煤与瓦斯突出危险性预测

李燕; 南新元; 蔺万科

doi:10.13272/j.issn.1671-251x.2021070072

煤与瓦斯突出危险性预测

doi: 10.13272/j.issn.1671-251x.2021070072

新疆大学电气工程学院, 新疆乌鲁木齐　830047

基金项目: 新疆维吾尔自治区自然科学基金项目（2019D01C079）。

详细信息

作者简介:
李燕（1996−），女，新疆伊犁人，硕士研究生，主要研究方向为信息融合技术，E-mail：yan_li_niyani@163.com

通讯作者:
南新元（1967−），男，新疆乌鲁木齐人，教授，硕士，硕士研究生导师，主要研究方向为流程工业系统控制与优化，E-mail：xynan@xju.edu.cn

中图分类号: TD713
计量
- 文章访问数: 177
- HTML全文浏览量: 89
- PDF下载量: 21
- 被引次数: 0
出版历程
- 收稿日期: 2021-07-26
- 修回日期: 2022-01-21
- 网络出版日期: 2022-03-05

Risk prediction of coal and gas outburst

School of Electrical Engineering, Xinjiang University, Urumqi 830047, China

摘要

摘要: 针对现有基于支持向量机(SVM)的煤与瓦斯突出预测方法存在准确率低与响应速度慢的问题，提出了一种基于改进灰狼算法(IGWO)优化SVM的煤与瓦斯突出危险性预测方法。采用灰色关联熵权法分析各个影响因素对煤与瓦斯突出的影响程度，根据关联度排序提取瓦斯压力、瓦斯含量、瓦斯放散初速度和开采深度作为煤与瓦斯突出主控因素，将其分为训练集和测试集，并进行归一化处理；为改善传统灰狼算法（GWO）种群易陷入局部最优和寻优速度慢的缺陷，引入越界处理机制和嵌入莱维飞行的随机差分变异策略对GWO算法进行改进（即IGWO），有效提升了GWO的收敛精度与速度；采用IGWO对SVM的核心参数和惩罚参数进行优化，将煤与瓦斯突出的主控因素输入到IGWO−SVM中进行分类，并将其与实际测试集分类结果进行对比，实现煤与瓦斯突出危险性预测。仿真结果表明：与基于鲸鱼算法−支持向量机(WOA−SVM)、灰狼算法−支持向量机(GWO−SVM)和粒子群−支持向量机(PSO−SVM)的预测方法相比，基于IGWO−SVM的预测方法具有更高的预测精度，在提高SVM运算效率的同时满足煤与瓦斯突出预测的精度和可靠性要求，准确率达到96.67%，预测速度为5.58 s。
- 煤与瓦斯突出 /
- 危险性预测 /
- 灰色关联熵 /
- 支持向量机 /
- 越界处理机制 /
- 莱维飞行 /
- 灰狼算法
Abstract: In order to solve the problems of low accuracy and slow response speed of existing support vector machine (SVM)-based coal and gas outburst prediction methods, a risk prediction method of coal and gas outburst based on improved grey wolf optimizer (IGWO) optimized SVM is proposed. The influence degree of each influencing factor on coal and gas outburst is analyzed by using the grey relational entropy weight method, and gas pressure, gas content, initial gas diffusion speed and mining depth are extracted as main control factors of coal and gas outburst according to the correlation degree order, and the main control factors are divided into a training set and a test set, and normalized. In order to improve the defects of the traditional grey wolf optimizer (GWO) population easily falling into local optimum and slow optimization speed, the out-of-bounds processing mechanism and the random difference mutation strategy embedded in Levy flight are introduced to improve the grey wolf optimizer (ie IGWO), so as to improve the convergence precision and speed of GWO effectively. The core parameters and penalty parameters of SVM are optimized by IGWO, and the main control factors of coal and gas outburst are input into IGWO-SVM for classification. And the classification results are compared with the actual test set so as to realize the risk prediction of coal and gas outburst. The simulation results show that compared with the prediction methods based on whale optimization algorithm-SVM ( WOA-SVM), grey wolf optimizer-SVM ( GWO-SVM) and particle swarm optimization-SVM ( PSO-SVM), the prediction method based on IGWO-SVM has higher prediction precision, and can meet the precision and reliability requirements of coal and gas outburst prediction while improving the operation efficiency of SVM. The accuracy rate reaches 96.67% and the prediction speed is 5.58 s.
- coal and gas outburst /
- risk prediction /
- grey relational entropy /
- support vector machine /
- out-of-bounds processing mechanism /
- Levy flight /
- grey wolf algorithm

HTML全文

图 1 Sphere函数优化曲线

Figure 1. Sphere function optimization curves

下载: 全尺寸图片幻灯片

图 2 Griewank函数优化曲线

Figure 2. Griewank function optimization curves

下载: 全尺寸图片幻灯片

图 3 IGWO−SVM预测流程

Figure 3. Prediction process of IGWO-SVM

下载: 全尺寸图片幻灯片

图 4 GWO−SVM预测结果

Figure 4. Prediction result of GWO-SVM

下载: 全尺寸图片幻灯片

图 7 PSO−SVM预测结果

Figure 7. Prediction result of PSO-SVM

下载: 全尺寸图片幻灯片

图 5 IGWO−SVM预测结果

Figure 5. Prediction result of IGWO-SVM

下载: 全尺寸图片幻灯片

图 6 WOA−SVM预测结果

Figure 6. Prediction result of WOA-SVM

下载: 全尺寸图片幻灯片

图 8 4种算法预测时间对比

Figure 8. Comparison of prediction time of four algorithms

下载: 全尺寸图片幻灯片

表 1 部分样本数据

Table 1. Part of sample data

序号	G₁/MPa	${G_2}/({{\rm{m}}^3} \cdot {{\rm{t}}^{ - 1} })$	G₃/mmHg	G₄	G₅	G₆/ｍ	突出危险性
1	0.451	9.639	18.407	0.491	Ⅰ	556.884	1
2	0.461	9.131	18.039	0.499	Ⅲ	535.376	2
3	0.730	12.230	18.485	0.463	Ⅰ	546.180	1
4	2.302	17.366	18.918	0.381	Ⅱ	557.050	3
5	0.670	9.690	12.836	0.582	Ⅱ	499.971	2
							
86	0.797	9.797	17.078	0.488	Ⅱ	482.869	1
87	1.282	12.095	9.079	0.612	Ⅱ	613.958	2
88	1.187	12.291	18.703	0.408	Ⅲ	605.029	2
89	0.806	12.148	19.909	0.498	Ⅰ	565.645	2
90	2.197	16.776	19.019	0.378	Ⅲ	556.155	3

下载: 导出CSV

表 2 灰色关联度

Table 2. Grey relation degree

影响因素	平均灰色关联度	加权灰色关联度	关联度顺序
G₁	0.709 3	0.149 1	3
G₂	0.673 2	0.138 5	4
G₃	0.711 5	0.150 6	2
G₄	0.620 9	0.119 4	6
G₅	0.654 4	0.130 6	5
G₆	0.714 2	0.152 9	1

下载: 导出CSV

参考文献(21)

[1]	李长兴,关金锋,李回贵,等. 煤与瓦斯突出预测的Bayes−逐步判别分析模型及应用[J]. 中国矿业,2020,29(2):117-123. LI Changxing,GUAN Jinfeng,LI Huigui,et al. Bayes stepwise discriminant analysis model and application of coal and gas outburst prediction[J]. China Mining Magazine,2020,29(2):117-123.
[2]	舒龙勇,王凯,齐庆新,等. 煤与瓦斯突出关键结构体致灾机制[J]. 岩石力学与工程学报,2017,36(2):347-356. SHU Longyong,WANG Kai,QI Qingxin,et al. Key structural body theory of coal and gas outburst[J]. Chinese Journal of Rock Mechanics and Engineering,2017,36(2):347-356.
[3]	付华,丰胜成,高振彪,等. 基于双耦合算法的煤与瓦斯突出预测模型[J]. 中国安全科学学报,2018,28(3):84-89. FU Hua,FENG Shengcheng,GAO Zhenbiao,et al. Study on double coupling algorithm based model for coal and gas outburst prediction[J]. China Safety Science Journal,2018,28(3):84-89.
[4]	LIU Haibo,DONG Yujie,WANG Fuzhong,et al. Gas outburst prediction model using improved entropy weight grey correlation analysis and IPSO-LSSVM[J]. Mathematical Problems in Engineering,2020,152:63-72.
[5]	WU Yaqin,GAO Ronglei,YANG Jinzhen. Prediction of coal and gas outburst: a method based on the BP neural network optimized by GASA[J]. Process Safety and Environmental Protection,2019,133:64-72.
[6]	郑晓亮,来文豪,薛生. MI和SVM算法在煤与瓦斯突出预测中的应用[J]. 中国安全科学学报,2021,31(1):75-80. ZHENG Xiaoliang,LAI Wenhao,XUE Sheng. Application of MI and SVM in coal and gas outburst prediction[J]. China Safety Science Journal,2021,31(1):75-80.
[7]	韩永亮,李胜,胡海永,等. 基于改进的GA−ELM煤与瓦斯突出预测模型[J]. 地下空间与工程学报,2019,15(6):1895-1902. HAN Yongliang,LI Sheng,HU Haiyong,et al. Prediction model of coal and gas outburst based on optimized GA-ELM[J]. Chinese Journal of Underground Space and Engineering,2019,15(6):1895-1902.
[8]	温廷新,于凤娥,邵良杉. 基于灰色关联熵的煤与瓦斯突出概率神经网络预测模型[J]. 计算机应用研究,2018,35(11):3326-3329. WEN Tingxin,YU Feng'e,SHAO Liangshan. Probabilistic neural network prediction model of coal and gas outburst based on grey relational entropy[J]. Application Research of Computers,2018,35(11):3326-3329.
[9]	吴雅琴,李惠君,徐丹妮. 基于IPSO−Powell优化SVM的煤与瓦斯突出预测算法[J]. 工矿自动化,2020,46(4):46-53. WU Yaqin,LI Huijun,XU Danni. Prediction algorithm of coal and gas outburst based on IPSO-Powell optimized SVM[J]. Industry and Mine Automation,2020,46(4):46-53.
[10]	BIAN Xiaoqiang,ZHANG Qian,ZHANG Lu,et al. A grey wolf optimizer-based support vector machine for the solubility of aromatic compounds in supercritical carbon dioxide[J]. Chemical Engineering Research and Design,2017,123:284-294. doi: 10.1016/j.cherd.2017.05.008
[11]	冯璋,裴东,王维. 基于改进灰狼算法优化支持向量机的人脸识别[J]. 计算机工程与科学,2019,41(6):1057-1063. FENG Zhang,PEI Dong,WANG Wei. Face recognition by support vector machine optimized by an improved grey wolf algorithm[J]. Computer Engineering & Science,2019,41(6):1057-1063.
[12]	陈闯,RYAD Chellali,邢尹. 改进GWO优化SVM的语音情感识别研究[J]. 计算机工程与应用,2018,54(16):113-118. CHEN Chuang,RYAD Chellali,XING Yin. Research on speech emotion recognition based on improved GWO optimization SVM[J]. Computer Engineering and Applications,2018,54(16):113-118.
[13]	王志华,罗齐,刘绍廷. 基于混沌灰狼优化算法的SVM分类器研究[J]. 计算机工程与科学,2018,40(11):2040-2046. WANG Zhihua,LUO Qi,LIU Shaoting. A SVM classifier based on chaotic gray wolf optimization algorithm[J]. Computer Engineering & Science,2018,40(11):2040-2046.
[14]	郑直,张华钦,潘月. 基于改进鲸鱼算法优化LSTM的滚动轴承故障诊断[J]. 振动与冲击,2021,40(7):274-280. ZHENG Zhi,ZHANG Huaqin,PAN Yue. Rolling bearing fault diagnosis based on IWOA-LSTM[J]. Journal of Vibration and Shock,2021,40(7):274-280.
[15]	LIU Haibo,DONG Yujie,WANG Fuzhong. Gas outburst prediction model using rough set and support vector machine[J]. Evolutionary Intelligence,2020,7:1-9.
[16]	ZHANG Chaolin,WANG Enyuan,XU Jiang,et al. A new method for coal and gas outburst prediction and prevention based on the fragmentation of ejected coal[J]. Fuel,2021,287:1-10.
[17]	李冬,彭苏萍,杜文凤,等. 煤层瓦斯突出危险区综合预测方法[J]. 煤炭学报,2018,43(2):466-472. LI Dong,PENG Suping,DU Wenfeng,et al. Comprehensive prediction method of coal seam gas outburst danger zone[J]. Journal of China Coal Society,2018,43(2):466-472.
[18]	陈恋,袁梅,高强,等. 主成分−费歇尔判别模型在煤与瓦斯突出等级预测中的应用[J]. 工矿自动化,2020,46(3):55-62. CHEN Lian,YUAN Mei,GAO Qiang,et al. Application of principal component-Fisher discrimination model in grade prediction of coal and gas outburst[J]. Industry and Mine Automation,2020,46(3):55-62.
[19]	李映洁. 多源信息融合技术在煤与瓦斯突出预测中的应用研究[D]. 徐州: 中国矿业大学, 2018. LI Yingjie. Study on the application of multi-source information fusion technology in the coal and gas outburst prediction[D]. Xuzhou: China University of Mining and Technology, 2018.
[20]	李杰. 煤与瓦斯突出IGSA−SVM预测模型及其应用[D]. 太原: 太原理工大学, 2016. LI Jie. Coal and gas outburst IGSA-SVM prediction model and its application[D]. Taiyuan: Taiyuan University of Technology, 2016.
[21]	朱政江. 基于神经网络和粒子群优化SVM的煤与瓦斯突出预测模型研究[D]. 太原: 太原理工大学, 2014. ZHU Zhengjiang. Research of coal and gas outburst prediction models based on neural network and PSO-SVM [D]. Taiyuan: Taiyuan University of Technology, 2014.