Coal and gas outbursts pose significant threats to underground personnel, making the development of accurate prediction models crucial for reducing casualties. By addressing the challenges of highly nonlinear relationships among predictive parameters, poor interpretability of models, and limited sample data in existing studies, this paper proposes an interpretable Ali Baba and the Forty Thieves–Transformer–Support Vector Machine (AFT-Transformer-SVM) model with high predictive accuracy. The Ali Baba and the Forty Thieves (AFT) algorithm is employed to optimise a Transformer-based feature extraction, thereby reducing the degree of nonlinearity among sample data. A Transformer-SVM model is constructed, wherein the Support Vector Machine (SVM) model provides negative feedback to refine the Transformer feature extraction, enhancing the prediction accuracy of coal and gas outbursts. Various classification assessment methods, such as TP, TN, FP, FN tables, and SHAP analysis, are utilised to improve the interpretability of the model. Additionally, the permutation feature importance (PFI) method is applied to conduct a sensitivity analysis, elucidating the relationship between the sample data and outburst risks. Through a comparative analysis with algorithms such as eXtreme gradient boosting (XGBoost), k-nearest neighbour (KNN), radial basis function networks (RBFNs), and Bayesian classifiers, the proposed method demonstrates superior accuracy and effectively predicts coal and gas outburst risks, achieving 100% accuracy in the sample dataset. The influence of parameters on the model is analysed, highlighting that the coal seam gas content is the primary factor driving the outburst risks. The proposed approach provides technical support for coal and gas outburst predictions across different mines, enhancing emergency response and prevention capabilities for underground mining operations.

Methane concentration anomalies during coal mining operations are identified as important factors triggering major safety accidents. This study aimed to address the key issues of insufficient adaptability of existing detection methods in dynamic and complex underground environments and limited characterization capabilities for non-uniform sampling data. Specifically, an intelligent diagnostic model was proposed by integrating the improved Dung Beetle Optimization Algorithm (SGDBO) with Transformer-SVM. A dual-path feature fusion architecture was innovatively constructed. First, the original sequence length of samples was unified by interpolation algorithms to adapt to deep learning model inputs. Meanwhile, statistical features of samples (such as kurtosis and differential standard deviation) were extracted to deeply characterize local mutation characteristics. Then, the Transformer network was utilized to automatically capture the temporal dependencies of concentration time series. Additionally, the output features were concatenated with manual statistical features and input into the LSSVM classifier to form a complementary enhancement diagnostic mechanism. Sine chaotic mapping initialization and a golden sine search mechanism were integrated into DBO. Subsequently, the SGDBO algorithm was employed to optimize the hyperparameters of the Transformer-LSSVM hybrid model, breaking through the bottleneck of traditional parameter optimization falling into local optima. Experiments reveal that this model can significantly improve the classification accuracy and robustness of anomaly curve discrimination. Furthermore, core technical support can be provided to construct coal mine safety monitoring systems, demonstrating critical practical value for ensuring national energy security production.

Mine ventilation network (MVN) regulation faces severe challenges: strong variable coupling, high search dimensionality, and the inherent conflict between energy conservation and safety constraints. To address these issues, we propose a novel airflow optimization framework integrating a Minimum Influence Spanning Tree (MIST), sensitivity attenuation boundaries, and an Improved Dung Beetle Optimizer (IDBO). Initially, high-influence co-tree chords are strategically extracted via MIST to compress the mathematical optimization dimensionality. Subsequently, effective ventilation resistance search intervals are bounded using sensitivity attenuation, preventing the algorithm from performing invalid searches in high-resistance regions. Furthermore, the standard DBO is enhanced via Fuchs chaotic initialization, Golden Sine and Lens Imaging collaborative learning, and differential mutation to minimize system power consumption. A 46-branch MVN case study validates the approach, identifying an 8-dimensional control combination as the absolute minimum requirement for full compliance. Compared to state-of-the-art baselines (DBO, SSA, WOA, DE), IDBO achieved the lowest power consumption. Post-optimization, the airflow constraint satisfaction rate improved from 89.13% to 100%, and total system power decreased by 11.87% (from 185.03 kW to 163.08 kW). Ultimately, this method robustly achieves Ventilation on Demand (VoD), providing a reliable computational tool for intelligent underground mining.

Ventilation network feature graphs (Q-H graphs) are a key visualisation tool for mine ventilation systems, and their automated generation reduces to a combinatorial optimisation problem over independent-path permutations. Existing methods, however, exhibit three limitations: a single-dimensional evaluation criterion, inadequate nodal pressure-energy assignment, and unstable convergence in factorial-scale search spaces. This paper proposes an adaptive NSGA-II (A-NSGA-II) framework with coordinated enhancements at the evaluation, modelling, and algorithmic levels. A three-objective system that minimises split-block count, topological-spatial discrepancy, and layout fragmentation is established, together with an aggregate evaluation score (AES) for engineering decision-making; nodal pressure energies are reconstructed via the longest path on a directed acyclic graph; and topology-aware initialisation, Lagrange three-point interpolated adaptive operators, and periodic memetic local search are integrated within NSGA-II. Experiments on two mine ventilation networks (75 and 112 branches) over 30 independent trials show that A-NSGA-II consistently outperforms four benchmarks (NSGA-II, MOEA/D, SPEA2, and MOSA) in terms of split-block count, AES, and hypervolume; statistical tests confirm significant, large-effect HV advantages on the 112-branch network, while the 75-branch network shows a 56.6–71.5% reduction in HV standard deviation.

This study develops an interpretable point-and-interval prediction method for mine ventilation-parameter identification using limited field samples. Guided by ventilation-resistance theory, eight engineering attributes—roadway length, width, height, cross-sectional area, wetted perimeter, equivalent diameter, support type, and cross-sectional shape—were selected, and a prediction dataset was constructed from 260 field samples. The extended Random Feature Model (xRFM) establishes a nonlinear mapping, and the proposed Evolution-Path Guided Ivy Algorithm (EPG-IVY) optimizes hyperparameters within the training data. Prediction intervals are then constructed from out-of-fold residuals using Adaptive Bandwidth Kernel Density Estimation (ABKDE), while SHAP is used to analyze the model’s dependence on engineering features. With a fixed 7:3 split, EPG-IVY-xRFM achieved R² = 0.9754, RMSE = 0.001600, and MAE = 0.001162. Repeated nested five-fold cross-validation yielded R² = 0.9719 ± 0.0084, RMSE = 0.001675 ± 0.000267, and MAE = 0.001225 ± 0.000182, with lower RMSE and MAE than the optimized XGBoost and CatBoost baselines. External validation on 28 independent samples from Balasu Coal Mine yielded R² = 0.890, RMSE = 0.007072, and MAE = 0.003873. The empirical coverage of the 90% ABKDE prediction interval was 0.8846, and its Wilson 95% confidence interval included the nominal coverage level. SHAP results identified support type, roadway width, and equivalent diameter as the main contributing factors in the current model. These results provide a data-driven framework for friction resistance coefficient identification with point prediction, uncertainty estimation, and feature attribution under limited field samples.