Prediction of Coal and Gas Outburst in Mine Working Face Based on PCA and Weighted Bayesian

doi:10.19678/j.issn.1000-3428.0058292

Abstract

Abstract: In order to realize fast, accurate and dynamic prediction of coal and gas outburst in working face, a prediction method based on Principal Component Analysis (PCA) and the weighted Bayesian model is proposed. A weighted Bayesian model for coal and gas outburst prediction in mine working face is built, which also determines the class of the outburst risk. Then the weight of classified variables in the prediction model is determined by using PCA to improve the accuracy of prediction. On this basis, the updating mechanism of the training data is designed based on similarity to rebuild the prediction model effectively. The experimental results show that compared with the naïve Bayesian model and the weighted Bayesian model, the proposed method could quickly generate more accurate prediction results, providing reference for on-site direction of production in mine working face.

Key words: coal and gas outburst in mine working face, Principal Component Analysis(PCA), weighted Bayesian model, dynamic prediction, prediction uncertainty

摘要： 为实现对工作面煤与瓦斯突出快速、准确和动态的预测，提出一种基于主成分分析和权重贝叶斯的工作面煤与瓦斯突出预测方法，通过建立工作面煤与瓦斯突出预测的权重贝叶斯模型进行突出危险性等级预测。利用主成分分析确定预测模型中分类变量权重以提高预测准确性。在此基础上，设计基于相似度的训练样本数据更新方式实现对突出预测模型的有效重构。实验结果表明，与朴素贝叶斯模型和权重贝叶斯模型相比，基于主成分分析和权重贝叶斯工作面煤与瓦斯突出预测方法能快速获得高准确度的突出预测结果，为现场指导矿井工作面安全生产提供参考。

关键词: 工作面煤与瓦斯突出, 主成分分析, 权重贝叶斯模型, 动态预测, 预测不确定性

CLC Number:

TP391.1

YAN Xin, ZHU Yonghao, TU Naiwei, WU Shuwen, WANG Yuhong. Prediction of Coal and Gas Outburst in Mine Working Face Based on PCA and Weighted Bayesian[J]. Computer Engineering, 2021, 47(8): 315-320.

阎馨, 朱永浩, 屠乃威, 吴书文, 王雨虹. 基于PCA与权重贝叶斯的工作面煤与瓦斯突出预测[J]. 计算机工程, 2021, 47(8): 315-320.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0058292

http://www.ecice06.com/EN/Y2021/V47/I8/315

Figures/Tables 6

References

[1] 邹永洺, 张占存.新型钻孔瓦斯涌出初速度测定钻杆研[J]. 煤矿安全, 2016, 47(3): 20-23. ZOU Y M, ZHANG Z C.Study on the new type of drill pipe for measuring the initial velocity of gas emission[J]. Safety in Coal Mines, 2016, 47(3): 20-23.(in Chinese)
[2] WANG L, LU Z, CHEN D P, et al. Safe strategy for coal and gas outburst prevention in deep-and-thick coal seams using a soft rock protective layer mining[J]. Safety Science, 2020, 129(9): 1-8.
[3] WANG C J, LI X W, XU C H, et al. Study on factors influencing and the critical value of the drilling cuttings weight:an index for outburst risk prediction[J]. Process Safety and Environmental Protection, 2020, 140:356-366.
[4] YANG Z H, ZHANG H W, LI S, et al. Prediction of residual gas content during coal roadway tunneling based on drilling cuttings indices and BA-ELM algorithm[J]. Journal of Mathematics, 2020, 15(1): 1504-1512.
[5] 曹学军, 朱南南, 舒龙勇.煤与瓦斯突出综合指标预测模型及应用[J]. 能源技术与管理, 2019, 44(6): 34-37, 52. CAO X J, ZHU N N, SHU L Y.Prediction model and application of comprehensive index of coal and gas out burst[J]. Energy Technology and Management, 2019, 44(6): 34-37, 52.(in Chinese)
[6] 陈亮, 范志浩, 付江伟, 等. 基于电磁辐射峰谷比值法的煤与瓦斯突出预警[J]. 中国安全生产科学技术, 2019, 15(6): 94-98. CHEN L, FAN Z H, FU J W, et al. Early warning of coal and gas outburst based on peak-to-valley ratio method of electromagnetic radiation[J]. Journal of Safety Science and Technology, 2019, 15(6): 94-98.(in Chinese)
[7] LI Z H, WANG E Y, OU J C, et al. Hazard evaluation of coal and gas outbursts in a coal-mine roadway based on logistic regression model[J]. International Journal of Rock Mechanics and Mining Sciences, 2015, 80:185-195.
[8] WU Y Q, GAO R L, YANG J Z.Prediction of coal and gas outburst:a method based on the BP neural network optimized by GASA[J]. Process Safety and Environmental Protection, 2020, 133:64-72.
[9] 袁非牛, 章琳, 史劲亭, 等. 自编码神经网络理论及应用综述[J]. 计算机学报, 2019, 42(1): 203-230. YUAN F N, ZHANG L, SHI J T, et al. Review of the theory and application of self coding neural network[J]. Chinese Journal of Computers, 2019, 42(1): 203-230.(in Chinese)
[10] 方荣强, 王晶, 姚治成, 等. 多层神经网络算法的计算特征建模方法[J]. 计算机研究与发展, 2019, 56(6): 1170-1181. FANG R Q, WANG J, YAO Z C, et al. Computational feature modeling method of multilayer neural network algorithm[J]. Journal of Computer Research and Development, 2019, 56(6): 1170-1181.(in Chinese)
[11] 刘海波, 钱伟, 王福忠.基于粗糙集与粒子群优化支持向量机的瓦斯突出预测模型[J]. 中国科技大学学报, 2019, 49(2): 87-92. LIU H B, QIAN W, WANG F Z.Gas outburst prediction based on rough set and particle swarm optimization support vector machine[J]. Journal of University of Science and Technology of China, 2019, 49(2): 87-92.(in Chinese)
[12] YAN Z G, KAN Y, YANG Y X.A novel adaptive differential evolution SVM model for predicting coal and gas outbursts[J]. Journal of Difference Equations and Applications, 2016, 23(9): 238-248.
[13] ZHANG J, MA H W.Research on gas outburst prediction in coal mining in China based on a new kind of SVM algorithm[J]. Advanced Materials Research, 2013, 868:374-379.
[14] 边平勇, 石永奎, 张序萍.基于贝叶斯分类器的煤与瓦斯突出强度预测研究[J]. 佳木斯大学学报, 2013, 31(6): 890-894. BIAN P Y, SHI Y K, ZHANG X P.Research of coal and gas outburst prediction based on naive Bayes classifier[J]. Journal of Jiamusi University, 2013, 31(6): 890-894.(in Chinese)
[15] 朱克楠, 尹宝林, 冒亚明, 等. 基于有效窗口和朴素贝叶斯的恶意代码分类[J]. 计算机研究与发展, 2014, 51(2): 373-381. ZHU K N, YIN B L, MAO Y M, et al. Malicious code classification based on efficient window and naive Bayes[J]. Journal of Computer Research and Development, 2014, 51(2): 373-381.(in Chinese)
[16] 高晓利, 王维, 赵火军.几种改进的朴素贝叶斯分类器模型[J]. 探索与观察, 2018, 21(6): 40-41. GAO X L, WANG W, ZHAO H J.Several improved naive Bayesian classifier models[J]. Exploration and Observation, 2018, 21(6): 40-41.(in Chinese)
[17] 袁连海, 李湘文, 徐晶.基于改进贝叶斯原理的垃圾邮件过滤算法研究[J]. 计算机与数字工程, 2020, 48(3): 513-516, 712. YUAN L H, LI X W, XU J.Research on spam filtering algorithm based on improved Bayesian principle[J]. Computer & Digital Engineering, 2020, 48(3): 513-516, 712.(in Chinese)
[18] 任世超, 黄子良.基于二维信息增益加权的朴素贝叶斯分类算法[J]. 计算机系统应用, 2019, 28(6): 135-140. REN S C, HUANG Z L.Naive Bayesian classification algorithm based on two dimensional information gain weighting[J]. Computer Systems & Applications, 2019, 28(6): 135-140.(in Chinese)
[19] 谢娟英, 谢维信.基于特征子集区分度与支持向量机的特征选择算法[J]. 计算机学报, 2014, 37(8): 1704-1718. XIE J Y, XIE W X.Feature selection algorithm based on feature subset discrimination and support vector machine[J]. Chinese Journal of Computers, 2014, 37(8): 1704-1718.(in Chinese)
[20] GUO L L, WU P, LOU S W, et al. A multi-feature extraction technique based on principal component analysis for nonlinear dynamic process monitoring[J]. Journal of Process Control, 2020, 85(1): 159-172.
[21] LEVADA A L M.Parametric PCA for unsupervised metric learning[J]. Pattern Recognition Letters, 2020, 135(7): 425-430.
[22] CUI J G, LI G Q, YU M Y, et al. Aero-engine fault diagnosis based on kernel principal component analysis and wavelet neural network[C]//Proceedings of Control and Decision Conference.Washington D.C., USA:IEEE Press, 2019.
[23] LAM S T H, NGUYEN B T DINH, et al. Posterior concentration and fast convergence rates for generalized Bayesian learning[J]. Information Sciences, 2020, 538(10): 372-383.

Please choose a citation manager

Content to export