论文部分内容阅读
煤矿安全是煤矿生产的重要保障,煤矿事故预测是煤矿安全评价和决策的基础。结合灰色SCGM(1,1)_c预测模型和马尔可夫链理论的优点,根据煤矿生产的特殊条件,提出了基于马尔可夫链的SCGM(1,1)_c预测模型。首先利用灰色SCGM(1,1)_c预测模型对我国1990—2010年的煤矿事故百万t死亡率进行初次预测,然后根据初次预测结果,利用残差模型对SCGM(1,1)_c模型预测结果进行修正。最后在修正模型的基础上,运用马尔可夫SCGM(1,1)_c模型对我国2011—2013年煤矿事故百万t死亡率进行了预测,并对两种模型的预测误差进行了对比分析。结果表明,马尔可夫SCGM(1,1)_c预测模型既能揭示煤矿事故百万t死亡率变化的总体趋势,又能克服随机波动性数据对预测精度的影响,具有较强的工程实用性。
Coal mine safety is an important guarantee for coal mine production. Coal mine accident prediction is the basis of coal mine safety assessment and decision-making. Combined with the advantages of gray SCGM (1,1) _c prediction model and Markov chain theory, a Markov chain based SCGM (1,1) _c prediction model is proposed according to the special conditions of coal mine production. Firstly, the gray SCGM (1,1) _c forecasting model was used to predict the annual mortality rate of coal mine accident in China from 1990 to 2010. Based on the results of the first forecast, the residual model was used to predict the SCGM (1,1) _c model The result is corrected. Finally, based on the modified model, the Markov SCGM (1,1) _c model is used to predict the death rate of coal mine accidents in China from 2011 to 2013, and the prediction errors of the two models are compared. The results show that Markov’s SCGM (1,1) _c forecasting model can not only reveal the general trend of the death rate of one million tons of coal mine accidents, but also overcome the influence of stochastic volatility data on prediction accuracy and have strong engineering practicability .