Applicability of existing criteria of rockburst tendency of sandstone in coal mines

Abstract

To evaluate the accuracy of rockburst tendency classification in coal-bearing sandstone strata, this study conducted uniaxial compression loading and unloading tests on sandstone samples with four distinct grain sizes. The tests involved loading the samples to 60%, 70%, and 80% of their uniaxial compressive strength, followed by unloading and reloading until failure. Key parameters such as the elastic energy index and linear elasticity criteria were derived from these tests. Additionally, rock fragments were collected to calculate their initial ejection kinetic energy, serving as a measure of rockburst tendency. The classification of rockburst tendency was conducted using grading methods based on burst energy index (WET), pre-peak stored elastic energy (PES) and experimental observations. Multi-class classification and regression analyses were applied to machine learning models using experimental data to predict rockburst tendency levels. A comparative analysis of models from two libraries revealed that the Random Forest model achieved the highest accuracy in classification, while the AdaBoost Regressor model excelled in regression predictions. This study highlights that on a laboratory scale, integrating ejection kinetic energy with the unloading ratio, failure load, WET and PES through machine learning offers a highly accurate and reliable approach for determining rockburst tendency levels.

1. Introduction

With the depletion of shallow mineral resources and the growing pressure on surface land resources [1], the exploitation of abundant deep mineral resources and vast underground spaces has become an inevitable development trend. The utilization of underground resources and the rapid advancement of infrastructure development are accelerating [2,3]. However, as mining operations extend deeper, geological conditions become increasingly complex and geostress correspondingly intensifies [4]. This exacerbates the issue of induced rockburst incidents during mining and other production activities, making it a critical challenge in deep-earth engineering and resource extraction [5,6]. Rockburst refers to the sudden and violent failure of rock under high-stress conditions [7], posing significant hazards to underground excavations. Rockbursts can happen in brittle coal beds in coal mines (then the term ''coalburst'' is often used [5]), but also occur sometimes in hard rocks. Sandstone rocks found in coal mines, which are usually of high strength and brittleness, can perfectly absorb elastic strain energy under high-stress conditions and cause damage with a rockburst effect [2,7]. Investigating the specific mechanical properties and failure characteristics of sandstone rockburst, as well as implementing appropriate monitoring and mitigation strategies, also seems crucial to ensuring the safety of underground excavations into sandstone rock beds.

The occurrence of rockbursts is closely associated with the accumulation and sudden release of energy within rocks. It is generally accepted that rockbursts result from the rapid and intense release of large amounts of stored elastic energy [8,9]. Currently, predicting rockbursts or establishing robust criteria for identifying rockburst tendency remains a significant challenge and, as such, a focal point for research. Developing accurate and widely applicable criteria is the central objective of ongoing studies [10,11]. Since the 1980s, researchers have proposed various criteria for rockburst proneness. Hoek and Brown [12] analyzed rockburst occurrences in underground mining and suggested using the ratio of maximum tangential stress to the uniaxial compressive strength of the rock as a rockburst grading index. Kidybinski [13] proposed the use of the burst energy index (WET) as a measure of rockburst tendency.