An Intelligent Rockburst Prediction Model Based on Scorecard Methodology

Honglei Wang,Aleksei Sobolev,Zhenlei Li,Majid Khan,Xueqiu He,Dazhao Song

doi:10.3390/min11111294

Abstract

Rockburst is a serious hazard in underground engineering, and accurate prediction of rockburst risk is challenging. To construct an intelligent prediction model of rockburst risk with interpretability and high accuracy, three binary scorecards predicting different risk levels of rockburst were constructed using ChiMerge, evidence weight theory, and the logistic regression algorithm. An intelligent rockburst prediction model based on scorecard methodology (IRPSC) was obtained by integrating the three scorecards. The effects of hazard sample category weights on the missed alarm rate, false alarm rate, and accuracy of the IRPSC were analyzed. Results show that the accuracy, false alarm rate, and missed alarm rate of the IRPSC for rockburst prediction in riverside hydropower stations are 75%, 12.5%, and 12.5%, respectively. Setting higher hazard sample category weights can reduce the missed alarm rate of IRPSC, but it will lead to a higher false alarm rate. The IRPSC can adaptively adjust the threshold and weight value of the indicator and convert the abstract machine learning model into a tabular form, which overcomes the commonly black box problems of machine learning model, as well as is of great significance to the application of machine learning in rockburst risk prediction.

Highlights

Published: 22 November 2021Rockburst is a phenomenon caused by mining unloading, in which the internal elasticity of the rock is suddenly released, resulting in bursting, spalling, spraying, and throwing of material [1,2,3]
Rockburst prediction methods can be divided into two categories: the empirical approach and mathematical models, with mathematical models divided into uncertainty theory algorithmic models and machine learning models [8,9]
Ratios of Safety and Though existing research considers the influence of rock burst factors, this study selects the shear stress σθ, uniaxial compressive strength σc, uniaxial tensile strength σt, stress coefficient σθ /σc, rock brittleness coefficient σc /σt, and elastic energy index W et as rockburst risk prediction indicators. σθ refers to the σθ around underground opening; σc and σt refer to uniaxial compressive stress and uniaxial tensile stress; σθ /σc is stress concentration factor; σc /σt represent two forms of rock brittleness index; W et reflects a ratio between the stored elastic strain energy and the dissipated elastic strain energy in a hysteresis looping test

Summary

Introduction

Rockburst is a phenomenon caused by mining unloading, in which the internal elasticity of the rock is suddenly released, resulting in bursting, spalling, spraying, and throwing of material [1,2,3]. Rockburst is a very serious hazard that can cause damage to mining equipment, roadway failure, injuries, and seismic activity [4,5]. Rockburst is a complex phenomenon, influenced by numerous factors such as rock properties, geological formations, ground stresses, and extraction activities, making rockburst prediction difficult, and effectively predicting rockburst remains a serious challenge [8,9]. The empirical approach assesses rockburst risk by analyzing the phenomenon in terms of stress/strength, brittleness, energy, and depth [10,11,12,13,14]. The most outstanding advantages of the empirical approach are simplicity and operability, which have been widely used in the identification

Methods

Results

Discussion

Conclusion