摘要
矿井灾害频发是影响我国煤炭产业发展的重要问题之一,灾前预警技术是目前应对这一问题的主要方法。为进一步提升矿井灾害监测预警能力,提出了基于ARIMA模型的矿井灾害预测方法研究。通过确立灾害风险监测指标构建了安全态势评估指标体系,基于时序预测法建立了灾害预测评估模型,经模型定阶及训练等过程确定最佳ARIMA预测模型参数。通过研究模型残差的正态性分布从而得到预测模型可靠度,将ARIMA(10,0,0)模型与时间序列拟合后进行自相关图和偏自相关图分析,得到了风险灾害未来短期预测结果;提出了“红橙黄蓝绿”5级灾害预警等级和准则,并进行了现场应用试验,结果证明,ARIMA模型对未来值的预测具有较高准确性,系统能及时对灾害进行预测和分级响应,可实现对矿井灾害的风险判别和预测预警。
The frequent occurrence of mine disasters is one of the important issues affecting the development of my country's coal industry.Pre-disaster early warning technology is the main method to deal with this problem.In order to further improve the ability of mine disaster monitoring and early warning,a mine disaster prediction method based on ARIMA model is proposed.By establishing disaster risk monitoring indicators,a security situation assessment index system is established,and a disaster prediction and evaluation model is established based on the time series prediction method.The optimal ARIMA prediction model parameters are determined through the process of model order determination and training.By studying the normal distribution of model residuals to obtain the reliability of the forecast model,after fitting the ARIMA(10,0,0)model to the time series,the autocorrelation diagram and partial autocorrelation diagram are analyzed,the future short-term prediction results of risk disasters are obtained;the five-level disaster warning level and criteria of"red orange yellow blue green"were proposed,and field application tests were carried out.The results proved that the ARIMA model has high accuracy in predicting future values,and the system can predict disasters in time.Hierarchical response can realize risk discrimination,prediction and early warning of mine disasters.
作者
翟小伟
周翔
宋波波
郝乐
ZHAI Xiaowei;ZHOU Xiang;SONG Bobo;HAO Le(College of Safety Science and Engineering,Xi'an University of Science and Technology,Xi'an 710054,China;Shaanxi Province Key Laboratory of Coal Fire Disaster Prevention and Control,Xi'an University of Science and Technology,Xi'an 710054,China;Mine Emergency Rescue Innovation Team,The Youth Innovation Team of Shaanxi Universities,Xi'an 710054,China)
出处
《煤炭技术》
CAS
2024年第6期165-168,共4页
Coal Technology
基金
国家自然科学基金项目(51974236,52274229)
陕西省自然科学基础研究计划项目(2021JC-48)
陕西省教育厅青年创新团队建设科研计划项目(21JP078)
榆林国家高新技术产业开发区科技计划项目(ZD-2021-13)。
关键词
矿井灾害
指标体系
评估模型
预警准则
mine disaster
index system
evaluation model
early warning criterion
