Rockburst Prediction Using Gaussian Process Machine Learning
Guoshao Su, Ke‐Shi Zhang, Zhi Chen · 2009
Rockburst is a geological disaster occurred usually in deep mines. Because of poor understanding of the mechanism and influence factors of rockburst, it is very difficult to give accurate prediction using conventional methods. A new model based on Gaussian process (GP), which is a probabilistic kernel machine leaning and has become a power tool for solving highly nonlinear problems, therefore, is proposed. At first, case histories of rockburst occurrence with the real records of rockburst intensity and influence factors of rockburst are collected and are taken as prior knowledge to be learned by GP binary classification machine learning tech, where, maximum tangential stress in surround rockmass, uniaxial compressive strength, tensile strength of rock, and rockburst tendency index of rock, which can reflect the internal and exterior conditions of rockburst occurrence nicely are suggested to be main influential factors of rockburst. Then, the nonlinear mapping relationship between rockburst intensity and its influence factors can be established easily by GP model. Finally, prediction for the novel conditions in deep mines can be obtained using the model. The new model is applied in prediction for rockburst intensity at practical projects in China, Norway and USSR. Results of case study show the model is feasible, effective and simple to implement for rockburst prediction.