MI和SVM算法在煤与瓦斯突出预测中的应用

doi:10.16265/j.cnki.issn 1003-3033.2021.01.011

中国安全科学学报 ›› 2021, Vol. 31 ›› Issue (1): 75-80.doi: 10.16265/j.cnki.issn 1003-3033.2021.01.011

MI和SVM算法在煤与瓦斯突出预测中的应用

郑晓亮^1,2 教授, 来文豪², 薛生^1,3 教授

1 安徽理工大学深部煤矿采动响应与灾害防控国家重点实验室,安徽淮南 232001;
2 安徽理工大学电气与信息工程学院,安徽淮南 232001;
3 安徽理工大学能源与安全学院,安徽淮南 232001

收稿日期:2020-10-27 修回日期:2020-12-13 出版日期:2021-01-28 发布日期:2021-07-28
作者简介:郑晓亮 (1979—),男,安徽淮南人,博士,教授,主要从事煤矿安全监测与监控方面的研究。E-mail:zhengxl@aust.edu.cn。
基金资助:
“十三五”国家重点研发计划项目(2018YFC0808000)。

Application of MI and SVM in coal and gas outburst prediction

ZHENG Xiaoliang^1,2, LAI Wenhao², XUE Sheng^1,3

1 State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines, Anhui University of Science and Technology, Huainan Anhui 232001, China;
2 School of Electric and Information Engineering, Anhui University of Science and Technology, Huainan Anhui 232001, China;
3 School of Mining and Safety Engineering, Anhui University of Science and Technology, Huainan Anhui 232001, China

Received:2020-10-27 Revised:2020-12-13 Online:2021-01-28 Published:2021-07-28

摘要/Abstract

摘要： 为解决能用于煤与瓦斯突出预测模型的真实事故训练数据量小、数据集缺失严重的问题,提出采用数据挖掘多重填补(MI)算法填补事故数据中缺失参数,增大可用数据集,并将填补后的数据用于支持向量机(SVM)预测模型的训练与测试,选取K最近邻 (KNN) 算法与SVM进行对比。结果表明:SVM数据填补前后的平均识别率分别为88.37%和88.87%,事故数据的识别率分别79.71%和91.27%;KNN算法在数据填补前后,平均识别率分别为87.59%和88.37%,事故识别率分别为70.4%和84.23%;可见:MI对平均识别率的提升作用不大,对事故识别率的提升作用显著,可提高煤与瓦斯突出事故预测率,数据填补后SVM算法比KNN算法的事故识别率高。

关键词: 多重填补(MI), 支持向量机(SVM), 煤与瓦斯突出, 预测, 事故识别率

Abstract: In order to address problems of small quantity of accidents training data and lack of data set that can be used in coal and gas outburst prediction model, MI data mining algorithm was presented to fill up missing parameters in accident data and increase available data sets. Then, imputed data were employed in SVM prediction model's training and testing, and K-Nearest Neighbors (KNN) algorithm was selected and compared with SVM. The results show that the average recognition rate of SVM algorithm is 88.37% and 88.87% before and after data inputting respectively, and recognition rate of accident data is 79.71% and 91.27% respectively. That of KNN algorithm before and after data inputting is 87.59% and 88.37% respectively while accident recognition rate being 70.4% and 84.23%, respectively. Therefore, MI has little effect on improving average recognition rate, but has a greater one on improving accident recognition rate, which can improve prediction rate of coal and gas outburst accidents. The incident recognition rate of SVM algorithm is higher than that of KNN algorithm after data inputting.

Key words: multiple imputation (MI), support vector machine (SVM), coal and gas outburst, prediction, accident recognition rate

中图分类号:

X936

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.

参考文献

[1] 袁亮,薛生.煤层瓦斯含量法预测煤与瓦斯突出理论与技术[M].北京:科学出版社,2014:22.
[2] 煤矿安全网.2019年11月25日,贵州三甲煤矿发生煤与瓦斯突出事故共造成7人死亡,1人获救[EB/OL].(2019-11-25).http://www.mkaq.org/html/2019/11/25/503800.shtml.
[3] 新华社.2019年12月17日凌晨1点,贵州省安龙县发生煤矿事故致16人死亡,搜救结束[EB/OL].(2019-12-17).http://www.mkaq.org/html/2019/12/17/507067.shtml.
[4] 谢国民, 谢鸿, 付华,等. 煤与瓦斯突出预测的NN-SVM模型[J]. 传感技术学报, 2016, 29(5): 733-738.
XIE Guomin, XIE Hong, FU Hua, et al. Prediction model for coal and gas outburst based on NN-SVM[J]. Chinese Journal of Sensors and Actuators, 2016, 29(5): 733-738.
[5] 郑晓亮.基于瓦斯含量法的煤与瓦斯突出预测关键技术研究[D].淮南:安徽理工大学,2018,.
ZHENG Xiaoliang.Research on key technology of coal and gas outburst prediction based on gas content method[D].Huainan:Anhui University of Science and Technology,2018.
[6] 李定启, 程远平, 王海峰,等. 基于决策树ID3改进算法的煤与瓦斯突出预测[J]. 煤炭学报, 2011, 36(4): 619-622.
LI Dingqi, CHENG Yuanping, WANG Haifeng, et al. Coal and gas outburst prediction based on improved decision tree ID3 algorithm[J].Journal of China Coal Society, 2011,36(4): 619-622.
[7] 肖红飞, 何学秋, 刘黎明. 改进BP算法在煤与瓦斯突出预测中的应用[J]. 中国安全科学学报, 2003, 13(9): 59-61.
XIAO Hongfei, HE Xueqiu, LIU Liming. Application of modified BP neural network in predicting coal and gas outburst[J]. China Safety Science Journal, 2003, 13(9): 59-61.
[8] 任少伟. 基于PCA的PSO-DE混合算法优化BP神经网络在煤与瓦斯突出预测中的应用研究[D]太原:太原理工大学, 2015.
REN Shaowei. The application study of BP neural network based on PSO-DE hybrid algorithm of PCA algorithm in the prediction of coal and methne outburst [D].Taiyuan: Taiyuan University of Technology, 2015.
[9] 杨敏,汪云甲,李瑞霞.煤与瓦斯突出强度预测的IGABP方法[J].重庆大学学报,2010,33(1): 113-118
YANG Min, WANG Yunjia, LI Ruixia. Prediction of coal and gas outburst intensity with incorporate genetic algorithm based back propagation neural network(IGABP)[J].Journal of Chongqing University, 2010,33(1): 113-118.
[10] 朱志洁,张宏伟,韩军,等.基于PCA-BP神经网络的煤与瓦斯突出预测研究[J].中国安全科学学报,2013,23(4): 45-50.
ZHU Zhijie, ZHANG Hongwei, HAN Jun, et al. Prediction of coal and gas outburst based on PCA-BP neural network[J]. China Safety Science Journal, 2013, 23(4): 45-50.
[11] 付华, 李海霞, 卢万杰,等. 一种改进的极限学习机煤与瓦斯突出预测模型[J]. 传感技术学报, 2016, 29(1): 69-74.
FU Hua, LI Haixia, LU Wanjie, et al. A prediction model of coal and gas outburst based on improved extreme learning machine[J]. Chinese Journal of Sensors and Actuators,2016,29(1): 69-74.
[12] 王江荣, 罗资琴, 文晖. 基于因子分析的极限学习机在煤与瓦斯突出等级识别中的应用[J]. 煤, 2014,23(11): 13-16.
WANG Jiangrong, LUO Ziqin, WEN Hui. Application of extreme learning machine based on factor analysis in the recognition of grade on coal and gas outburst[J]. Coal,2014,23(11): 13-16.
[13] RUBIN D B. Multiple imputation after 18+ years[J]. Journal of the American statistical Association, 1996, 91: 473-489.
[14] SOMVANSHI M, CHAVAN P. A review of machine learning techniques using decision tree and support vector machine[C].2016 International Conference on Computing Communication Control and automation (ICCUBEA), IEEE, 2016: 1-7.
[15] GRAY I. The mechanism of energy release associated with outbursts[C]. Proceedings of the Occurrence and Control of Outbursts in Coal Mines, 1980: 111-125.
[16] 王刚,程卫民,谢军,等.煤与瓦斯突出过程中煤体瓦斯的作用研究[J].中国安全科学学报,2010,20(9): 116-120.
WANG Gang, CHENG Weimin, XIE Jun, et al. Study on the effect of gas in the coal and gas outburst [J]. China Safety Science Journal, 2010, 20(9): 116-120.
[17] 陈鲜展,袁亮,薛生,等. 瓦斯含量法在煤与瓦斯突出能量分析中的应用[J].中国安全科学学报,2017,27(10): 93-98.
CHEN Xianzhan, YUAN Liang, XUE Sheng, et al. Energy analysis of coal and gas outburst process based on gas content method[J]. China Safety Science Journal,2017,27(10): 93-98.

MI和SVM算法在煤与瓦斯突出预测中的应用

Application of MI and SVM in coal and gas outburst prediction

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杨文臣, 周燕宁, 田毕江, 郭凤香, 胡澄宇. 基于聚类分析和SVM的二级公路交通事故严重度预测[J]. 中国安全科学学报, 2022, 32(5): 163-169.
[2]	熊晓夏, 刘擎超, 沈钰杰, 蔡英凤, 陈龙. 基于LSTM-BF的高速公路交通事故风险模型[J]. 中国安全科学学报, 2022, 32(5): 170-176.
[3]	唐飞, 王云刚, 杜炳成, 孔祥岩. 基于优化马尔可夫模型的煤矿事故死亡人数预测[J]. 中国安全科学学报, 2022, 32(4): 122-128.
[4]	张新生, 王旭业, 张莹莹, 常潆戈. 海底腐蚀管道剩余寿命预测与维修策略研究[J]. 中国安全科学学报, 2022, 32(3): 41-47.
[5]	高云骥, 罗越扬, 李智胜, 张玉春, 喻洋阳, 李涛. 分岔隧道火灾烟气回流长度及温度分布试验研究[J]. 中国安全科学学报, 2022, 32(3): 109-115.
[6]	丁茜, 赵晓东, 吴鑫俊, 张泰丽, 徐振涛. 基于RBF核的多分类SVM滑塌易发性评价模型[J]. 中国安全科学学报, 2022, 32(3): 194-200.
[7]	郑度奎, 程远鹏, 李昊燃, 何天隆. IAFSA-GRNN在油田集输管道CO₂腐蚀速率预测中的应用^*[J]. 中国安全科学学报, 2022, 32(1): 110-117.
[8]	吴孟龙, 叶义成, 胡南燕, 王其虎, 李文, 江慧敏. 基于模糊信息粒化的矿业安全生产态势区间预测^*[J]. 中国安全科学学报, 2021, 31(9): 119-127.
[9]	张新生, 蔡宝泉. 基于改进随机森林模型的海底管道腐蚀预测^*[J]. 中国安全科学学报, 2021, 31(8): 69-74.
[10]	巫诚诚, 陈大伟. 交叉口非机动车冲突易发点空间预测模型^*[J]. 中国安全科学学报, 2021, 31(8): 165-171.
[11]	赵挺生, 庞奇志, 姜雯茜. 基于数据库与支持向量机的施工升降机安全风险预测[J]. 中国安全科学学报, 2021, 31(4): 11-17.
[12]	隆能增, 袁梅, 王关亮, 王清辉, 许石青, 李鑫灵. 煤与瓦斯突出微震-瓦斯互动响应预警研究[J]. 中国安全科学学报, 2021, 31(4): 125-132.
[13]	刘雨晴, 张培红. 大坡度倾斜巷道火灾烟气温度分布特征研究[J]. 中国安全科学学报, 2021, 31(4): 156-162.
[14]	张凯, 张科, 李昆. 主元分析-神经网络岩爆等级预测模型[J]. 中国安全科学学报, 2021, 31(3): 96-104.
[15]	栗婧, 王真, 秦亚茹, 汪振, 罗江昊. 不同噪声强度对煤矿工人作业失误率的影响研究[J]. 中国安全科学学报, 2021, 31(2): 179-184.