Due to the complex spatial hierarchy and large network scale of the mine ventilation system, it is difficult to obtain ventilation information of all branches in real-time, accurately, and comprehensively by arranging sensors. To overcome this difficulty, this paper proposes an optimal layout method of sensors based on the DETMAX algorithm and Tabu search algorithm. Given a known number of sensors, the proposed method can efficiently select an optimal set of branches to arrange these sensors according to the calculated airflow of each branch while considering both the air resistance error and the sensor error. This optimized sensor layout can minimize the airflow error of the undetected branches and obtain the ventilation information of the entire ventilation system accurately with a limited number of sensors. The proposed method has significant economic benefits and can provide technical support for developing intelligent ventilation systems. Finally, the performance and efficiency of this method are verified by comparing it with the Monte Carlo algorithm and the Ant Colony algorithm with data from the Wangjialing coal mine in China.

In order to effectively reduce the risk of subway fires and to improve the safety of passengers, a review of the background to subway fires employing literature and comparative analyses, computer simulation, expert consultation, and other research methods has been employed to conduct an in-depth study of subway fire risk assessment and control measures. A subway fire risk assessment model based on analysis theory was established. Firstly, a subway fire risk evaluation index system was developed, and the weight values of each level were determined using the interval analytic hierarchy process (IAHP), then the evaluation was derived using the fuzzy evaluation method, and the passenger distribution simulation was introduced to improve the objectivity of the evaluation. The results show that the fire evaluation of this subway system is safe. The results show that a subway fire risk assessment model may provide a scientific basis for establishing prevention and control measures, extinguishing methods, passenger safety evacuation schemes, and carrying out fire safety management activities during subway operations.

The research analyzes and improves upon the concept of ventilation safety subregions in coal mines and proposes a partition method based on the breadth-first search algorithm for assessing the quality of the ventilation. This involves the analysis of the function of ventilation subregions and of ventilation gas-monitoring data. Then, using the so-called ventilation sensitivity matrix as the analysis method, we confirm the consistency of considering safety subregions, which are associated with air consumption places as the core concept and the objective positioning of the safety subregions within the ventilation analysis. This allows us to establish the validity and practicability of employing regional characteristic information of mine ventilation and gas concentrations in the mines air. Finally, based on the characteristics of the ventilation subregions, ventilation air quantity network maps with safety subregions are proposed and their application is demonstrated. The advantages and characteristics of using these maps to replace ventilation network maps for ventilation analysis are demonstrated.

This study addresses the problems of multi-source data redundancy, insufficient feature capture timing, and delayed risk warning in the prediction of gas concentration in fully mechanized coal-mining operations by constructing a three-pronged technical approach that integrates feature dimensionality reduction, hybrid modeling, and intelligent early warning. First, sparse kernel principal component analysis (SKPCA) is used to accomplish the feature decoupling of multi-source monitoring data, and its optimal dimensionality reduction performance is verified using long-term and short-term neural networks (LSTMs). Second, an innovative TCN–Transformer hybrid architecture is proposed. The transient fluctuation characteristics of gas concentration are captured using causal dilation convolution, while a multi-head self-attention mechanism is used to analyze the cross-scale correlation of geological mining parameters. A flood optimization algorithm (FLA) is used to establish a hyperparameter collaborative optimization framework. Compared to TCN-LSTM, CNN-GRU, and other hybrid models, the hybrid model proposed in this study exhibits superior point prediction performance, with a maximum R² of 0.980988. Finally, a dynamic confidence interval is established using the locally weighted kernel density estimation (LWD-KDE) method with an optimized bandwidth, and an unsupervised early warning mechanism for the risk of gas concentration fluctuations in coal mines is constructed. The results provide a comprehensive approach to preventing and controlling gas disasters in fully mechanized mining operations. This research effectively promotes the transformation and upgrading of coal-mine-safety-monitoring systems to an active defense paradigm.

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.

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.