An Attempt to Use Machine Learning Algorithms to Estimate the Rockburst Hazard in Underground Excavations of Hard Coal Mine

Wojtecki, Łukasz; Iwaszenko, Sebastian; Apel, Derek B.; Cichy, Tomasz

doi:10.3390/en14216928

Cited by 22 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ANN in Ulivieri’s study showed good discrimination, with an AUC of 0.8 by external validation 40 . Machine learning approaches were also applied to develop geological prediction models which provided the triage solutions to predict an occurance of rockburst during underground rock excavations 41 , 42 . We also figured out that the averaged AUROC values of the four tools in our study were higher than ones of FRAX models which were calculated at 0.796 and 0.768 respectively 43 .…”

Section: Discussionmentioning

confidence: 99%

“…Similarly to our methods, the indices (precision, recall, F1-core) were estimated to evaluate the performance of machine learning algorithms 41 , 42 . Ullah et al developed Extreme Gradient Boosting (XGBoost) model with support from K-means clustering and an enhanced stochastic neighbour embedding (SNE) Based t-SNE algorithm to predict the risk of rockburst 42 .…”

Section: Discussionmentioning

confidence: 99%

“…The XGBoost was then evaluated by the estimation of precision, recall and F1-score 42 . In addition, Wojtecki et al applied 16 machine learning models to forecast the risk of rockburst caused by tremors 41 . The recall, precision, and F1-score were also applied to assess the accuracy of included models 41 .…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting the risk of osteoporosis in older Vietnamese women using machine learning approaches

Bui

Hà

Pham

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Osteoporosis contributes significantly to health and economic burdens worldwide. However, the development of osteoporosis-related prediction tools has been limited for lower-middle-income countries, especially Vietnam. This study aims to develop prediction models for the Vietnamese population as well as evaluate the existing tools to forecast the risk of osteoporosis and evaluate the contribution of covariates that previous studies have determined to be risk factors for osteoporosis. The prediction models were developed to predict the risk of osteoporosis using machine learning algorithms. The performance of the included prediction models was evaluated based on two scenarios; in the first one, the original test parameters were directly modeled, and in the second the original test parameters were transformed into binary covariates. The area under the receiver operating characteristic curve, the Brier score, precision, recall and F1-score were calculated to evaluate the models’ performance in both scenarios. The contribution of the covariates was estimated using the Permutation Feature Importance estimation. Four models, namely, Logistic Regression, Support Vector Machine, Random Forest and Neural Network, were developed through two scenarios. During the validation phase, these four models performed competitively against the reference models, with the areas under the curve above 0.81. Age, height and weight contributed the most to the risk of osteoporosis, while the correlation of the other covariates with the outcome was minor. Machine learning algorithms have a proven advantage in predicting the risk of osteoporosis among Vietnamese women over 50 years old. Additional research is required to more deeply evaluate the performance of the models on other high-risk populations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting the risk of osteoporosis in older Vietnamese women using machine learning approaches

Bui

Hà

Pham

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…With the deep mining of coal seam, the problems of coal-rock dynamic disaster prevention and control such as rockburst have been paid more attention. − In this context, researchers have studied various problems arising in the process of rockburst, for example, the internal or external causes of rockburst, , the risk assessment of rockburst accident, − the law of coal-rock cracking, the law of impact signal transmission, etc. In these research fields, coal-rock dynamic disaster prediction plays an important role, which is directly related to the safety of life and property.…”

Section: Introductionmentioning

confidence: 99%

Coupling Mechanism of Dissipated Energy–Infrared Radiation Energy of the Deformation and Fracture of Composite Coal-Rock under Load

Yang

et al. 2022

ACS Omega

View full text Add to dashboard Cite

The fracture of composite coal-rock under load is the process of energy conversion. As the dissipative energy composition, there is a correlation between the infrared radiation energy and the coal-rock states. Based on theories of theoretical mechanics, modern quantum mechanics, thermodynamics, and other disciplines, first, this paper explained the causes of infrared radiation energy in the process of coal-rock fracture by using the microanalysis method. After that, the mathematical model of dissipation energy−infrared radiation energy coupling was deduced and established, and the experimental analysis was carried out under different loading conditions. The analysis shows that the conversion of mechanical energy and internal energy in the process of loading caused constant collisions between molecules in coal-rock, which led to a temperature rise. After entering the excited state, molecules have to transition to a lower energy level, which generates infrared radiation. The experimental results show that there was a strong correlation between energy characteristic parameters, which is consistent with the established relationship. In addition, the energy conversion and dissipated energy changes in the loading process had stages. Before the elastic−plastic stage, the dissipated energy obtained by coal-rock energy conversion was less, but it increased rapidly in the later stage, which eventually led to the fracture of coal-rock. In the early elastic−plastic period, infrared radiation energy was the main component of the dissipated energy and its variation trend was consistent with the dissipated energy. After that, the infrared radiation energy remained stable, but the dissipation energy still increased. At this time, infrared radiant energy was no longer the main component of dissipated energy. And the infrared radiation energy dropped rapidly before coal-rock fracture, which had certain precursory characteristics. The coupling mechanism of dissipated energy−infrared radiation energy can be used to explain the failure reason of composite coal-rock under different loading conditions from the perspective of energy, which will provide a new idea for assisting the prediction of coal-rock dynamic disasters.

show abstract

“…Due to the rapid development of China's economy, large quantities of coal resources in shallow mining have been basically depleted, so the mining of most coal resources has moved to the deep-lying stratum [1][2][3]. With the increase in the mining depth, both the frequency and intensity of the coal mining engineering risk in the underground stope are increasing, such as rock burst, soft rock large deformation, water inrush and flowing deformation [4][5][6], which brings tremendous threat to the efficient mining of coal resources and the safety of miners. For the deep soft rock mining roadway, the structural instability and nonlinear large deformation of surrounding rock are the most common problems with the stress environment's deterioration [7].…”

Section: Introductionmentioning

confidence: 99%

Analytical Approach Based on Full-Space Synergy Technology to Optimization Support Design of Deep Mining Roadway

Zhang

Yin

2022

Minerals

View full text Add to dashboard Cite

The stability of surrounding rock is the basic guarantee of underground space engineering safety. The large deformation of a roadway’s surrounding rock is a very common phenomenon during the underground excavation of coal mine roadways or coal mining, especially in deep soft rock mining roadways. With the increase in mining depth and mining stress, it is very important to prevent disasters caused by surrounding rock deformation. This work aims to conduct an optimization design of roadway support for deep soft rock in coal mines using a full-space synergy control technology. FLAC3D-based orthogonal numerical experiments are adopted to study the influence of bolt parameters and plastic yield zone variation on the deformation of roadway surrounding rock, which provides a basis for optimizing the support design of coal mine roadways. According to the results of the numerical analysis, the optimal support parameters are determined as 20 mm, 2.2 m and 700–900 mm for diameter, length and interval of the bolt, respectively. Finally, the determined bolt-shotcrete net beam support scheme from the full-space synergy control idea is used in a study case. Results illustrate that this study can provide reliable guidance for the stability control of deep soft rock roadways in mining fields under high stress, and it can work well to keep the surrounding rock deformation within the safe limits.

show abstract

An Attempt to Use Machine Learning Algorithms to Estimate the Rockburst Hazard in Underground Excavations of Hard Coal Mine

Cited by 22 publications

References 31 publications

Predicting the risk of osteoporosis in older Vietnamese women using machine learning approaches

Predicting the risk of osteoporosis in older Vietnamese women using machine learning approaches

Coupling Mechanism of Dissipated Energy–Infrared Radiation Energy of the Deformation and Fracture of Composite Coal-Rock under Load

Analytical Approach Based on Full-Space Synergy Technology to Optimization Support Design of Deep Mining Roadway

Contact Info

Product

Resources

About