相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Feiyue Sun et al.
Electronic Journal of Structural Engineering
(2023)
Article
Engineering, Geological
Mingliang Li et al.
Summary: Intelligent prediction of rock bursts is of great significance in rock mechanics research and engineering applications. A new method based on a Bayes-optimized convolutional neural network (BOCNN) was proposed for intelligent rockburst prediction. Six prediction models were built and evaluated using various indicators. The study showed that the intelligent rockburst prediction system can provide technical support and a scientific basis for predicting rockburst hazards and designing support structures in various projects.
INTERNATIONAL JOURNAL OF GEOMECHANICS
(2023)
Article
Geosciences, Multidisciplinary
Ying-hao Lou et al.
Summary: This paper proposes a rockburst rating evaluation method based on principal component analysis and the catastrophe progression method, which takes into account several influencing factors. The method can accurately predict the occurrence of rockburst hazards.
FRONTIERS IN EARTH SCIENCE
(2023)
Article
Engineering, Geological
Binzhong Zhu et al.
Summary: This study establishes a multi-factor rockburst criterion based on the elastic strain energy and properties of surrounding rock mass. The results indicate that the distribution of stress and releasable elastic energy in surrounding rock mass remains consistent under different buried depths, and the occurrence of rockburst correlates with areas of larger elastic strain energy release. Increasing buried depth increases the probability of rockburst. These findings can enhance understanding of rockburst mechanism and aid in rockburst prediction.
GEOTECHNICAL AND GEOLOGICAL ENGINEERING
(2022)
Article
Mathematics
Barkat Ullah et al.
Summary: Accurate prediction of short-term rockburst is crucial for improving worker safety in mining and geotechnical projects. This study utilized t-distributed stochastic neighbor embedding (t-SNE), K-means clustering, and extreme gradient boosting (XGBoost) to predict the risk of short-term rockburst. The proposed model achieved high accuracy in predicting rockburst levels, providing a valuable benchmark for future predictions.
Article
Computer Science, Artificial Intelligence
Meichang Zhang
Summary: This paper studied the rockburst risk prediction method based on particle swarm algorithm and neural network, using BP neural network for impact risk assessment and optimizing connection weights with PSO algorithm to improve accuracy; Experimental results show that the evaluation accuracy of the PSO-BP model is increased by 15% compared with the standard BP model.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Engineering, Geological
Deping Guo et al.
Summary: In this study, a multivariate adaptive regression splines (MARS) model and a novel deep forest algorithm were used to predict and classify rockburst intensity with 344 worldwide rockburst cases. The t-distributed stochastic neighbor embedding method (t-SNE) was utilized for visualization and dimensionality reduction, and the Gaussian mixture model was employed to determine rockburst intensity. The study showed that the proposed models have the capability to assess and forecast rockburst risk, with the most important features being sigma(theta) and sigma(c).
Article
Engineering, Geological
Mohammad Hossein Kadkhodaei et al.
Summary: This paper develops a semi-quantitative risk matrix model to assess rockburst risk. Two models are developed using the logistic model tree method to quantitatively determine the probability and consequence of rockburst. The results show that both models have high accuracy and comparable performance to previous models. A framework is provided based on these models to evaluate rockburst risk and reduce casualties during design and construction phases in underground spaces.
GEOTECHNICAL AND GEOLOGICAL ENGINEERING
(2022)
Article
Engineering, Geological
Shaojun Li et al.
Summary: This paper proposes an integrated method using combination weighting and matter-element extension theory for rockburst hazard prediction in the Bayu Tunnel. The method constructs a rockburst tendency evaluation index system by introducing several evaluation indexes, and determines the weight of each index using methods like triangular fuzzy number analytic hierarchy process. The prediction of rockburst grade is carried out using matter-element extension theory. The applicability and superiority of selected rockburst control factors are verified and discussed. The research results provide a new analysis method and technical means for rockburst tendency assessment in deep tunnels.
ENGINEERING GEOLOGY
(2022)
Article
Mathematics
Shaohong Yan et al.
Summary: Rock burst disasters pose a serious threat to underground high-stress rock mass mining and excavation engineering, and their classification prediction is crucial for reducing such hazards. This study utilized extensive sample data to establish an Intelligent Rock burst Identification System (IRIS) based on an optimized SVM model, which showed higher prediction accuracy compared to traditional SVM models. The results were consistent with the actual rock burst intensity, validating the effectiveness of the approach.
Article
Geosciences, Multidisciplinary
Weizhang Liang et al.
Article
Computer Science, Artificial Intelligence
Ran Liu et al.
NEURAL COMPUTING & APPLICATIONS
(2019)
Review
Construction & Building Technology
Sajjad Afraei et al.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2019)
Article
Engineering, Environmental
Yiguo Xue et al.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2019)
Article
Metallurgy & Metallurgical Engineering
Ke-ping Zhou et al.
TRANSACTIONS OF NONFERROUS METALS SOCIETY OF CHINA
(2016)
Article
Engineering, Industrial
Zhou Jian et al.
