[1]马恒,任美学,高科.基于随机搜索优化XGBoost的瓦斯涌出量预测模型*[J].中国安全生产科学技术,2022,18(5):129-134.[doi:10.11731/j.issn.1673-193x.2022.05.020]
MA Heng,REN Meixue,GAO Ke.Prediction model of gas emission amount based on XGBoost optimized with random search algorithm[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(5):129-134.[doi:10.11731/j.issn.1673-193x.2022.05.020]
点击复制
基于随机搜索优化XGBoost的瓦斯涌出量预测模型*
MA Heng,REN Meixue,GAO Ke.Prediction model of gas emission amount based on XGBoost optimized with random search algorithm[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(5):129-134.[doi:10.11731/j.issn.1673-193x.2022.05.020]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 18
- 期数:
- 2022年5期
- 页码:
- 129-134
- 栏目:
- 职业安全卫生管理与技术
- 出版日期:
- 2022-05-31
文章信息/Info
- Title:
- Prediction model of gas emission amount based on XGBoost optimized with random search algorithm
- 文章编号:
- 1673-193X(2022)-05-0129-06
- 分类号:
- X936;TD712
- 文献标志码:
- A
- 摘要:
- 为防治瓦斯灾害，解决井下瓦斯涌出量在预测过程中因影响因素繁多带来的精度较低问题，提出1种基于套索(Lasso)回归与随机搜索优化极限梯度提升(XGBoost)的模型进行瓦斯涌出量预测。以沈阳某煤矿综采面瓦斯涌出量历史数据为例，综合考虑影响瓦斯涌出量的影响因素。首先利用Lasso回归提取对瓦斯涌出量有重要影响的特征数据，作为预测输入；采用随机搜索算法对XGBoost模型4种主要参数进行寻优，选取最优参建立预测模型获得预测指标并分析比较其他模型。研究结果表明：Lasso回归筛选出的影响因素结合随机搜索获得的最优参数组合优化XGBoost比其他模型预测精度更高，平均相对误差为1.53%，均方根误差为0.140 3 m3/min，希尔不等系数为0.013 2，研究结果可为现场瓦斯管理提供参考依据。
- Abstract:
- In order to prevent the gas disasters,and solve the problem of inaccuracy in the process of predicting underground gas emission amount due to many influencing factors,a model based on the Lasso regression and limit gradient boosting (XGBoost) optimized with random search was proposed to predict the gas emission amount.Taking the historical data of gas emission amount from the fully-mechanized mining face of a coal mine in Shenyang as an example,the factors affecting the gas emission amount were comprehensively considered.The Lasso regression was used to extract the feature data with important influence on the gas emission amount as the prediction input.The random search algorithm was used to optimize the four key parameters of the XGBoost model,and the optimal parameters were selected to establish a prediction model,so as to obtain the prediction indexes and analyze and compare the other models.The results showed that the influencing factors selected by Lasso regression combined with the optimal parameters combination optimization XGBoost obtained by random search had higher prediction accuracy than the other models.The average relative error was 1.53%,the root mean square error was 0.140 3 m3/min,and the Theil inequality coefficient was 0.013 2,which provides a reference for the on-site gas management.
参考文献/References:
［1］刘峰,曹文君,张建明,等.我国煤炭工业科技创新进展及“十四五”发展方向［J］.煤炭学报,2021,46(1):1-15.
LIU Feng,CAO Wenjun,ZHANG Jianming,et al.The technological innovation progress of my country’s coal industry and the development direction of the “14th Five-Year Plan”［J］.Journal of China Coal Society,2021,46(1):1-15.
［2］缪协兴,钱鸣高.中国煤炭资源绿色开采研究现状与展望［J］.采矿与安全工程学报,2009,26(1):1-14.
MIAO Xiexing,QIAN Minggao.Research status and prospect of green mining of coal resources in China［J］.Journal of Mining and Safety Engineering,2009,26(1):1-14.
［3］付华,姜伟,单欣欣.基于耦合算法的煤矿瓦斯涌出量预测模型研究［J］.煤炭学报,2012,37(4):654-658.
FU Hua,JIANG Wei,SHAN Xinxin.Research on coal mine gas emission prediction model based on coupling algorithm［J］.Journal of China Coal Society,2012,37(4):654-658.
［4］师超,凡永鹏,王延生.SFLA-Verhulst组合模型预测矿井瓦斯涌出量［J］.中国安全生产科学技术,2018,14(3):72-76.
SHI Chao,FAN Yongpeng,WANG Yansheng.SFLA-Verhulst combination model predicts mine gas emission［J］.Journal of Safety Science and Technology,2018,14(3):72-76.
［5］肖鹏,谢行俊,双海清,等.基于KPCA-CMGANN算法的瓦斯涌出量预测研究［J］.中国安全科学学报,2020,30(5):39-47.
XIAO Peng,XIE Xingjun,SHUANG Haiqing,et al.Research on gas emission prediction based on KPCA-CMGANN algorithm［J］.China Safety Science Journal,2020,30(5):39-47.
［6］YUAN B Q.Study on gas emission prediction of working face based on GM (1,1) model［J］.Journal of Physics:Conference Series,2020,1549(4):042031.
［7］赵玮,徐良杰,冉斌,等.基于Adaptive Lasso及RF算法的冰雪天气交通事故分析［J］.中国安全科学学报,2017,27(2):98-103.
ZHAO Wei,XU Liangjie,Ran Bin,et al.Analysis of traffic accidents in ice and snow based on Adaptive Lasso and RF algorithm［J］.China Safety Science Journal,2017,27(2):98-103.
［8］杨丽,刘晖,毛善君,等.基于多元分布滞后模型的瓦斯浓度动态预测［J］.中国矿业大学学报,2016,45(3):455-461.
YANG Li,LIU Hui,MAO Shanjun,et al.Dynamic prediction of gas concentration based on multivariate distribution lag model［J］.Journal of China University of Mining & Technology,2016,45(3):455-461.
［9］CHEN T,GUESTRIN C.XGBoost:a scalable tree boosting system［J］.the 22nd ACM SIGKDD International Conference,2016.
［10］李清亮,蔡凯旋,耿庆田,等.极限梯度提升和长短期记忆网络相融合的土壤温度预测［J］.光学精密工程,2020,28(10):2337-2348.
LI Qingliang,CAI Kaixuan,GENG Qingtian,et al.Soil temperature prediction based on the fusion of extreme gradient boosting and long-short-term memory network［J］.Optics and Precision Engineering,2020,28(10):2337-2348.
［11］谢学斌,孔令燕.基于ARIMA和XGBoost组合模型的交通事故预测［J］.安全与环境学报,2021,21(1):277-284.
XIE Xuebin,KONG Lingyan.Traffic accident prediction based on ARIMA and XGBoost combined model［J］.Journal of Safety and Environment,2021,21(1):277-284.
［12］魏良针.基于支持向量机的铁路周边地表沉降变形量预测［J］.中国安全生产科学技术,2019,15(S1):90-94.
WEI Liangzhen.Prediction of surface settlement and deformation around railway based on support vector machine［J］.Journal of Safety Science and Technology,2019,15(S1):90-94.
［13］解明垒,马尚权.基于多元线性回归理论的煤矿瓦斯涌出量预测［J］.陕西煤炭,2021,40(1):26-29,52.
XIE Minglei,MA Shangquan.Coal mine gas emission prediction based on multiple linear regression theory［J］.Shaanxi Coal,2021,40(1):26-29,52.
［14］洪林,赫祥林,董晓雷,等.PCA-GA-ELM煤矿瓦斯涌出量预测［J］.辽宁工程技术大学学报(自然科学版),2015,34(7):779-784.
HONG Lin,HE Xianglin,DONG Xiaolei,et al.PCA-GA-ELM coal mine gas emission prediction［J］.Journal of Liaoning Technical University (Natural Science Edition),2015,34(7):779-784.
［15］吕鹏飞,陈学华.基于PSO优化LSSVM模型的回采巷道顶底板移近量预测［J］.安全与环境学报,2017,17(6):2045-2049.
LYU Pengfei,CHEN Xuehua.Prediction of approaching amount of roof and floor of mining roadway based on PSO optimized LSSVM model［J］.Journal of Safety and Environment,2017,17(6):2045-2049.
相似文献/References:
备注/Memo
- 备注/Memo:
-
收稿日期： 2021-04-07
* 基金项目： 国家自然科学基金项目（52074148）
作者简介： 马恒，博士，教授，主要研究方向为矿井通风安全、信息安全工程等。
通信作者： 任美学，硕士研究生，主要研究方向为矿井通风与瓦斯防治等。
