguo, Li Zijuan, et al. Experimental Study on Evacuation Process in a Stairwell of a High-rise Building[J]. Building and Environment(S0360-1323), 2012, 47: 316-321.
19	Lui C H, Fong N K, Lorente S, et al. Constructal Design of Evacuation from a Three-dimensional Living Space[J]. Physica A(S0378-4371), 2015, 422: 47-57.
20	Wu Guanyuan, Huang Haochang. Modeling the Emergency Evacuation of the High Rise Building based on the Control Volume Model[J]. Safety Science(S0925-7535), 2015, 73: 62-72.
21	Yilmaz Sevcan, Oysal Yusuf. Fuzzy Wavelet Neural Network Models for Prediction and Identification of Dynamical Systems[J]. IEEE Transactions on Neural Networks(S1045-9227), 2010, 21(10): 1599-1609.

[1]	谢启苗, 郭帅帅. 基于社会力模型的客船人员疏散仿真研究[J]. 系统仿真学报, 2022, 34(8): 1710-1724.
[2]	魏娟, 李忠玉, 游磊, 郭阳勇, 唐志海, 胡周义. 考虑精英混沌搜索策略的室内行人疏散模型[J]. 系统仿真学报, 2021, 33(7): 1609-1616.
[3]	李昌华, 杨晶, 李智杰. 一种应用于人群仿真的改进社会力模型[J]. 系统仿真学报, 2021, 33(3): 521-528.
[4]	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.
[5]	王曦, 张蕊, 费硕, 杨明航. 基于社会力模型的地铁站域复合型通道行人仿真研究[J]. 系统仿真学报, 2021, 33(11): 2552-2560.
[6]	林海波, 郑利平, 王建伟, 张姝洁. 一种通用的层次化人群疏散仿真框架[J]. 系统仿真学报, 2020, 32(8): 1524-1530.
[7]	王杰, 陈彬, 袁鹏, 马亮, 邱晓刚. 数据驱动的最优互惠避碰模型偏好速度研究[J]. 系统仿真学报, 2019, 31(12): 2731-2739.
[8]	许伊婷, 张蕊. 基于同伴群行人仿真的通道设置研究[J]. 系统仿真学报, 2019, 31(11): 2477-2484.
[9]	孟小凡, 宋华. 基于神经网络的卫星姿控系统故障预测[J]. 系统仿真学报, 2019, 31(11): 2499-2508.
[10]	王修岩, 刘艳敏, 张革文, 李宗帅, 林家泉. 基于PSO和CRO联合算法的飞机客舱能耗预测[J]. 系统仿真学报, 2018, 30(8): 3074-3081.
[11]	庞明宝, 裴亚男, 张宁. 中小学门口道路上学混合交通流的综合仿真[J]. 系统仿真学报, 2018, 30(3): 1162-1171.
[12]	陈彬, 王亦平, 邱晓刚, 刘亮, 马亮. 动态数据驱动仿真应用思考:从物理域到社会域[J]. 系统仿真学报, 2018, 30(12): 4546-4554.
[13]	钟少波, 余致辰, 杨永胜, 孙超, 黄全义. 基于社会力模型的机场人员疏散建模研究[J]. 系统仿真学报, 2018, 30(10): 3648-3656.
[14]	刘经纬, 周瑞, 赵辉, 朱敏玲, 孟祥花, 张宇豪. 预测小波神经网络智能控制系统仿真研究[J]. 系统仿真学报, 2018, 30(10): 3770-3780.
[15]	董崇杰, 刘毅, 彭勇. 改进布谷鸟算法在人群疏散多目标优化中的应用[J]. 系统仿真学报, 2016, 28(5): 1063-1069.

基于小波神经网络的多楼层疏散模型

Multi-floor Evacuation Model Based on Wavelet Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价