基于SSA-RBF神经网络的煤自然发火预测模型

doi:10.16265/j.cnki.issn1003-3033.2024.08.1567

摘要/Abstract

摘要：

为解决传统煤自燃预测模型预测状态单一和预测精度不高的问题,提出基于麻雀搜索算法(SSA)优化的径向基(RBF)神经网络煤自然发火预测模型。首先,采用程序升温试验分析煤样指标气随温度的变化特征,将煤自然发火过程按煤温分为缓慢(80≤t_i<120 ℃)、加速(120≤t_i<160 ℃)和激烈(t_i≥160 ℃)3个氧化阶段,同时分析这3个阶段指标气与煤温的灰色关联度;其次通过不同维度测试函数检验粒子群算法(PSO)、灰狼算法(GWO)和SSA算法性能;最后利用6个矿区数据验证基于SSA-RBF神经网络的煤自燃预测模型的优越性。结果显示,缓慢氧化阶段CO/ΔO₂、CO、C₂H₄这3种指标气体与煤温的灰色关联系数最大;而加速氧化阶段C₂H₄/C₂H₆、CO/ΔO₂、CO₂/CO 3种指标与煤温的灰色关联系数最大。3种不同维度函数的测试结果表明:SSA与PSO、GWO相比具有更好的全局搜索能力和稳定性,其收敛速度更快;神经元数量为5个、迭代次数为300次时,SSA-RBF神经网络预测模型对缓慢氧化和加速氧化阶段的预测准确性分别达到了99%和93%。

关键词: 麻雀搜索算法(SSA), 径向基函数(RBF)神经网络, 煤自然发火, 预测模型, 指标气, 灰色关联度

Abstract:

To solve the problems of single prediction state and insufficient prediction accuracy of the traditional coal spontaneous combustion prediction model, a prediction model based on RBF neural network optimized by SSA was proposed. Firstly, the temperature programmed test was used to analyze the variation characteristics of the index gas of coal samples with temperature. The coal spontaneous combustion process was divided into slow oxidation stage (80≤t_i<120 ℃), accelerated oxidation stage (120≤t_i<160 ℃) and intense oxidation stage (t_i≥160 ℃) with coal temperature as the node. At the same time, the grey correlation degree between the index gas and coal temperature in each stage of coal spontaneous combustion was analyzed. Secondly, the performance of Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO) and SSA algorithm was tested by different dimension test functions. Finally, the superiority of the RBF neural network optimized by SSA algorithm to the coal spontaneous combustion prediction model was verified by using six mining area data. The results show that the grey correlation coefficients of CO/ΔO₂, CO and C₂H₄ with coal temperature are the largest in the slow oxidation stage. The grey correlation coefficient between C₂H₄/C₂H₆, CO/ΔO₂, CO₂/CO and coal temperature is the largest in the accelerated oxidation stage. The test results of three different dimensional functions show that SSA has better global search ability, stability and faster convergence speed compared with PSO and GWO. When the number of neurons is 5 and the number of iterations is 300, the prediction accuracy of the SSA-RBF neural network prediction model for the slow and accelerated oxidation stages reaches 99% and 93% respectively.

Key words: sparrow search algorithm (SSA), radial basis function (RBF), coal spontaneous combustion, prediction model, indicator gas, grey relational analysis

中图分类号:

X936

高飞, 梁宁, 贾喆, 侯青. 基于SSA-RBF神经网络的煤自然发火预测模型[J]. 中国安全科学学报, 2024, 34(8): 128-137.

GAO Fei, LIANG Ning, JIA Zhe, HOU Qing. Prediction model of coal spontaneous combustion based on SSA-RBF neural network[J]. China Safety Science Journal, 2024, 34(8): 128-137.

图/表 8

图1

图2

表1

图3

表2

8种测试函数

测试函数	维度	范围	理论最小值
$f 1 (x) = ∑ i = 1 n ([x i + 0.5]) 2$	30	[-100,100]	0
$f 2 (x) = ∑ i = 1 n i x i 4 + r a n d o m [0,1)$	30	[-1.28,1.28]	0
$f 3 (x) = ∑ i = 1 n - x i s i n (\| x i \|)$	30	[-500,500]	-12 569.5
$f 4 (x) = ∑ i = 1 n [x i 2 - 10 c o s (2 π x i) + 10]$	30	[-5.12,5.12]	0
$f 5 (x) = - 20 e x p - 0.2 1 n ∑ i = 1 n x i 2 - e x p 1 n ∑ i = 1 n c o s (2 π x i) + 20 + e$	30	[-32,32]	0
$f 6 (x) 14000 ∑ i = 1 n x i 2 - ∏ i = 1 n c o s (x i i) + 1$	30	[-600,600]	0
$f 7 (x) = 1500 + ∑ j = 1 25 1 j + ∑ i = 1 2 (x i - a i j) 6 - 1$	2	[-65,65]	1
$f 8 (x) = x 2 - 5.1 4 π 2 x 12 + 5 π x 1 - 6 2 + 10 1 - 1 8 π c o s x 1 + 10$	2	[-5,5]	0.398

表2

图4

图5

图6

参考文献 20

[1]	刘一鸣. 2022年煤炭行业发展年度报告[R]. 中国煤炭工业协会, 2023.
[2]	谭波, 邵壮壮, 郭岩, 等. 基于指标气关联分析的煤自燃分级预警研究[J]. 中国安全科学学报, 2021, 31(2): 33-39. doi: 10.16265/j.cnki.issn 1003-3033.2021.02.005
	TAN Bo, SHAO Zhuangzhuang, GUO Yan, et al. Research on grading and early warning of coal spontaneous combustion based on correlation analysis of index gas[J]. China Safety Science Journal, 2021, 31(2): 33-39. doi: 10.16265/j.cnki.issn 1003-3033.2021.02.005
[3]	SAHAY N, VARMAD N. Critical temperature-an approach to define proneness of coal towards spontaneous heating[J]. Journal of Mines, Metal & Fuel, 2007, 55(10/11):510-516
[4]	罗海珠, 梁运涛. 煤自然发火预测预报技术的现状与展望[J]. 中国安全科学学报, 2003, 13(3): 79-81.
	LUO Haizhu, LIANG Yuntao. Present situation and prospect of coal spontaneous combustion prediction technology[J]. China Safety Science Journal, 2003, 13(3): 79-81.
[5]	姚海飞, 张体镇, 阚国栋, 等. 典型整合矿井煤自燃标志气体判定[J]. 煤炭科学技术, 2014, 42(2): 50-53.
	YAO Haifei, ZHANG Tizhen, KAN Guodong, et al. Typical integrated mine coal spontaneous combustion sign gas determination[J]. Coal Science and Technology, 2014, 42(2): 50-53.
[6]	邓军, 李贝, 李珍宝, 等. 预报煤自燃的气体指标优选试验研究[J]. 煤炭科学技术, 2014, 42(1): 55-59.
	DENG Jun, LI Bei, LI Zhenbao, et al. Experimental study on gas index optimization for predicting coal spontaneous combustion[J]. Coal Science and Technology, 2014, 42(1): 55-59.
[7]	ITAY M, HILL C, CLASSER D, et al. A study of the low temperature oxidation of coal[J]. Fuel Processing Technology, 1989, 21(2): 81-97.
[8]	HU Wen, YU Zhijin, FAN Shixing, et al. Prediction of spontaneous combustion potential of coal in the gob area using co extreme concentration: a case study[J]. Combust Science and Technology, 2017, 189(10): 1 713-1 727.
[9]	王福生, 韩慧兰, 柳晓莉, 等. 煤自然发火预测预报模型的构建[J]. 矿业安全与环保, 2011, 38(1): 21-22.
	WANG Fusheng, HAN Huilan, LIU Xiaoli, et al. Construction of coal spontaneous combustion prediction model[J]. Mining Safety and Environmental Protection, 2011, 38(1): 21-22.
[10]	宋志, 曹坤, 孙宝铮. 采场自然发火的预测和识别[J]. 黑龙江矿业学院学报, 1996, 9(3): 23-25.
	SONG Zhi, CAO Kun, SUN Baozheng. Prediction and identification of spontaneous combustion in stope[J]. Journal of Heilongjiang Mining Institute, 1996, 9(3): 23-25.
[11]	徐杨, 周延. 煤自然发火预报的人工神经网络模型[J]. 西安科技大学学报, 2009, 29(4): 410-413.
	XU Yang, ZHOU Yan. Artificial neural network model for prediction of coal spontaneous combustion[J]. Journal of Xi'an University of Science and Technology, 2009, 29(4): 410-413.
[12]	孟倩, 王洪权, 王永胜, 等. 煤自燃极限参数的支持向量机预测模型[J]. 煤炭学报, 2009, 34(11): 1 489-1 493.
	MENG Qian, WANG Hongquan, WANG Yongsheng, et al. Support vector machine prediction model of coal spontaneous combustion limit parameters[J]. Journal of China Coal Society, 2009, 34(11): 1 489-1 493.
[13]	LI Shuang, XU Kun, XUE Guangzhe, et al. Prediction of coal spontaneous combustion temperature based on improved grey wolf optimizer algorithm and support vector regression[J]. Fuel, 2022, 324: 564-577.
[14]	陆新晓, 赵鸿儒, 朱红青, 等. 氧化煤复燃过程自燃倾向性特征规律[J]. 煤炭学报, 2018, 43(10): 2 809-2 816.
	LU Xinxiao, ZHAO Hongru, ZHU Hongqing, et al. Characteristics of spontaneous combustion tendency in reburning process of oxidized coal[J]. Journal of China Coal Society, 2018, 43(10): 2 809-2 816.
[15]	费金彪. 煤自燃阶段判定理论与分级预警方法研究[D]. 西安: 西安科技大学, 2019.
	FEI Jinbiao. Study on determination theory of coal spontaneous combustion stage and classification early warning method[D]. Xi'an: Xi'an University of Science and Technology, 2019.
[16]	杨永国, 黄福臣. 非线性方法在矿井突水水源判别中的应用研究[J]. 中国矿业大学学报, 2007, 36 (3): 283-286.
	YANG Yongguo, HUANG Fuchen. Application of nonlinear method in discrimination of mine water inrush source[J]. Journal of China University of Mining and Technology, 2007, 36(3): 283-286.
[17]	张利冬, 宋泽阳, 罗振敏, 等. 基于机器学习的煤自然发火期预测[J]. 中国安全科学学报, 2022, 32(12): 118-124. doi: 10.16265/j.cnki.issn1003-3033.2022.12.0134
	ZHANG Lidong, SONG Zeyang, LUO Zhenmin, et al. Prediction of coal spontaneous combustion period based on machine learning[J]. China Safe Science Journal, 2022, 32(12): 118-124.
[18]	张卫亮, 梁运涛, 杨宏民. CO/CO₂比值作为煤自然发火指标气体在安家岭井工矿中的应用[C]. 2008年全国煤矿安全学术年会, 2008: 180-185.
[19]	屈丽娜. 煤自燃阶段特征及其临界点变化规律的研究[D]. 北京: 中国矿业大学(北京), 2013.
	QU Li'na. Study on the characteristics of coal spontaneous combustion stage and its critical point change law[D]. Beijing: China University of Mining and Technology (Beijing), 2013.
[20]	刘奇. 基于LVQ神经网络的煤自然发火预报系统研究[D]. 唐山: 华北理工大学, 2017.
	LIU Qi. Research on coal spontaneous combustion prediction system based on LVQ neural network[D]. Tangshan: North China University of Science and Technology, 2017.

煤种	30~120 ℃							120~160 ℃
煤种	C₂H₄	C₂H₆	CO	CH₄	C₂H₄/ C₂H₆	CO₂/CO	CO/ ΔO₂	C₂H₄	C₂H₆	CO	CH₄	C₂H₄/ C₂H₆	CO₂/CO	CO/ΔO₂
两渡	0.691	0.651	0.736	0.650	0.691	0.691	0.771	0.636	0.672	0.653	0.629	0.985	0.767	0.776
高阳	0.643	0.606	0.719	0.643	0.643	0.533	0.731	0.583	0.667	0.603	0.541	0.740	0.712	0.755
柳湾	0.740	0.697	0.767	0.740	0.740	0.612	0.802	0.586	0.644	0.615	0.600	0.927	0.707	0.724
水峪	0.772	0.723	0.805	0.727	0.772	0.646	0.827	0.566	0.613	0.585	0.602	0.976	0.715	0.685
回坡底	0.689	0.646	0.725	0.648	0.689	0.557	0.756	0.573	0.650	0.592	0.638	0.871	0.690	0.689
吕临能	0.674	0.633	0.743	0.702	0.674	0.559	0.780	0.554	0.648	0.609	0.646	0.527	0.720	0.719
平均值	0.702	0.661	0.749	0.685	0.702	0.580	0.778	0.583	0.649	0.610	0.609	0.838	0.719	0.725