煤矿安全大数据特征及治理方法体系研究

陈孝慈; 李东海

doi:10.13272/j.issn.1671-251x.18097

煤矿安全大数据特征及治理方法体系研究

doi: 10.13272/j.issn.1671-251x.18097

陈孝慈^1,,
李东海^2, ,

1.
常州大学商学院, 江苏常州　213000
2.
内蒙古师范大学政府管理学院, 内蒙古呼和浩特　010022

基金项目: 国家自然科学基金项目(42261032)；内蒙古自然科学基金项目(2022LHQN07003)。

详细信息

作者简介:
陈孝慈(1991—)，男，浙江宁波人，讲师，博士，主要研究方向为可视化管理、知识可视化等，E-mail：nb.chenxc@qq.com

通讯作者:
李东海(1984—)，男，山西大同人，讲师，博士，主要研究方向为能源经济，E-mail：donghai.1984@163.com

中图分类号: TD67
计量
- 文章访问数: 886
- HTML全文浏览量: 89
- PDF下载量: 58
- 被引次数: 0
出版历程
- 收稿日期: 2023-04-03
- 修回日期: 2023-04-25
- 网络出版日期: 2023-05-10

Research on the coal mine safety big data features and governance method system

CHEN Xiaoci^1
,,
LI Donghai^{2
, ,}

1.
Business School, Changzhou University, Changzhou 213000, China
2.
School of Government Management, Inner Mongolia Normal University, Hohhot 010022, China

摘要

摘要: 高效分析利用煤矿安全大数据，对于提高煤矿的安全管理水平和生产效率具有重要意义。目前煤矿安全大数据治理存在数据特征不明、治理方法不清等问题，针对该问题，着重分析了煤矿安全大数据特征，得出煤矿安全大数据具有5V特征，即数据体量大(Volume)、数据类型多(Variety)、处理速度快(Velocity)、价值密度低(Value)、真实性(Veracity) ，此外还具有结构化程度不一致的特征。介绍了可应用于煤矿安全管理中的主要数据治理方法及模型，并分为单变量方法、多变量统计分析方法、智能模式识别方法、系统动力学模型和综合集成模型五大类。从主体和客体的视角，提出了煤矿安全大数据治理方法体系，认为数据治理方法的选择必须与智慧矿山的主体、客体的数据治理目标相契合。基于主体的治理方法选择：根据数据主体的需求、层次、担负的任务及安全管理目标确定数据治理具体内容；基于客体的治理方法选择：根据客体对象的时效性、吞吐量要求及安全管理目标确定数据治理具体内容。最后得出煤矿安全大数据治理方法的确定需要在统一目标和统一标准下，根据作用域和作用对象的不同，满足共性和个性需求。
- 智慧矿山 /
- 煤矿安全大数据 /
- 数据特征 /
- 数据治理目标 /
- 数据治理方法选择 /
- 时效性 /
- 吞吐量
Abstract: Efficient analysis and utilization of coal mine safety big data is of great significance for improving the safety management level and production efficiency of coal mines. At present, there are some problems in coal mine safety big data governance, such as unclear data features and governance methods. In order to solve the above problems, this paper emphatically analyzes the features of coal mine safety big data. It is concluded that coal mine safety big data has 5V features, namely, large data volume (Volume), multiple data varieties (Variety), fast processing velocity (Velocity), low value density (Value), veracity (Veracity), and also has the features of inconsistent structural degree. This paper introduces the main data governance methods and models that can be applied to coal mine safety management. The methods are divided into five categories: single variable method, multivariate statistical analysis method, intelligent pattern recognition method, system dynamics model and comprehensive integration model. From the perspective of the subject and object, this paper puts forward a big data governance method system for coal mine safety. It is believed that the selection of data governance methods must be consistent with the data governance goals of the subject and object of intelligent mines. Selection of subject-based governance methods: the specific content of data governance is determined according to the needs, levels, tasks and security management objectives of data subjects. Selection of object-based governance methods: the specific content of data governance is determined according to the timeliness of object objects, throughput requirements and security management objectives. Finally, it is concluded that the determination of coal mine safety big data governance method needs to meet the common and individual needs according to the different scopes and objects under the unified goal and standard.
- intelligent mine /
- coal mine safety big data /
- data feature /
- data governance objective /
- data governance method selection /
- timeliness /
- throughput

HTML全文

图 1 数据结构化层次

Figure 1. Data structured hierarchy

下载: 全尺寸图片幻灯片

图 2 基于主体的数据治理方法选择过程

Figure 2. Subject-based selection process of data governance methods

下载: 全尺寸图片幻灯片

图 3 煤矿安全数据分类

Figure 3. Classification of coal mine safety data

下载: 全尺寸图片幻灯片

图 4 基于客体的数据治理方法选择过程

Figure 4. Object-based selection process of data governance methods

下载: 全尺寸图片幻灯片

图 5 煤矿安全大数据治理方法体系逻辑框架

Figure 5. Logical framework of the big data governance method system for coal mine safety

下载: 全尺寸图片幻灯片

图 6 煤矿安全大数据治理方法体系应用示例

Figure 6. Application of the big data governance approach system for coal mine safety

下载: 全尺寸图片幻灯片

表 1 SVM和ANN的主要特性

Table 1. The main features of SVM and ANN

主要特性	SVM	ANN
数据要求	适用于一定规模的高维数据	适用于大规模的数据集
解释性	结果易解释	结果较难解释
鲁棒性	对噪声和离群点具有一定鲁棒性	对噪声和离群点较敏感
精度	精度较高，与特征选取相关	精度高，与训练数据相关

下载: 导出CSV

参考文献(21)

[1]	谭章禄,王美君. 智慧矿山数据治理概念内涵、发展目标与关键技术[J]. 工矿自动化,2022,48(5):6-14. TAN Zhanglu,WANG Meijun. Research on the concept connotation,development goal and key technologies of data governance for smart mine[J]. Journal of Mine Automation,2022,48(5):6-14.
[2]	谭章禄,吴琦. 智慧矿山理论与关键技术探析[J]. 中国煤炭,2019,45(10):30-40. TAN Zhanglu,WU Qi. Analysis and discussion of smart mine theory and key technologies[J]. China Coal,2019,45(10):30-40.
[3]	王国法,王虹,任怀伟,等. 智慧煤矿2025情景目标和发展路径[J]. 煤炭学报,2018,43(2):295-305. WANG Guofa,WANG Hong,REN Huaiwei,et al. 2025 scenarios and development path of intelligent coal mine[J]. Journal of China Coal Society,2018,43(2):295-305.
[4]	王龙康. 煤矿安全隐患层次分析与预警方法研究[D]. 北京: 中国矿业大学（北京）, 2015. WANG Longkang. The hierarchy analysis for hidden danger and research on early warning method in coal mine[D]. Beijing: China University of Mining & Technology-Beijing, 2015.
[5]	陈孝慈. 煤矿安全隐患管理知识发现研究[D]. 北京: 中国矿业大学（北京）, 2021. CHEN Xiaoci. Research on knowledge discovery of coal mine safety hidden peril management[D]. Beijing: China University of Mining & Technology-Beijing, 2021.
[6]	PROVOST F,FAWCETT T. Data science and its relationship to big data and data-driven decision making[J]. Big Data,2013,1(1):51-59. doi: 10.1089/big.2013.1508
[7]	GOLDSTON D. Big data:data wrangling[J]. Nature,2008,455:15. doi: 10.1038/455015a
[8]	REICHMAN O J,JONES M B,SCHILDHAUER M P. Challenges and opportunities of open data in ecology[J]. Science,2011,331(6018):703-705. doi: 10.1126/science.1197962
[9]	GUPTA U G,GUPTA A. Vision:a missing key dimension in the 5V big data framework[J]. Journal of International Business Research and Marketing,2016,1(3):46-52.
[10]	何敏. 智能煤矿数据治理框架与发展路径[J]. 工矿自动化,2020,46(11):23-27. HE Min. Framework and development path of data governance in intelligent coal mine[J]. Industry and Mine Automation,2020,46(11):23-27.
[11]	王国法,刘峰,庞义辉,等. 煤矿智能化——煤炭工业高质量发展的核心技术支撑[J]. 煤炭学报,2019,44(2):349-357. WANG Guofa,LIU Feng,PANG Yihui,et al. Coal mine intellectualization:the core technology of high quality development[J]. Journal of China Coal Society,2019,44(2):349-357.
[12]	谭章禄,王美君. 智能化煤矿数据归类与编码实质、目标与技术方法[J]. 工矿自动化,2023,49(1):56-62,72. TAN Zhanglu,WANG Meijun. The essence,goal and technical method of intelligent coal mine data classification and coding[J]. Journal of Mine Automation,2023,49(1):56-62,72.
[13]	WU Xindong,KUMAR V,QUINLAN J R,et al. Top 10 algorithms in data mining[J]. Knowledge and Information Systems,2008,14:1-37. doi: 10.1007/s10115-007-0114-2
[14]	FREITAS A A. A review of evolutionary algorithms for data mining[M]//MAIMON O, ROKACH L. Data mining and knowledge discovery handbook. New York: Springer, 2010: 371-400.
[15]	GRABMEIER J,RUDOLPH A. Techniques of cluster algorithms in data mining[J]. Data Mining and Knowledge Discovery,2002,6:303-360. doi: 10.1023/A:1016308404627
[16]	赵勇, 林辉. 大数据革命[M]. 北京: 电子工业出版社, 2014. ZHAO Yong, LIN Hui. Big data revolution[M]. Beijing: Publishing House of Electronics Industry, 2014.
[17]	李航. 统计学习方法[M]. 2版. 北京: 清华大学出版社, 2019. LI Hang. Statistical learning methods[M]. 2nd ed. Beijing: Tsinghua University Press, 2019.
[18]	刘年平. 煤矿安全生产风险预警研究[D]. 重庆: 重庆大学, 2012. LIU Nianping. Research on risk early warning in mine safety production[D]. Chongqing: Chongqing University, 2012.
[19]	NASSAJI H. Qualitative and descriptive research:data type versus data analysis[J]. Language Teaching Research,2015,19(2):129-132. doi: 10.1177/1362168815572747
[20]	谭章禄,吴琦. 基于层级链参考模型的智慧矿山建设问题分析[J]. 矿业科学学报,2022,7(2):257-266. TAN Zhanglu,WU Qi. Analysis of the problems of smart mine construction based on the layer-level-chain reference model[J]. Journal of Mining Science and Technology,2022,7(2):257-266.
[21]	谭章禄,王美君. 智能化煤矿数据治理概念模型及技术架构研究[J]. 矿业科学学报,2023,8(2):242-255. TAN Zhanglu,WANG Meijun. Research on the conceptual model and technical architecture of data governance for intelligent coal mine[J]. Journal of Mining Science and Technology,2023,8(2):242-255.