• 论文
主办单位:煤炭科学研究总院有限公司、中国煤炭学会学术期刊工作委员会
我国煤矿水害事故现状、预测及防治建议
  • Title

    Current states , prediction and prevention suggestions for water hazard accidents in China’s coal mines

  • 作者

    孙文洁李文杰宁殿艳任凌枫

  • Author

    SUN Wenjie;LI Wenjie;NING Dianyan;REN Lingfeng

  • 单位

    陕西省煤矿水害防治技术重点实验室中国矿业大学(北京) 国家煤矿水害防治工程技术研究中心中煤科工西安研究院(集团)有限公司

  • Organization
    Shaanxi Key Laboratory of Prevention and Control Technology for Coal Mine Water Hazard
    National Coal Mine Water Hazard Prevention Engineering Technology Research Center, China University of Mining and Technology (Beijing)
    CCTEG Xi’an Research Institute (Group) Co., Ltd.
  • 摘要
    现阶段我国煤炭资源开发格局发生变化,制约煤矿安全生产的水害事故仍时有发生,为探究我国煤矿水害事故的特征规律,科学研判水害事故演变趋势,以2001—2022年全国煤矿水害事故作为统计对象,从水害事故发生年份、发生区域、事故级别以及水害事故的影响因素等方面进行研究,构建长短期记忆神经网络(Long Short-Term Memory,LSTM)模型,同时引入等维新息灰色G(1,1)模型作为基准模型,对2023—2024年全国煤矿水害事故百万吨死亡率进行预测,并根据事故发生特征提出相应的防治措施。结果表明:2001—2022年我国水害事故共1 103起,死亡人数为4 667人,从2016年开始我国煤矿水害事故起数下降至个位数,事故死亡人数控制在每年50人以内,随着我国煤炭资源开发中心西移以及煤炭资源开采深度加大,煤矿水害事故起数和死亡人数又有上升的趋势;我国煤矿水害事故主要发生在华北、华南和东北水害区,表现出明显的集聚性,近两年发生在西北水害区的煤矿水害事故占近两年总起数的36.36%,死亡人数占比高达74.24%;煤矿水害事故规模整体控制较好,特别重大煤矿水害事故从2011年开始清零,重大水害事故波动下降后在近两年又有反弹,较大和一般水害事故发生起数和伤亡人数明显降低;在目前煤炭资源开发格局下,煤炭产量稳步递增导致不确定性水害致灾风险的提高;LSTM模型的预测精度高于等维新息灰色G(1,1)模型,2种模型未来两年全国煤矿水害事故百万吨死亡率预测值分别为0.004 1、0.002 2与0.003 5、0.001 2,预测结果均显示我国煤矿水害事故造成的伤亡人数整体呈现下降趋势,安全形势稳定。
  • Abstract
    At present, the pattern of coal resource development in China has changed, but the water hazard accidents that restrict the safety production of coal mine still occur from time to time. In order to explore the characteristics and laws of water hazard accidents in coal mines in China and scientifically study and judge the evolution trend of water hazard accidents, study was performed in terms of the year, region, accident level and influencing factors of water hazard accidents, with the nationwide water hazard accidents from 2001 to 2022 as the statistical objects. Meanwhile, the Long Short-Term Memory (LSTM) model was built, and the equal-dimension and new-information grey G(1,1) model was introduced as the benchmark model to predict the fatality rate per million tonnes in coal mine water accidents in 2023-2024. Besides, approprioate prevention and control measures were put forward according to the characteristics of the accidents. The results show that: From 2001 to 2022, there were a total of 1 103 water hazard accidents in China, with a death toll of 4 667 people. Since 2016, the number of water hazard accidents in China’s coal mines has dropped to a single digit, and the death toll of accidents has been controlled within 50 people per year. With the westward migration of China’s coal resource development center and the deepening of coal resource exploitation, the number of coal mine water hazard accidents and the death toll have a rising trend. In China, water hazard accidents in coal mines mainly occur in North China, South China and northeast China, showing obvious agglomeration. In the past two years, the water accidents occurred in northwest coal mines accounts for 36.36% in the total, with the proportion of deaths up to 74.24%. The scale of water hazard accidents in coal mines has been well controlled on the whole. Especially major water hazard accidents in coal mines have been eliminated since 2011. However, the major water accidents used to be decreased but show a rebound in the past two years. The number of major and ordinary water accidents and casualties have decreased significantly. Under the current development pattern of coal resources, the steady increase of coal production leads to the increase of the risk of uncertain water hazard. The prediction accuracy of the LSTM model is higher than that of the equal-dimension and new-information grey G(1,1) model. The predicted fatality rates per million tonnes by the two models in the next two years are 0.004 1, 0.002 2, and 0.003 5, 0.001 2, respectively, for the nationwide water hazard accidents in coal mine. The predicted results show that the number of casualties caused by coal mine water hazard accidents in China shows an overall decreasing trend, which indicates the stable security situation.
  • 关键词

    煤矿水害事故特征演变趋势统计分析长短期记忆神经网络百万吨死亡率安全

  • KeyWords

    coal mine water hazard;accident characteristics;evolution trend;statistical analysis;Long Short-Term Memory;fatality rate per million tonnes;safety

  • 基金项目(Foundation)
    陕西省煤矿水害防治技术重点实验室开放基金项目(2021SKMS01);国家重点研发计划项目(2023YFC3012101);国家自然科学基金项目(42172282,42372285);华北科技学院河北省矿井灾害防治重点实验室开放基金课题(KJZH2022K02,KJZH2022K03)
  • DOI
  • 引用格式
    孙文洁,李文杰,宁殿艳,等. 我国煤矿水害事故现状、预测及防治建议[J]. 煤田地质与勘探,2023,51(12):185−194.
  • Citation
    SUN Wenjie,LI Wenjie,NING Dianyan,et al. Current states , prediction and prevention suggestions for water hazard accidents in China’s coal mines[J]. Coal Geology & Exploration,2023,51(12):185−194.
  • 图表
    •  
    •  
    • 2001—2022年全国煤矿水害事故变化趋势

    图(8) / 表(0)

相关问题

主办单位:煤炭科学研究总院有限公司 中国煤炭学会学术期刊工作委员会

©版权所有2015 煤炭科学研究总院有限公司 地址:北京市朝阳区和平里青年沟东路煤炭大厦 邮编:100013
京ICP备05086979号-16  技术支持:云智互联