GWO-BP-based forecasting of emergency material demand in post-earthquake transitional resettlement phase

doi:10.16265/j.cnki.issn1003-3033.2024.10.0131

Abstract

Abstract:

In order to accurately predict the material demand in the transitional resettlement stage of earthquakes and improve the efficiency and accuracy of emergency material mobilization, the factors that have a great impact on the number of resettled population were determined based on the historical seismic data in China. A prediction model of the resettled population based on GWO-BP was established, which combined with the quantitative relationship between the population and emergency supplies, to predict the material demand in the transitional resettlement stage after the earthquake. The experimental results show that the GWO-BP neural network model exhibits high accuracy and stability in predicting the number of relocated populations, and can effectively predict the number of relocated populations in disaster areas, thereby calculating the corresponding material demand. GWO-BP neural network model has a certain application value in predicting material demand in post-earthquake transitional resettlement stage, and can provide a reference for the decision-making of emergency material procurement after the earthquake.

Key words: gray wolf optimization algorithm(GWO), back propagation(BP) neural network, earthquake, transitional resettlement phase, emergency material, demand forecasting

CLC Number:

X913.4安全系统工程

ZHAN Wei, CHENG Chunxin. GWO-BP-based forecasting of emergency material demand in post-earthquake transitional resettlement phase[J]. China Safety Science Journal, 2024, 34(10): 17-23.

Figures/Tables 10

Fig.1

Fig.2

Table 1

Fig.3

Fig.4

Table 2

Fig.5

Table 3

Table 4

Parameter setting

参数	k₁	k₂	k₃	k₄	k₅	P	$θ$
数值	2 000	1.6	1.66	0.5	1	3	1

Table 4

Table 5

References 18

[1]	王海鹰, 孙刚, 欧阳春, 等. 地震应急期关键时间阶段划分研究[J]. 灾害学, 2013, 28(3): 166-169,197.
	WANG Haiying, SUN Gang, OUYANG Chun, et al. Phases of earthquake emergency response period[J]. Journal of Catastrophology, 2013, 28(3): 166-169, 197.
[2]	陈刚, 付江月. 兼顾公平与效率的多目标应急物资分配问题研究[J]. 管理学报, 2018, 15(3): 459-466.
	CHEN Gang, FU Jiangyue. Multi-objective emergency resources allocation with fairness and efficiency considerations[J]. Chinese Journal of Management, 2018, 15(3): 459-466.
[3]	王丛虎. 构建和完善服务需求导向的应急物资保障[J]. 人民论坛, 2022(9): 58-61.
	WANG Conghu. Build and improve service demand-oriented emergency material security[J]. People's Tribune, 2022(9): 58-61.
[4]	中华人民共和国应急管理部. 《“十四五”应急物资保障规划》解读[EB/OL]. (2023-02-02). https://www.mem.gov.cn/gk/zcjd/202302/t20230202_441507.shtml.
[5]	郭金芬, 周刚. 大型地震应急物资需求预测方法研究[J]. 价值工程, 2011, 30(22): 27-29.
	GUO Jinfen, ZHOU Gang. Research on emergency material demand forecast method under large-scale earthquakes[J]. Value Engineering, 2011, 30(22): 27-29.
[6]	刘芳, 冯丹, 宫雪然. 基于IACO-BP算法的洪涝灾害应急物资需求预测[J]. 沈阳工业大学学报, 2019, 41(3): 332-338. doi: 10.7688/j.issn.1000-1646.2019.03.17
	LIU Fang, FENG Dan, GONG Xueran. Demand predicting of emergency supplies for flood disaster based on IACO-BP algorithm[J]. Journal of Shenyang University of Technology, 2019, 41(3): 332-338. doi: 10.7688/j.issn.1000-1646.2019.03.17
[7]	樊睿. 基于PSO-BP神经网络的大型地震应急物资需求预测研究[D]. 北京: 北京交通大学, 2020.
	FAN Rui. Forecast of large earthquake emergency material demand based on PSO-BP neural network[D]. Beijing: Beijing Jiaotong University, 2020.
[8]	周德红, 冯豪, 冯文斌, 等. 基于GA-BP神经网络的化工园区应急救援能力可靠性分析[J]. 安全与环境工程, 2017, 24(5): 43-49.
	ZHOU Dehong, FENG Hao, FENG Wenbin, et al. Reliability analysis for emergency rescue capacity in the chemical industry park based on GA-BP neural network[J]. Safety and Environmental Engineering, 2017, 24(5): 43-49.
[9]	MIRJALILI S, MIRJALILI M S, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014,69: 46-61.
[10]	钱枫林, 崔健. BP神经网络模型在应急需求预测中的应用:以地震伤亡人数预测为例[J]. 中国安全科学学报, 2013, 23(4): 20-25.
	QIAN Fenglin, CUI Jian. Application of BP neural networkanalysis in forecasting emergency demand:a case study on earthquake casualty forecasting[J]. China Safety Science Journal, 2013, 23(4): 20-25.
[11]	杨书杰, 叶霞, 李俊山. 基于灰狼算法的BP神经网络图像恢复算法[J]. 微电子学与计算机, 2018, 35(3): 19-22,27.
	YANG Shujie, YE Xia, LI Junshan. BP neural network for image restoration based on grey wolf optimization algorithm[J]. Microelectronics & Computer, 2018, 35(3): 19-22,27.
[12]	单无牵, 宁芊, 周新志, 等. 基于灰狼优化算法的灌区流量预测模型研究[J]. 现代计算机, 2023, 29(1): 45-49120.
	SHAN Wuqian, NING Qian, ZHOU Xinzhi, et al. Research on irrigation area discharge prediction model based on grey wolf optimization algorithm[J]. Modern Computer, 2023, 29(1): 45-49120.
[13]	CHOU Yiingjeng, HUANG Nicole, LEE Chenghua, et al. Who is at risk of death in an earthquake?[J]. American Journal of Epidemiology, 2004, 7: 688-695.
[14]	ARMENIAN H K, NOJI E K, OGANESIAN A P. A casecontrol study of injuries arising from the earthquake in armenia, 1988[J]. Bulletin of the World Health Organization, 1992, 70(2): 251-257.
[15]	闫佳琦, 陈相兆, 孙柏涛. 地震人员伤亡评估方法及损失评估系统综述[J]. 工程力学, 2021, 38(12): 1-16.
	YAN Jiaqi, CHEN Xiangzhao, SUN Baitao. Review of estimation metods and systems used to predict earthquake casualties[J]. Engineering Mechanics, 2021, 38(12): 1-16.
[16]	RAMIREZ M, PEEK A C. Epidemiology of traumatic injuries from earthquakes[J]. Epidemiologic Reviews, 2005, 27(1): 47-55.
[17]	蔡荣辉, 崔雨轩, 薛培静. 三层BP神经网络隐层节点数确定方法探究[J]. 电脑与信息技术, 2017, 25(5): 29-33.
	CAI Ronghui, CUI Yuxuan, XUE Peijing. Research on the methods of determining the number of hidden nodes in three-layer bp neural network[J]. Computer and Information Technology, 2017, 25(5): 29-33.
[18]	聂高众, 高建国, 苏桂武, 等. 地震应急救助需求的模型化处理:来自地震震例的经验分析[J]. 资源科学, 2001, 23(1): 69-76.
	NIE Gaozhong, GAO Jianguo, SU Guiwu, et al. Models on rapid jugement for the emergent rescue needs during earthquake:by analysis on post earthquake events[J]. Resources Science, 2001, 23(1): 69-76.

序号	地点	震级	发生时间	设防烈度	破坏烈度	住房捣毁/间	预报水平	人口密度/ (人·km^-2)	受灾人口/人
1	河北唐山	7.9	2	5	7	656 136	2	11 000	2 300 000
2	云南丽江	7	1	7	8	959 000	2	11	1 075 000
3	云南宁洱	6.4	2	9	4	360 000	2	73	186 000
4	四川攀枝花	6.4	2	9	4	365 120	3	102	103 055
5	西藏拉萨	6.1	1	7	8	7 466	3	121	130 300
6	青海玉树	7.1	1	7	4	3 805	1	7	201 955
7	四川雅安	7	1	7	4	910	2	122	152 001
8	云南鲁甸	6.5	1	7	4	900	1	265	108 8400
9	新疆和田	7.3	1	7	4	13 662	1	4	455 570
10	四川宜宾	6	1	6	6	30 655	1	340	243 881
11	四川宜宾	4.5	2	6	5	90	1	344	83 000
12	西藏林芝	6.9	1	7	8	3 000	1	1	12 000
13	新疆精河	6.6	1	7	8	5 469	1	12	10 500
14	四川九寨沟	7	1	8	9	73 671	1	3 000	176 492
15	新疆阿克陶	6.7	1	7	9	571	1	7	2 546
16	西藏当雄	6.6	1	7	8	200 000	1	320	870 000
17	四川攀枝花	6.1	1	7	8	7 455	3	121	130 311
18	四川凉山	6.1	1	7	8	36 500	3	101	103 054
19	云南姚安	6.5	1	7	7	31 932	1	19	995 000
20	四川小金	6.6	1	7	9	86	1	50	120 000
21	云南澜沧	7.6	1	7	9	1 858 800	3	49	2 500 000
22	云南普洱	6.8	1	7	9	40 500	2	104	53 6000
23	四川炉霍	7.9	1	7	10	18 567	3	6	1 500 000
24	山西阳高	5.6	2	7	7	5 670	3	6 800	49 064
25	新疆伽师	6.8	1	8	7	7 880	3	11	445 660
26	云南漾濞	6.4	2	8	8	341 700	2	56	96 000
27	甘肃漳县	6.6	1	7	7	320 000	2	189	603 139

震级	发生时间	设防烈度	破坏烈度	住房捣毁	预报水平	人口密度/(人·km^-2)	受灾人口
1	1	0	0.5	0.352 959	0.5	1	0.919 918
0.735 294	0	0.5	0.666 667	0.515 902	0.5	0.000 909	0.429 419
0.558 824	1	1	0	0.193 636	0.5	0.006 546	0.073 456
0.558 824	1	1	0	0.196 391	1	0.009 183	0.040 245
0.470 588	0	0.5	0.666 667	0.003 97	1	0.010 91	0.051 154
0.764 706	0	0.5	0	0.002 001	0	0.000 546	0.079 845
0.735 294	0	0.5	0	0.000 443	0.5	0.011 001	0.059 843
0.588 235	0	0.5	0	0.000 438	0	0.024 002	0.434 784
0.823 529	0	0.5	0	0.007 304	0	0.000 273	0.181 394
0.441 176	0	0.25	0.333 333	0.016 446	0	0.030 821	0.096 632
0	1	0.25	0.166 667	0.000 215	0	0.031 185	0.032 214
0.705 882	0	0.5	0.666 667	0.001 568	0	0	0.003 785
0.617 647	0	0.5	0.666 667	0.002 896	0	0.001	0.003 185
0.735 294	0	0.75	0.833 333	0.039 589	0	0.272 661	0.069 649
0.647 059	0	0.5	0.833 333	0.000 261	0	0.000 546	0
0.617 647	0	0.5	0.666 667	0.107 555	0	0.029 003	0.347 335
0.470 588	0	0.5	0.666 667	0.003 965	1	0.010 91	0.051 158
0.470 588	0	0.5	0.666 667	0.019 591	1	0.009 092	0.040 244
0.588 235	0	0.5	0.5	0.0171 33	0	0.001 637	0.397 386
0.617 647	0	0.5	0.833 333	0	0	0.004 455	0.047 029
0.911 765	0	0.5	0.833 333	1	1	0.004 364	1
0.676 471	0	0.5	0.833 333	0.021 743	0.5	0.009 364	0.213 599
1	0	0.5	1	0.009 943	1	0.000 455	0.599 592
0.323 529	1	0.5	0.5	0.003 004	1	0.618 147	0.018 626
0.676 471	0	0.75	0.5	0.004 193	1	0.000 909	0.177 426
0.558 824	1	0.75	0.666 667	0.183 791	0.5	0.005	0.037 42
0.617 647	0	0.5	0.5	0.172 116	0.5	0.017 092	0.240 482