Entropy weight-normal cloud model for water inrush risk prediction of coal seam floor

doi:10.16265/j.cnki.issn1003-3033.2022.S1.0445

Abstract

Abstract:

In order to overcome the uncertainty and ambiguity in the risk classification, an entropy weight-normal cloud model was put forward for the risk classification prediction of floor water inrush in the coal seam. Thirteen influencing factors were selected to construct the evaluation index system, and the weights of each index were obtained by the EWM. The comprehensive uncertainty was calculated using the normal cloud model, and the prediction results were obtained. Fourteen geological blocks in the Feicheng mining area were used as test samples to detect them. The results show that the forecast of the model is basically in line with the actual situation, and it has advantages over AHP in forecast accuracy and error, with the accuracy increased by 7.14%. MAE, MSE, MAPE and RMSE are reduced by 0.21, 0.35, 0.069 and 0.27, respectively.

Key words: floor water invasion, entropy weight method (EWM), normal cloud model, hierarchical prediction, hazard level

MA Tianxing, LIN Yun, ZHOU Xiaobin, WEI Peirong, LI Renzong, SU Jiayu. Entropy weight-normal cloud model for water inrush risk prediction of coal seam floor[J]. China Safety Science Journal, 2022, 32(S1): 171-177.

Figures/Tables 8

Tab.1

Tab.2

Fig.1

Fig.2

Tab.3

Tab.4

Fig.3

Tab.5

References 15

[1]	李忠辉, 马云波, 郑安琪, 等. 掘进工作面突出危险性预测及危险区可视化研究[J]. 中国安全科学学报, 2020, 30(11): 53-59. doi: 10.16265/j.cnki.issn 1003-3033.2020.11.008
	LI Zhonghui, MA Yunbo, ZHENG Anqi, et al. Research on outburst risk prediction and visualization of dangerous zone in driving face[J]. China Safety Science Journal, 2020, 30(11): 53-59. doi: 10.16265/j.cnki.issn 1003-3033.2020.11.008
[2]	肖建于, 童敏明, 姜春露. 基于模糊证据理论的煤层底板突水量预测[J]. 煤炭学报, 2012, 37(增1): 131-137.
	XIAO Jianyu, TONG Minming, JIANG Chunlu. Prediction of water inrush quantity from coal floor based on fuzzy evidence theory[J]. Journal of China Coal Society, 2012, 37(S1): 131-137.
[3]	魏大勇, 王飞, 许进鹏, 等. 基于分形与模糊综合评价法的矿井突水危险性评价[J]. 煤矿安全, 2013, 44(8): 184-186.
	WEI Dayong, WANG Fei, XU Jinpeng, et al. Risk evaluation of mine water inrush based on the fractal and fuzzy comprehensive evaluation method[J]. Safety in Coal Mines, 2013, 44(8): 184-186.
[4]	王心义, 姚孟杰, 张建国, 等. 基于改进AHP法与模糊可变集理论的煤层底板突水危险性评价[J]. 采矿与安全工程学报, 2019, 36(3): 558-565.
	WANG Xinyi, YAO Mengjie, ZHANG Jianguo, et al. Evaluation of water bursting in coal seam floor based on improved AHP and fuzzy variable set theory[J]. Journal of Mining & Safety Engineering 2019, 36(3): 558-565.
[5]	施龙青, 张荣遨, 徐东晶, 等. 基于GWO-Elman神经网络的底板突水预测[J]. 煤炭学报, 2020, 45(7): 2 455-2 463.
	SHI Longqing, ZHANG Rong'ao, XU Dongjing, et al. Prediction of water inrush from floor based on GWO-Elman neural network[J]. Journal of China Coal Society, 2020, 45(7): 2 455-2 463.
[6]	陈建平, 王春雷, 王雪冬. 基于CNN神经网络的煤层底板突水预测[J]. 中国地质灾害与防治学报, 2021, 32(1): 50-57.
	CHEN Jianping, WANG Chunlei, WANG Xuedong. Coal mine floor water inrush prediction based on CNN neural network[J]. The Chinese Journal of Geological Hazard and Control, 2021, 32(1): 50-57.
[7]	LI Yanhui, BAI Jianbiao, YAN Wei, et al. Risk early warning evaluation of coal mine water inrush based on complex network and its application[J]. Advances in Civil Engineering, 2021,DOI: 10.1155/2021/9980948. doi: 10.1155/2021/9980948
[8]	ZHOU Rongyi, LIU Aiqun, LI Shuqing. Study on the non-linear forecast method for water inrush from coal seam floor based on wavelet neural network[J]. Journal of China Coal Society, 2007, 13(1): 44-48.
[9]	王景春, 林佳秀, 靳俊中. 基于云模型的隧道突水突泥风险评估[J]. 铁道标准设计, 2019, 63(3): 100-104,142.
	WANG Jingchun, LIN Jiaxiu, JIN Junzhong. Risk assessment of water gushing and mud bursting in tunnels based on cloud model[J]. Railway Standard Design, 2019, 63(3): 100-104,142.
[10]	尹会永, 周鑫龙, 郎宁, 等. 基于SSA优化的GA-BP神经网络煤层底板突水预测模型与应用[J]. 煤田地质与勘探, 2021, 49(6): 175-185.
	YIN Huiyong, ZHOU Xinlong, LANG Ning, et al. Prediction model of water inrush from coal floor based on GA-BP neural network optimized by SSA and its application[J]. Coal Geology & Exploration, 2021, 49(6): 175-185.
[11]	BO Fang. Method for quickly identifying mine water inrush using convolutional neural network in coal mine safety mining[J]. Wireless Personal Communications, 2021,DOI: 10.1007/s11277-021-08452-w. doi: 10.1007/s11277-021-08452-w
[12]	李德毅, 孟海军, 史雪梅. 隶属云和隶属云发生器[J]. 计算机研究与发展, 1995, 32(6): 15-20.
	LI Deyi, MENG Haijun, SHI Xuemei. Membership clouds and membership cloud generators[J]. Journal of Computer Research and Development, 1995, 32(6): 15-20.
[13]	龚艳冰. 基于正态云模型和熵权的河西走廊城市化生态风险综合评价[J]. 干旱区资源与环境, 2012, 26(5): 169-174.
	GONG Yanbing. Comprehensive assessment on ecological risk of Hexi corridor urbanization based on normal cloud model and entropy weight[J]. Journal of Arid Land Resources and Environment, 2012, 26(5): 169-174.
[14]	王迎超, 靖洪文, 张强, 等. 基于正态云模型的深埋地下工程岩爆烈度分级预测研究[J]. 岩土力学, 2015, 36(4): 1 189-1 194.
	WANG Yingchao, JING Hongwen, ZHANG Qiang, et al. A normal cloud model-based study of grading prediction of rockburst intensity in deep underground engineering[J]. Rock and Soil Mechanics, 2015, 36(4): 1 189-1 194.
[15]	叶世雄, 贾明涛, 潘传鹏, 等. 基于未确知测度理论的煤层底板突水危险性评价[J]. 安全与环境学报, 2015, 15(1): 26-30.
	YE Shixiong, JIA Mingtao, PAN Chuanpen, et al. New assessment model for water-inrush hazard from the coal seam floor based on the fuzzy theory measurement[J]. Journal of Safety and Environment, 2015, 15(1): 26-30.

危险性等级	地质构造条件		水文地质条件	底板隔水层条件			开采条件
危险性等级	S₁/(条·km^-2)	S₃/%	S₅/MPa	S₉/m	S₁₀/MPa	S₁₁/(条·m^-3)	S₁₂/m	S₁₃/m
Ⅰ级	>3	>50	>3	<30	<1	>20	>3	>800
Ⅱ级	2~3	30~50	2~3	30~50	1~2	10~20	2~3	600~800
Ⅲ级	1~2	10~30	1~2	50~70	2~3	3~10	1~2	400~600
Ⅳ级	<1	<10	<1	>70	>3	<3	<1	<400

危险性等级	赋值	地质构造条件		水文地质条件
危险性等级	赋值	S₂	S₄	S₆	S₇	S₈
Ⅰ级	1	明显	发育	高	发育	强
Ⅱ级	2	较明显	较发育	较高	较发育	较强
Ⅲ级	3	较不明显	发育中等	中	发育中等	较弱
Ⅳ级	4	不明显	发育较差	低	发育较差	弱

样本	地质构造参数				水文地质参数				底板隔水层参数			开采参数		预测结果	AHP 结果	实际级别
样本	S₁	S₂	S₃	S₄	S₅	S₆	S₇	S₈	S₉	S₁₀	S₁₁	S₁₂	S₁₃	Ⅰ	Ⅰ	Ⅰ
1	2.56	1	60	1	2.85	1	1	1	29.7	2.6	7.09	1.5	300	Ⅱ	Ⅱ	Ⅱ
2	2.56	1	19	1	2.5	2	1	1	29.7	2.6	7.09	1.75	300	Ⅱ	Ⅰ	Ⅱ
3	1.35	3	50	1	2.52	1	2	1	30.7	1.75	3.8	2	400	Ⅱ	Ⅱ	Ⅱ
4	1.35	3	10	1	2.55	1	2	1	30.7	1.75	3.8	2	500	Ⅲ	Ⅲ	Ⅲ
5	1.35	3	10	2	2.95	2	3	3	35	1.75	4	2.15	500	Ⅰ	Ⅱ	Ⅱ
6	2	1	20	2	2.45	1	1	1	33	2.1	6	2	100	Ⅲ	Ⅲ	Ⅲ
7	1.9	3	15	2	2.25	1	3	3	35	2.1	7.1	1.75	600	Ⅲ	Ⅰ	Ⅱ
8	1.82	2	18	2	1.65	2	1	1	33.4	2.1	6.9	1.75	190	Ⅲ	Ⅱ	Ⅱ
9	1.78	2	17	2	1.9	2	3	2	33.4	2.1	7.1	2	560	Ⅲ	Ⅲ	Ⅲ
10	0.5	2	16	2	1.8	2	3	3	35	2.1	7.1	1.2	300	Ⅲ	Ⅳ	Ⅲ
11	0.55	3	10	3	1.6	3	3	3	32	2.1	10.5	2.05	800	Ⅲ	Ⅲ	Ⅱ
12	1.53	1	10	1	0.9	2	2	1	42	1.33	10.5	1.5	400	Ⅲ	Ⅰ	Ⅲ
13	0.4	3	40	1	1.25	1	3	3	30.9	1.33	8.04	1.5	1 060	Ⅲ	Ⅰ	Ⅱ
14	1.72	2	15	1	1.2	3	1	1	33	1.33	8.04	1.5	160	Ⅰ	Ⅰ	Ⅰ

模型	MAE	MSE	MAPE	RMSE
云模型	0.29	0.29	0.145	0.53
AHP	0.50	0.64	0.214	0.80