Application of Cloud Model in Rock Burst Prediction and Performance Comparison with Three Machine Learning Algorithms

• Published in: IEEE access Vol. 6; pp. 30958 - 30968
• Main Authors: Lin, Yun, Zhou, Keping, Li, Jielin
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Classification; Cloud model; Compressive strength; Entropy; Gaussian distribution; Indexes; Machine learning; normalization; Normalizing; performance comparison; Performance indices; Predictive models; rock burst; Rock masses; Rockbursts; Rocks; rough set; Stress; Tensile strength; Uncertainty
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2018.2839754

Rock burst is a common disaster in deep underground rock mass engineering excavation. In this paper, a cloud model (CM) is applied to classify and assess rock bursts. Some main factors that influence rock bursts include the uniaxial compressive strength (<inline-formula> <tex-math notation="LaTeX">\sigma _{\mathrm {\mathbf {c}}} </tex-math></inline-formula>), the tensile strength (<inline-formula> <tex-math notation="LaTeX">\sigma _{\mathrm {\mathbf {t}}} </tex-math></inline-formula>), the tangential stress (<inline-formula> <tex-math notation="LaTeX">\sigma _{\mathrm {\boldsymbol{\theta }}} </tex-math></inline-formula>), the rock brittleness coefficient (<inline-formula> <tex-math notation="LaTeX">\sigma _{\mathrm {\mathbf {c}}}/\sigma _{\mathrm {\mathbf {t}}} </tex-math></inline-formula>), the stress coefficient (<inline-formula> <tex-math notation="LaTeX">\sigma _{\mathrm {\boldsymbol{\theta }}}/\sigma _{\mathrm {\mathbf {c}}} </tex-math></inline-formula>), and the elastic energy index (<inline-formula> <tex-math notation="LaTeX">W_{\mathrm {\mathbf {et}}} </tex-math></inline-formula>), which are chosen to establish the evaluation index system. The weights of these indicators are obtained by the rough set method based on 246 sets of domestic and foreign rock burst samples. The 246 samples are classified by normalizing the data and establishing an RS-CM. The 10-fold cross validation was used to obtain higher generalization ability of models. The classification results of the RS-CM are compared with those of the Bayes, KNN, and RF methods. The results show that the RS-CM exhibits higher values of accuracy, Kappa, and three within-class classification metrics (recall, precision, and the F-measure) than the Bayes, KNN, and RF methods. Hence, the RS-CM, which is characterized by high discriminatory ability and simplicity, is a reasonable and appropriate approach to rock burst classification and prediction. Finally, the sensitivity of six indexes was investigated to take scientific and reasonable measures to prevent or reduce the occurrence of rock bursts.