Prediction of death toll in coal mine accidents based on optimized Markov model

doi:10.16265/j.cnki.issn1003-3033.2022.04.018

Abstract

Abstract:

In order to accurately predict death toll in coal mine accidents, applicability of three prediction models was analyzed, including grey model, renewal grey model and unbiased grey model. Firstly, their prediction accuracy was analyzed by adopting posterior residual ratio, mean relative error and small error probability. Then, optimized grey model prediction results was revised with Markov model. Finally,death number of coal mine accidents from 2020 to 2022 was predicted. The results show that the interval selection of original data has a great influence on prediction accuracy, so these with better accuracy should be selected as much as possible. The unbiased grey model proves to be the best one by comparing and analyzing prediction accuracy of all three models. The unbiased grey Markov model can not only eliminate inherent deviation of grey model, but also improve prediction accuracy with an average accuracy of 93.8%.

Key words: coal mine accident, grey model, unbiased grey model, renewal grey model, markov model, projection of death toll

TANG Fei, WANG Yungang, DU Bingcheng, KONG Xiangyan. Prediction of death toll in coal mine accidents based on optimized Markov model[J]. China Safety Science Journal, 2022, 32(4): 122-128.

Figures/Tables 11

Fig.1

Fig.2

Tab.1

Tab.2

Tab.3

Tab.4

Comparison of prediction accuracy of three models

模型	$ε -$	C	小误差概率P	精度等级
灰色模型	0.079 65	0.213 74	1.00	好
维新灰色模型	0.074 46	0.224 3	1.00	好
无偏灰色模型	0.071 86	0.223 5	1.00	好

Tab.4

Tab.5

Tab.6

Fig.3

Fig.4

Tab.7

References 17

[1]	煤矿安全网. 事故快报[EB/OL].(2020-12-05). http://www.mkaq.org.
[2]	YE Jing, DANG Yaoguo, LI Bingjun. Grey-Markov prediction model based on background value optimization and central-point triangular whitenization weight function[J]. Communications in Nonlinear Science and Numerical Simulation, 2018, 54:320-330. doi: 10.1016/j.cnsns.2017.06.004
[3]	RATHNAVAKA R, SENEVIRATNA D. Taylor series approximation and unbiased GM(1,1) based hybrid statistical approach for forecasting daily gold price demands[J]. Grey Systems: Theory and Application, 2019, 9(1):5-18. doi: 10.1108/GS-08-2018-0032
[4]	SAMET H, MOJALLAL A. Enhancement of electric arc furnace reactive power compensation using Grey-Markov prediction method[J]. Generation Transmission & Distribution Iet, 2014, 8(9):1626-1636. doi: 10.1049/iet-gtd.2013.0698
[5]	GOVINDAN K, RAMALINGAM S, BROUMI S. Traffic volume prediction using intuitionistic fuzzy Grey-Markov model[J]. Neural Computing and Applications, 2021, 33(19):1-16. doi: 10.1007/s00521-020-05444-y
[6]	徐建新, 杨杰. 煤矿百万吨死亡率动态无偏灰色马尔科夫预测[J]. 中国安全科学学报, 2012, 22(3):122-127.
	XU Jianxin, YANG Jie. Application of dynamic unbiased grey Markov model prediction of death rate per million-tons coal[J]. China Safety Science Journal, 2012, 22(3):122-127.
[7]	熊祖强, 王晓蕾. 矿井相对瓦斯涌出量动态无偏灰色马尔科夫预测[J]. 安全与环境学报, 2015, 15(3):15-18.
	XIONG Zuqiang, WANG Xiaolei. Application of the Markov bias-free dynamic gray model for the relative gas gush_out rate predict[J]. Journal of Safety and Environment, 2015, 15(3):15-18.
[8]	路倩, 王亚飞, 杨玲, 等. 基于等维新息灰色马尔科夫的地铁客流量预测[J]. 中国安全生产科学技术, 2021, 17(1):54-60.
	LU Qian, WANG Yafei, YANG Ling, et al. Prediction of subway passenger flow based on equal dimension new information grey Markov model[J]. China Safety Science and Technology, 2021, 17(1):54-60.
[9]	赵振武, 麻建军. 基于灰色马尔科夫模型的机场安检危险品数量预测[J]. 安全与环境学报, 2017, 17(1):51-53.
	ZHAO Zhenwu, MA Jianjun. Prediction of the amount of dangerous goods to be inspected by the airport security department via grey Markov model[J]. Journal of safety and environment, 2017, 17(1):51-53.
[10]	冯源, 业明达. 一种状态区间取值修正的灰色-马尔科夫链预测模型研究[J]. 测绘地理信息, 2021, 46(4):65-68.
	FENG Yuan, YE Mingda. Research on a Grey-Markov chain prediction model based on the range correction of state interval[J]. Geoinformation of Surveying, Mapping, 2021, 46(4):65-68.
[11]	刘玉洁, 毛倩, 管佩霞, 等. 灰色马尔科夫模型在湖北新冠肺炎出院人数预测中的应用[J]. 中国卫生统计, 2021, 38(3):332-335,339.
	LIU Yujie, MAO Qian, GUAN Peixia, et al. The application of grey Markov model in forecasting the number of discharged patients with novel coronavirus in Hubei province[J]. Chinese Health Statistics, 2021, 38(3):332-335,339.
[12]	马景, 武周虎, 邹艳均, 等. 基于灰色马尔科夫模型的南四湖水质预测[J]. 水资源保护, 2021, 37(5):153-158.
	MA Jing, WU Zhouhu, ZHOU Yanjun, et al. Water quality prediction of Nansi Lake based on grey Markov model[J]. Water Resources Protection, 2021, 37(5):153-158.
[13]	徐志胜, 姜学鹏. 安全系统工程(第3版)[M]. 北京: 机械工业出版社, 2016:192-198.
[14]	黄继广, 马汉鹏, 范春姣, 等. 我国煤矿安全事故统计分析及预测[J]. 陕西煤炭, 2020, 39(3):34-39,6.
	HUANG Jiguang, MA Hanpeng, FAN Chunjiao, et al. Statistic analysis and prediction of coal mine safety accidents in China[J]. Shaanxi Coal, 2020, 39(3):34-39,6.
[15]	李贤功, 万猛, 周晶, 等. 我国煤矿事故死亡人数组合预测及行业比较[J]. 矿业安全与环保, 2015, 42(4):109-112.
	LI Xiangong, WAN Meng, ZHOU Jing, et al. Combination prediction of coal mine fatalities and industry comparison in China[J]. Mining Safety and Environmental Protection, 2015, 42(4):109-112.
[16]	1949—2018全国煤矿死亡人数、百万吨死亡率[EB/OL].(2019-05-22). http://www.yte1.com/coal-pr.
[17]	国家矿山安全监察局:2020年全国煤矿无重特大瓦斯事故[EB/OL].(2021-01-08). https://www.chinamine-safety.gov.cn/.

预测精度等级	P	c
好	P >0.95	c<0.35
合格	0.95≥P >0.8	0.35≤c<0.5
勉强	0.8≥P >0.7	0.5≤c<0.65
不合格	P≤0.7	c≥0.65

年份	死亡人数	灰色模型	无偏灰色模型	维新灰色模型
2008	3 215	3 215	3 215	3 215
2009	2 631	2 826	2 777	2 630
2010	2 433	2 242	2 201	2 346
2011	1 973	1 778	1 743	1 814
2012	1 384	1 410	1 381	1 402
2013	1 067	1 118	1 094	1 084
2014	931	887	867	838
2015	588	704	687	648
2016	538	558	544	501
2017	375	443	431	387
2018	333	351	342	299
2019	316	278	271	231

年份	死亡人数	无偏灰色模型	相对误差	状态
2008	3 215	3 215	1	E₂
2009	2 631	2 777	1.056	E₃
2010	2 433	2 201	0.905	E₁
2011	1 973	1 743	0.883	E₁
2012	1 384	1 381	0.998	E₂
2013	1 067	1 094	1.025	E₂
2014	931	867	0.931	E₁
2015	588	687	1.168	E₃
2016	538	544	1.011	E₂
2017	375	431	1.149	E₃
2018	333	342	1.027	E₂
2019	316	271	0.858	E₁

年份	死亡人数	无偏灰色马尔可夫模型预测值
2008	3 215	3 215
2009	2 631	2 777
2010	2 433	2 201
2011	1 973	1 743
2012	1 384	1 381
2013	1 067	1 094
2014	931	867
2015	588	664
2016	538	544
2017	375	416
2018	333	342
2019	316	301

模型	2020年	2021年	2022年
维新灰色模型	187	145	112
无偏灰色马尔可夫模型	214	170	135