Research on the classification model of coal’s bursting liability based on database with large samples

Wang, Changhao; Song, Dazhao; Zhang, Chengliang; Liu, Lei; Zhou, Zhen; Huang, Xuchao

doi:10.1007/s12517-019-4562-2

Cited by 15 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Index selection is essential in studying of CBL classification by machine learning methods. Referring to previous studies 7 , 16 , 30 , duration of dynamic fracture ( DT ), elastic strain energy index ( W ET ), bursting energy index ( K E ), and uniaxial compressive strength ( R C ) as the classification indexes were selected and divided the CBL level into three classes: strong (class 1), weak (class 2), and none (class 3), and they are considered as the output of machine learning model.…”

Section: Methodsmentioning

confidence: 99%

“…Guo 18 determined the grey distance correlation degree of the evaluation object through the grey correlation analysis, constructed the grey identification model for CBL classification according to the minimum membership degree principle. Wang et al 7 applied Mahalanobis distance discriminant analysis (DDA) method to establish a DDA model for CBL classification based on 95 groups of training samples.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of coal bursting liability of some chinese coals using machine learning methods

Wang,

Liu,

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

The classification of coal bursting liability (CBL) is essential for the mitigation and management of coal bursts in mining operations. This study establishes an index system for CBL classification, incorporating dynamic fracture duration (DT), elastic strain energy index (WET), bursting energy index (KE), and uniaxial compressive strength (RC). Utilizing a dataset comprising 127 CBL measurement groups, the impacts of various optimization algorithms were assessed, and two prominent machine learning techniques, namely the back propagation neural network (BPNN) and the support vector machine (SVM), were employed to develop twelve distinct models. The models’ efficacy was evaluated based on accuracy, F1-score, Kappa coefficient, and sensitivity analysis. Among these, the Levenberg–Marquardt back propagation neural network (LM-BPNN) model was identified as superior, achieving an accuracy of 96.85%, F1-score of 0.9113, and Kappa coefficient of 0.9417. Further validation in Wudong Coal Mine and Yvwu Coal Industry confirmed the model, achieving 100% accuracy. These findings underscore the LM-BPNN model’s potential as a viable tool for enhancing coal burst prevention strategies in coal mining sectors.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classification of coal bursting liability of some chinese coals using machine learning methods

Wang,

Liu,

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, CBM is one of the main disasters restricting the safe production of coal mines, and its efficient mining is a fundamental measure for mine disaster management (Zheng et al, 2019;Zhou et al, 2019;Zou Q. L. et al, 2020) and resource utilization. Meanwhile, CH 4 , the main component of CBM, is used as a greenhouse gas (Wang et al, 2019;Li et al, 2021a). Its greenhouse effect is 21-25 times that of CO 2 , which has a huge impact on the environment and climate.…”

Section: Introductionmentioning

confidence: 99%

Influence of geological structures on the occurrence of coalbed methane in Sima coal mine, China

Zhang

et al. 2022

Front. Earth Sci.

View full text Add to dashboard Cite

Geological structures of Sima coal mine in Shanxi Province were analyzed to understand the control effect of the geological structures on the occurrence of coalbed methane (CBM) in coal seam #3 of Sima coal mine. The CBM contents in the districts #2 and #3 of Sima coal mine were tested, and the effects of buried depth, fault and collapse column on the distribution of coalbed methane content are studied. The research results showed that: 1) The average content of CBM has a linear relationship with buried depth and overburden thickness, but in the smallscale range of buried depth, the dispersion between CBM and buried depth is very large. 2) Faults and collapse columns significantly affect the content of local CBM nearby, but from the largescale range such as the whole mining area, the average value of CBM content at a certain buried depth will not be affected by faults and collapse columns. 3) In the hanging wall of F29 normal fault, it is roughly estimated that the average escape rate of CBM near the fault is 13.9%, while in the footwall of F29 normal fault, this value is 0.7%–1.1%. The results show that there is a significant difference in the influence of the fault on the CBM content in the hanging wall and footwall. 4) The control effect of collapse column on CBM occurrence is related to the development height of collapse column, the cementation degree of collapse column, groundwater runoff conditions and other factors. It can be divided into three categories: aggregation action, escape action (such as collapse column X8) and no obvious effect (such as collapse column DX7).

show abstract

“…Moreover, as a small tunnel, the deformation and creep will inevitably occur in the case of in situ stress and excavation interference. , The foamed polyurethane has great elasticity and compressibility, and the hardness of the foamed polyurethane is far smaller than that of the coal rock, which cannot effectively support the borehole shape. This results in the continuous formation of cracks around the borehole in the sealed section after the hole sealing (the gas leakage channel is in the second stage). − …”

Section: Introductionmentioning

confidence: 99%

Experimental Study on the Cement-Based Materials Used in Coal Mine Gas Extraction for Hole Sealing

Wang

et al. 2021

ACS Omega

View full text Add to dashboard Cite

Gas drainage is an important method to prevent and control gas disasters. Sealing materials have an important impact on the gas drainage effect. To improve the extraction rate, the configuration and related characteristics of sealing materials were studied in this study. It was found that the fluidity increased gradually with the increase of the dosage of the suspension concentrate (SC). The water−cement ratio was directly proportional to the setting time of the slurry. Also, the mixing amount of the special cement was inversely proportional to the setting time of the slurry. The influence of the amount of foaming agent, special cement, and suspending agent on the expansion rate of the slurry was positive, and the influence gradually weakened. When the water−cement ratio of cement-based materials was 0.6, the special cement content percentage was 6, the suspension agent content percentage was 3, the plasticizer content percentage was 0.7, the early strength agent content percentage was 1.2, and the foaming agent content percentage was 0.2, the sealing effect was the best. The research results suggest that the porosity and pore length of the cement-based material are smaller than those of polyurethane, and its sealing property was better. This could further increase the sealing effect of the gas borehole, thereby facilitating gas extraction.

show abstract

Research on the classification model of coal’s bursting liability based on database with large samples

Cited by 15 publications

References 9 publications

Classification of coal bursting liability of some chinese coals using machine learning methods

Classification of coal bursting liability of some chinese coals using machine learning methods

Influence of geological structures on the occurrence of coalbed methane in Sima coal mine, China

Experimental Study on the Cement-Based Materials Used in Coal Mine Gas Extraction for Hole Sealing

Contact Info

Product

Resources

About