Self-adaptive prediction and prewarning model of mine gas concentration
Abstract In order to expand the function of safety monitoring and control system in coalmine, and realize the accurate real-time prediction and reliable prewarning of mine gas concentration, study the self-adaptive prediction and prewarning method for gas concentration based on Empirical Mode Decomp...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-07-01
|
| Series: | Discover Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-025-07373-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract In order to expand the function of safety monitoring and control system in coalmine, and realize the accurate real-time prediction and reliable prewarning of mine gas concentration, study the self-adaptive prediction and prewarning method for gas concentration based on Empirical Mode Decomposition (EMD) and Gaussian Process Regression (GPR). The gas monitoring data were decomposed into several Intrinsic Mode Function (IMF) with different time scales by using EMD processing, and the GPR model was established by using phase space reconstruction. In prediction process, the prediction accuracy was evaluated by using prediction availability, and the IMFs’ phase space parameters and the GPR hyperparameters were adjusted dynamically to achieve the best prediction accuracy. The case study shows that the prediction accuracy of EMD-GPR was significantly higher than the direct GPR prediction, so the IMFs’ phase space parameters and the GPR hyperparameters need dynamically adjust to get the best prediction results, which indicates that the EMD processing make the fluctuation features of gas concentration clear in certain time scale, and determining the appropriate phase space parameters of the IMF and the GPR hyperparameters can realize self-adaptive prediction to improve the prediction accuracy, which solved the problem of low prediction accuracy at mutational points in gas concentration time series, and improves the reliability of gas concentration prewarning. |
|---|---|
| ISSN: | 3004-9261 |