Based on the theory of grey system, established GM （1, 1） grey catastrophe predict model for the first time in order to forecast the catastrophe periods of mine water inflowing （not the volume of water inflowing）....Based on the theory of grey system, established GM （1, 1） grey catastrophe predict model for the first time in order to forecast the catastrophe periods of mine water inflowing （not the volume of water inflowing）. After establishing the grey predict system of the catastrophe regularity of 10 month-average volume of water inflowing, the grey forewarning for mine water inflowing catastrophe periods was established which was used to analyze water disaster in 400 meter level of Wennan Colliery. Based on residual analysis, it shows that the result of grey predict system is almost close to the actual value. And the scene actual result also shows the reliability of prediction. Both the theoretical analysis and the scene actual result indicate feasibility and reliability of the method of grey catastrophe predict system.展开更多
In order to prevent and control the water inflow of mines, this paper built a new initial GM（1, 1） model to torecast the maximum water inflow according to the principle of new information. The effect of the new init...In order to prevent and control the water inflow of mines, this paper built a new initial GM（1, 1） model to torecast the maximum water inflow according to the principle of new information. The effect of the new initial GM（1, 1） model is not ideal by the concrete example. Then according to the principle of making the sum of the squares of the difference between the calculated sequences and the original sequences, an optimized GM（1, I） model was established. The result shows that this method is a new prediction method which can predict the maximum water inflow accurately. It not only conforms to the guide- line of prevention primarily, but also provides reference standards to managers on making prevention measures.展开更多
为提高采煤工作面涌水量预测准确度,收集大量工作面涌水量观测数据进行整理、统计、分析,将涌水量稳定性、周期性和季节性特征考虑在内,提出1种基于数据驱动的完全自适应模态分解算法(CEEMDAN)和改进的混合时间序列模型工作面涌水量预...为提高采煤工作面涌水量预测准确度,收集大量工作面涌水量观测数据进行整理、统计、分析,将涌水量稳定性、周期性和季节性特征考虑在内,提出1种基于数据驱动的完全自适应模态分解算法(CEEMDAN)和改进的混合时间序列模型工作面涌水量预测方法。该方法利用CEEMDAN处理涌水量数据,构建麻雀搜索算法(SSA)优化的长短期记忆网络(LSTM)和自回归移动平均模型(ARIMA)并行级联而成的混合时间序列模型对工作面涌水量进行预测。研究结果表明:该模型预测结果与真实数据相差更小,平均绝对误差为6.36 m 3/h,均方根误差为10.6 m 3/h,模型拟合系数为0.95,更适用于工作面涌水量预测。研究结果可为矿井工作面涌水量预测及防控提供参考。展开更多
隧道涌水是隧道建设及后期运营中最为常见的地质灾害,准确预测涌水量大小将为隧道设计及施工提供关键参数,因此隧道涌水量预测尤为重要。通过采用地下水动力学方法中的解析法(包括裘布依公式、古德曼公式等),结合数值模拟方法,以隧道导...隧道涌水是隧道建设及后期运营中最为常见的地质灾害,准确预测涌水量大小将为隧道设计及施工提供关键参数,因此隧道涌水量预测尤为重要。通过采用地下水动力学方法中的解析法(包括裘布依公式、古德曼公式等),结合数值模拟方法,以隧道导水断层为研究重点,对地处莲花山断裂带鸿图特长隧道典型段落(K91+634~K93+512)的最大涌水量和正常涌水量进行了预测。同时,利用已开挖段实测涌水量数值,将多种方法进行对比,分析研究各计算方法的适配性,并优化计算算法。研究表明,裘布依承压含水层公式预测与实际涌水量最为接近,鸿图特长隧道典型段落(K91+634~K93+512)的预测最大涌水量为119000 m 3/d,是极限情况下的涌水量预测,为设计施工开挖提供了可靠地水文地质参数。展开更多
文摘Based on the theory of grey system, established GM （1, 1） grey catastrophe predict model for the first time in order to forecast the catastrophe periods of mine water inflowing （not the volume of water inflowing）. After establishing the grey predict system of the catastrophe regularity of 10 month-average volume of water inflowing, the grey forewarning for mine water inflowing catastrophe periods was established which was used to analyze water disaster in 400 meter level of Wennan Colliery. Based on residual analysis, it shows that the result of grey predict system is almost close to the actual value. And the scene actual result also shows the reliability of prediction. Both the theoretical analysis and the scene actual result indicate feasibility and reliability of the method of grey catastrophe predict system.
文摘In order to prevent and control the water inflow of mines, this paper built a new initial GM（1, 1） model to torecast the maximum water inflow according to the principle of new information. The effect of the new initial GM（1, 1） model is not ideal by the concrete example. Then according to the principle of making the sum of the squares of the difference between the calculated sequences and the original sequences, an optimized GM（1, I） model was established. The result shows that this method is a new prediction method which can predict the maximum water inflow accurately. It not only conforms to the guide- line of prevention primarily, but also provides reference standards to managers on making prevention measures.
文摘为提高采煤工作面涌水量预测准确度,收集大量工作面涌水量观测数据进行整理、统计、分析,将涌水量稳定性、周期性和季节性特征考虑在内,提出1种基于数据驱动的完全自适应模态分解算法(CEEMDAN)和改进的混合时间序列模型工作面涌水量预测方法。该方法利用CEEMDAN处理涌水量数据,构建麻雀搜索算法(SSA)优化的长短期记忆网络(LSTM)和自回归移动平均模型(ARIMA)并行级联而成的混合时间序列模型对工作面涌水量进行预测。研究结果表明:该模型预测结果与真实数据相差更小,平均绝对误差为6.36 m 3/h,均方根误差为10.6 m 3/h,模型拟合系数为0.95,更适用于工作面涌水量预测。研究结果可为矿井工作面涌水量预测及防控提供参考。
文摘隧道涌水是隧道建设及后期运营中最为常见的地质灾害,准确预测涌水量大小将为隧道设计及施工提供关键参数,因此隧道涌水量预测尤为重要。通过采用地下水动力学方法中的解析法(包括裘布依公式、古德曼公式等),结合数值模拟方法,以隧道导水断层为研究重点,对地处莲花山断裂带鸿图特长隧道典型段落(K91+634~K93+512)的最大涌水量和正常涌水量进行了预测。同时,利用已开挖段实测涌水量数值,将多种方法进行对比,分析研究各计算方法的适配性,并优化计算算法。研究表明,裘布依承压含水层公式预测与实际涌水量最为接近,鸿图特长隧道典型段落(K91+634~K93+512)的预测最大涌水量为119000 m 3/d,是极限情况下的涌水量预测,为设计施工开挖提供了可靠地水文地质参数。
