基于变分模态分解的瓦斯浓度多尺度组合预测.

In order to improve the prediction accuracy of coal mine gas concentration this paper proposes to use autoregressive integrated moving average (ARIMA) model and gated recycler unit (GRU) model to predict each modal component after the variational mode decomposition of gas concentration series. Then a variable weight combination prediction model is constructed by using the induced generalized ordered weighted function average (IGOWFA) operator. The analysis and comparison of experimental data show that compared with the single prediction method or the fixed weight combination prediction method, the prediction results of this method have higher prediction accuracy, which provides a basis for coal mine to judge the probability of gas accidents. [ABSTRACT FROM AUTHOR]