Predicting rock burst hazard with incomplete data using Bayesian networks

• Published in: Tunnelling and underground space technology Vol. 61; pp. 61 - 70
• Main Authors: Li, Ning, Feng, Xianda, Jimenez, R.
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01-01-2017; Elsevier BV
• Subjects: Bayesian analysis; Bayesian networks; Bursting; Case histories; Casualties; Compressive strength; Cross-validation; Deformation; Incomplete data; Maximum tangential stress; Predictions; Rock burst; Sensitivity analysis; Structural damage; Tensile strength; Tree augmented Naïve Bayes classifier; Sensitivity analysis; Cross-validation; Tree augmented Naïve Bayes classifier; Incomplete data; Bayesian networks; Maximum tangential stress; Rock burst
• ISSN: 0886-7798; 1878-4364
• DOI: 10.1016/j.tust.2016.09.010

•Proposed a tree augmented Naïve Bayes classifier to predict the probability of rock burst occurrence.•Our approach can deal with incomplete input data and make predictions.•Improves the predictive capability and reduces database completeness requirement of previous models.•Sensitivity analysis points out the most influential parameter.
Rock burst is a dynamic process of sudden, rapid and violent release of elastic energy accumulated in rock and coal masses during underground activities. It can lead to casualties, to failure and deformation of the supporting structures, and to damage of the equipment on site; hence its prediction is of great importance. This paper presents a novel application of Bayesian networks (BNs) to predict rock burst. Five parameters —Buried depth of the tunnel (H), Maximum tangential stress of surrounding rock (MTS) (σθ), Uniaxial tensile strength of rock (UTS) (σt), Uniaxial compressive strength of rock (UCS) (σc) and Elastic energy index (Wet)— are adopted to construct the BN with the Tree augmented Naïve Bayes classifier structure. The Expectation Maximization algorithm is employed to learn from a data set of 135 rock burst case histories, whereas the belief updating is carried out by the Junction Tree algorithm. Finally, the model is validated with 8-fold cross-validation and with another new group of incomplete case histories that had not been employed during training of the BN. Results suggest that the error rate of the proposed BN is the lowest among the traditional criteria with capability to deal with incomplete data. In addition, a sensitivity analysis shows that MTS is the most influential parameter, which could be a guidance on the rock burst prediction in the future.