A Method for Predicting Coal-Mine Methane Outburst Volumes and Detecting Anomalies Based on a Fusion Model of...

The ability to predict the volume of methane outbursts in coal mines is critical for the prevention of methane outburst accidents and the assurance of coal-mine safety. This paper's central argument is that existing prediction models are limited in several ways. These limitations include the complexity of the models and their poor ability to generalize. The paper proposes a methane outburst volume-prediction and early-warning method. This method is based on a secondary decomposition and improved TSMixer model. First, data smoothing is achieved through an STL decomposition-adaptive Savitzky-Golay filtering-reconstruction framework to reduce temporal complexity. Second, a CEEMDAN-Kmeans-VMD secondary decomposition strategy is adopted to integrate intrinsic mode functions (IMFs) using K-means clustering. Variational mode decomposition (VMD) parameters are optimized via a novel exponential triangular optimization (ETO) algorithm to extract multi-scale features. Additionally, a refined TSMixer model is proposed, integrating reversible instance normalization (RevIn) to bolster the model's generalizability and employing ETO to fine-tune model hyperparameters. This approach enables multi-component joint modeling, thereby averting error accumulation. The experimental results demonstrate that the enhanced model attains RMSE, MAE, and R² values of 0.0151, 0.0117, and 0.9878 on the test set, respectively, thereby exhibiting a substantial improvement in performance when compared to the reference models. Furthermore, we propose an anomaly detection framework based on STL decomposition and dual lonely forests. This framework improves sensitivity to sudden feature changes and detection robustness through a weighted fusion strategy of global trends and residual anomalies. This method provides efficient and reliable dynamic early-warning technology support for coal-mine gas disaster prevention and control, demonstrating significant engineering application value.