During the past decade, coal dust and gas explosions have been most two serious types of disasters in China, threatening lives miners causing significant losses terms national property. In this paper, an evaluation model was constructed based on a fuzzy fault tree by taking Xingli Coal Mine as research site to identify risk factors explosions. Furthermore, hazards associated with such were evaluated for particular mine. After completing on-site investigation, probabilities basic events...

Methane is one of the most dangerous gases encountered in mining industry. During operations, methane can be broadly classified into three states: excavation, stoppage safety check, and abnormal concentration, which usually a precursor to gas accident, such as coal outburst. Consequently, it vital accurately predict concentrations. Herein, we apply deep learning methods—a recurrent neural network (RNN), long short-term memory (LSTM), gated unit (GRU)—to problem concentration prediction...

In this study, to further improve the prediction accuracy of coal mine gas concentration and thereby preventing accidents improving safety management, standard whale optimisation algorithm's (WOA) susceptibility falling into local optima, slow convergence speed, low single-factor long short-term memory (LSTM) neural network residual correction model are addressed. A new IWOA-LSTM-CEEMDAN is constructed based on improved algorithm (IWOA) IWOA-LSTM one-factor through use complete ensemble...

To investigate the mechanical properties and energy evolution laws of rocks under true triaxial unloading conditions, a study was conducted using rock testing system on three different types rocks: coal, sandy mudstone, siltstone. The examined behavior, failure patterns, fractal dimensions these conditions. tests revealed significant variations in stress–strain curves patterns among types. Observation indicated that with lower peak strength exhibited higher increased fragmentation upon...

Gas accidents threaten the safety of underground coal mining, which are always accompanied by abnormal gas concentration trend. The purpose this paper is to improve prediction accuracy so as prevent and level mine management. Combining LSTM model with LightGBM model, LSTM-LightGBM proposed variable weight combination method based on residual assignment, considers not only time subsequence feature data, but also nonlinear characteristics data. During data preprocessing, optimal parameters...

In order to improve the detonation performance of emulsion explosives, a new type explosives with TiH2 powders is developed. The influences amount sensitizers GMs and energetic additives on explosion characteristics are studied determine optimum compositions. Underwater brisance testing experiments show that, compared traditional sensitized shock wave specific impulse I total energy E GMs-TiH2 improved significantly, effect improving power better than that Ti powders. 23.80 mm compression...

The problem needs to be solved about stability control of small coal pillars along goaf in the mining process. In this paper, effects water reducer, accelerator and expansion agent on fluidity, setting time, ratio stone body strength grouting materials were analyzed through orthogonal experiments, optimal was obtained, it is applied engineering site obtain reinforcement effect pillar material pillar. results study show that: When dosage accelerating 4%, amount water-reducer 0.3%, expansive...

Using the Splitting Hopkinson Pressure Bar (SHPB) experimental system, investigations were made into dynamic mechanical performances of underground soft rocks. The experiments proved that measured stress–strain curves display characteristics plastic deformation. By making use a revised overstress constitutive formula for stress model and by taking account strain rate are function 1 − E(t)/E0, was simplified applying dimensional analysis consequently, obtained model. Then, consideration...

During the past decade, gas explosions have been one of most serious types disasters in China, threatening lives miners and causing significant losses terms national property. This article, by constructing fuzzy fault tree model explosion on coalface heading face, deduces minimum cut sets path tree, analyzes importance structure, obtains ratio explosion. The results show that isolation heat sources is effective way to prevent In addition, a close detection concentration appropriate treatment...

Abstract Coal mining under the geological conditions of a loose layer will lead to intensification surface movement and deformation, fault living slip fault. Mining both have great impact on safety coal production. To reveal evolution law coupling mechanism multi-physical fields overburden, numerical simulation method is used simulate with different thicknesses, analyze changes vertical stress key strata, subsidence, elastic energy zone activated area zone. The analysis shows that change...

Abstract Under the policy of achieving carbon peak before 2030, paper predicts whether Jiangsu province can achieve emissions 2030. Based on data from 2001 to 2018, uses Lasso regression model screen out 8 significant factors affecting emissions, sets values each influencing during 2019-2030, and BP neural network predict 2019-2030. The prediction results show that will in 2023 under hypothetical scenario, with 335.1755 million tons.