基于二次分解和BO-BiLSTM组合模型的采煤工作面瓦斯涌出量预测方法研究

    Research on prediction method of coal mining face gas outflow based on quadratic decomposition and BO-BiLSTM combination model

    • 摘要: 为了提高采煤工作面瓦斯涌出量预测精度,提出了一种基于二次分解和BO-BiLSTM组合模型的采煤工作面瓦斯涌出量预测方法。首先运用变分模态分解(VMD)将瓦斯涌出量时序数据进行一次分解,充分利用其分解后的残余分量,并采用自适应噪声完备经验模态分解(CEEMDAN)进行二次分解;然后将分解后的所有子序列分别输入到贝叶斯算法优化双向长短期记忆网络(BO-BiLSTM)模型中进行瓦斯涌出量预测;最后将各子序列模型输出结果进行叠加得到最终瓦斯涌出量预测结果。以陕西彬长矿区某矿采煤工作面绝对瓦斯涌出量日监测数据为例进行建模和预测分析,结果表明:所提出的瓦斯涌出量组合预测模型具有较高的预测精度,验证了该模型在瓦斯涌出量预测方面的有效性和适用性。

       

      Abstract: In order to improve the prediction accuracy of coal mining face gas outflow, a coal mining face gas outflow prediction method based on quadratic decomposition and BO-BiLSTM combination model is proposed. Firstly, variational mode decomposition (VMD) is used to decompose the gas outflow time series data once, making full use of the residual component after decomposition, and using adaptive noise complete empirical mode decomposition(CEEMDAN) for secondary decomposition. Then, all the subsequences after decomposition are input into the Bayesian algorithm optimized bidirectional long short-term memory network (BO-BiLSTM) model for gas outflow prediction. Finally, the output results of each subseries model are superimposed to obtain the final gas outflow prediction results. Taking the daily monitoring data of absolute gas outflow in a mine face in Binchang Mining Area of Shaanxi Province as an example, the results show that the proposed combined prediction model of gas outflow has high prediction accuracy, which verifies the effectiveness and applicability of the model in the prediction of gas outflow.

       

    /

    返回文章
    返回