Method for Quickly Identifying Mine Water Inrush Using Convolutional Neural Network in Coal Mine Safety Mining

Fang, Bo

doi:10.1007/s11277-021-08452-w

Cited by 20 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The lowest point of the bottom slab fracture development starts 8.95 m from the coal seam 15 Geofluids floor. However, according to the empirical formula (7) for the bottom slab damage zone used by the researchers, the bottom slab damage depth is 20.30 m when working face 9211 is mined via the conventional collapse method. Therefore, using this PFM method reduces the bottom slab damage depth by 11.35 m compared to the traditional collapse method.…”

Section: Evolution Of the Pore Water Pressure During Miningmentioning

confidence: 99%

“…In mining, mine water is not only a groundwater resource but also a potential threat that has become more important due to increases in mining depths and therefore the hydraulic pressures [5,6]. More than 25 billion tons of coal resources are at risk of water inrush from the floor, especially in deep Permo-Carboniferous coal seams in the central and eastern parts of northern China [7][8][9][10][11]. Therefore, determining how to exploit resources threatened by a floor water inrush is an important main problem for scientific researchers and is important to continued mine development.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application and Research of Gangue Partial-Filling Mining Method in Preventing Water Inrush from Floor

et al. 2022

View full text Add to dashboard Cite

Coal gangue produced during coal production not only poses a serious threat to the ground environment but also imposes serious economic burdens on the mine. The partial-filling mining (PFM) method proposed in this paper can make full use of coal gangue and is of great significance to the prevention and control of water disasters at the working face. The specific process used to implement this method is to first divide the working face into several narrow working faces and then fill the filling body into part of the goaf. The ability of PFM to restrain floor water inrush is analyzed by physical simulation, and the field application research is carried out at the No. 9211 mining face of Bucun Coal Mine in Shandong, China. The physical simulation results show that the failure depth of this layer is less than 5 m. The field measurements reveal that the maximum compression deformation of the filling body is 89.1 mm, and the maximum floor failure depth of the floor is only 8.6 m. Comparative analysis indicates that the floor failure depth of the No. 9211 working face with the local filling method is 4.6 m lower than that of the No. 9110 working face with the strip mining method. In addition, no water inrush accident occurs at the No. 9211 working face during mining. Therefore, PFM not only controls the floor damage depth effectively but also consumes coal gangue to protect the mine environment.

show abstract

Section: Evolution Of the Pore Water Pressure During Miningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application and Research of Gangue Partial-Filling Mining Method in Preventing Water Inrush from Floor

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Moreover, there is no systematic standard to verify the evaluation of the method for confined water disaster prevention and control effect of deep coal seam mining. The main problem is that the geological conditions of deep mining areas are different [13][14][15][16][17]. Therefore, the schemes for preventing and controlling water disasters are also different in these mining areas.…”

Section: Introductionmentioning

confidence: 99%

Evaluation Method of Water Hazard Control Effect of Coal Seam Floor in Deep Mining: Sequence Verification Evaluation

Wang

Chen

et al. 2022

Geofluids

View full text Add to dashboard Cite

Deep, highly pressurized aquifers seriously threaten the exploitation of resources of North China coalfield. At present, there is no particular guidance system to evaluate the prevention and control effect of water inrush disaster in deep coal seam mining. Therefore, this research focuses on the evaluation of the method for confined water disaster prevention and control effect of deep coal seam mining. Based upon various methods, such as effective thickness and water resistance capacity of aquifuge, water inrush coefficient, GIS (Geographic Information System) analysis of grouting data, dense drilling verification, and professional analysis system based on integrated sequence evaluation, the evaluation of the method for confined water disaster prevention and control effect of deep coal seam mining was put forward for the first time. The proposed method was called the “sequence verification evaluation (SVE)” method. The prevention and control of the effects of Ordovician water inrush disaster in deep mining of Huanghebei coalfield was evaluated using the proposed SVE method. The results show that the SVE method can effectively reflect the prevention and control of the effects of water inrush from confined water and provide scientific basis for the safe production of deep coal seam mining.

show abstract

“…Combining machine learning methods with water chemistry ions to construct discriminant models is necessary. Many scholars have achieved fruitful results by introducing machine learning methods into the identification of mine water sources, such as Support Vector Machines, Naive Bayes 15 , Back Propagation Neural Networks 16 , Logistic Regression Analysis 17 , and Random Forest 18,19 . All of the above methods can solve most practical problems.…”

mentioning

confidence: 99%

Identification of mine water source based on TPE-LightGBM

Wang,

Zhang,

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Mine water inrush is a serious threat to mine safety production. It is very important to identify water inrush source types quickly to prevent and control water damage. In this study, the aqueous chemical components Na+ + K+, Ca2+, Mg2+, Cl−, SO42− and HCO3− of different aquifers in Pingdingshan coalfield were selected as the characteristic values, and the Surface water, Quaternary pore water, Carboniferous limestone karst water, Permian sandstone water, and Cambrian limestone karst water were used as the labels. An intelligent water source discrimination model is proposed by combining data mining, classification models, and reinforcement learning. As outlier data in the samples may interfere with the model recognition ability, the data distribution range was analyzed using box plots, and 20 groups of abnormal samples were excluded. The processed water chemistry data were divided into 80% learning samples and 20% test samples, and the learning samples were fed into a light gradient boosting machine (LightGBM) for training. The tree-structured parson estimator (TPE) obtains the optimal values of the main parameters of LightGBM in a very short time. Substituting the hyperparameters back into the model yields a 13.9% improvement in the accuracy of the model, proving the effectiveness of the TPE algorithm. To further validate the performance of the model, TPE-LightGBM is compared and analyzed with a Random Search-Multi Layer Perceptron Machine (RS-MLP) and Genetic Algorithm-Extreme Gradient Boosting Tree (GA-SVM). The accuracy of TPE-LightGBM, RS-MLP, and GA-SVM is 0.931, 0.759, 0.724 in that order, and the generalization error RMSE is 0.415, 1.05, and 1.313 in that order. The results show that TPE-LightGBM is more advantageous in water source identification and is more resistant to overfitting. By calculating and comparing the information gain of each variable, the contribution of Ca2+ is the highest, so it is necessary to pay attention to the change in Ca2+ concentration. TPE-LightGBM’s high accuracy and generalization ability have a good prospect for the identification of sudden water source types.

show abstract

Method for Quickly Identifying Mine Water Inrush Using Convolutional Neural Network in Coal Mine Safety Mining

Cited by 20 publications

References 21 publications

Application and Research of Gangue Partial-Filling Mining Method in Preventing Water Inrush from Floor

Application and Research of Gangue Partial-Filling Mining Method in Preventing Water Inrush from Floor

Evaluation Method of Water Hazard Control Effect of Coal Seam Floor in Deep Mining: Sequence Verification Evaluation

Identification of mine water source based on TPE-LightGBM

Contact Info

Product

Resources

About