[1]任福鹏,高攀祥.粒子群优化小波神经网络在火灾预测中的应用研究[J].西安建筑科技大学学报:自然科学版,2014,46(03):348-352.[doi:10.15986/j.1006-7930.2014.03.008]
　REN Fupeng,GAO Panxiang.Application and research on particle swarm optimizing wavelet neural network in the prediction of fire[J].J.Xi’an Univ. of Arch. & Tech.:Natural Science Edition,2014,46(03):348-352.[doi:10.15986/j.1006-7930.2014.03.008]
点击复制

粒子群优化小波神经网络在火灾预测中的应用研究()
分享到：

西安建筑科技大学学报:自然科学版[ISSN:1006-7930/CN:61-1295/TU]

卷:
46
期数:
2014年03期
页码:
348-352
栏目:
出版日期:
2014-06-30

文章信息/Info

Title:
Application and research on particle swarm optimizing wavelet neural network in the prediction of fire
文章编号:
1006-7930(2014)03-0348-05
作者:
任福鹏1; 高攀祥2
(1.西安市新城区公安消防大队,陕西 西安 710003;2. 中国航天建设集团有限公司,北京 100071)
Author(s):
REN Fupeng1;  GAO Panxiang2
(1. Xi’an Xincheng District Public Security Fire Brigade, Xi’an 710003, China; 2. China Aerospace Construction Group Co.,Ltd.,Beijing 100071,China)
关键词:
火灾预测; 粒子群; 小波神经网络; 优化
Keywords:
fire prediction;  particle swarm;  wavelet neural network;  optimization
分类号:
TP183
DOI:
10.15986/j.1006-7930.2014.03.008
文献标志码:
A
摘要:
针对城市建筑火灾预测的高度非线性和不确定性,采用粒子群算法(PSO)优化小波神经网络(WNN)后建立火灾事故时间序列预测模型.将改进后的模型进行实验仿真训练并应用于某城市建筑火灾发生次数预测中,仿真应用结果表明,网络输出值和期望值很好吻合,收敛速度和泛化能力有所提高.所以该模型能够对火灾发生情况进行分析预测,为消防安全管理部门消防警力、设施投入及城市综合防灾减灾提供科学依据和决策指导.
Abstract:
In connection with the highly nonlinear and uncertainty of fire prediction of the city building, particle swarm optimization (PSO) is used to optimize the wavelet neural network (WNN) , so as to establish the fire accident time series prediction model. The improved model is applied in the experimental simulation training and forecasting of the number that the fire broke out of a city building. The simulation application results show that the network output and expected values are in good agreement, and the convergence speed and generalization ability is much improved. So the model can be used to analyze and forecast the fire and thus provide a scientific basis and decision-making guidance for fire police, investment in facilities and the city’s comprehensive disaster prevention and mitigation of fire safety management department.

参考文献/References:

[1] 杜兰萍.正确认识当前和以后一个时期我国火灾形势仍将相当严峻的客观必然性[J]. 消防科学与技术, 2005(1):1-4.

DU Lanping. The necessity to appropriately understand the fire situation in china is still serious now and in the future[J]. Fire Science and Technology, 2005(1):1-4.

[2] 李引擎. 建筑防火工程[M].北京:化学工业出版社, 2004.

LI Yinqing. Building fire protection engineering[M]. Beijing: Chemical Industry Press, 2004.

[3] 刘海生,张鑫磊,宋丽霞.基于统计数据的全国火灾形势综合评价与预测[J].中国安全科学学报, 2011, 2(6):54-59.

LIU Haisheng, ZHANG Xinlei, SONG Lixia. Comprehensive evaluation and prediction of fire accidents in China based on statistics[J]. China Safety Science Journal, 2011, 2(6):54-59.

[4] 张烨, 田雯, 刘盛鹏.基于集合经验模式分解的火灾时间序列预测[J].计算机工程, 2012,38(24): 152-154.

ZHANG Ye, TIAN Wen, LIU Shengpeng. Fire time series forecasting based on ensemble empirical mode decomposition[J]. Computer Engineering, 2012, 38(24): 152-154.

[5] KENNEDY J, EBERHART R. Particle swarm optimization [C]//Proc IEEE Int Confon Neural Net works ,1995(4):1942-1948.

[6] LI Daolun, LU Detang, KONG Xiangyan. Implicitcurves and surfaces based on BP neural network[J]. Journal of Information and Computational Science,2005,2(2):259-271.

[7] 王美玲, 张长江, 付梦印, 等.一种用于非线性函数逼近的小波神经网络算法仿真[J].北京理工大学学报, 2002, 22(3):274-278.

WANG Meiling, ZHANG Changjiang, FU Mengyin, et al. Simulation study of a kind of wavelet neural network algorithm used in approaching non-linear functions[J]. Journal of Beijing Institute of Technology, 2002, 22(3):274-278.

[8] 姜学鹏, 徐志胜.我国火灾起数的灰色拓扑预测[J].中国公共安全:学术版,2006(2):58-61.

JIANG Xuepeng, XU Zhisheng. Grey topological method in forecasting fire occurred in China[J]. China Public Security, 2006(2):58-61.

[9] 张栋楠, 舒中俊.改进型灰色神经网络在火灾预测中的应用研究[J].中国安全科学学报, 2012,22(2):53-54.

ZHANG Dongnan, SHU Zhongjun. Research on application of improved gray neural network in fire forecasting[J]. China Safety Science Journal, 2012, 22(2):53-54.

[10] 卓金武.MATLAB 在数学建模中的应用[M].北京:北京航空航天大学出版社, 2011.

ZHUO Jinwu. The application of MATLAB in mathematical modeling[M]. Beijing: Beijing Uni-versity of Aeronautics & Astronautics press, 2011.

备注/Memo

备注/Memo:
收稿日期:2013-11-21 修改稿日期:2014-06-13
基金项目:2012 年西安市产业技术创新计划项目(CX12181)
作者简介:任福鹏(1979-),男,少校,主要研究方向为火灾预测.E-mail:love_100000@163.com
更新日期/Last Update: 2015-09-01