Rock bolts are one of the most effective and conventional support techniques widely used in underground mining and tunneling operations to stabilize excavations and jointed rock masses. External factors such as corrosion, overloading, and improper installation can weaken rock bolts, which could result in ground failure causing injury or loss of life and production. Monitoring the health condition of rock bolts will reduce the risk of accidents providing a safer environment for workers and equipment. This paper reviews monitoring methods currently used to assess the condition of installed rock bolts. Furthermore, we classify the surveyed techniques depending on the type of problems they attempt to solve. Presented are methods such as ultrasonics, fiber optics, piezoelectric, electromagnetics, impact echo, acoustic emission, and numerical algorithms. Each method is based on a unique physical principle that aids in evaluating corrosion and strain levels in the rock bolt. However, recent research to detect corrosion has primarily focused on rebar type of rock bolts used in concrete structures. Consequently, more research is needed to monitor the condition of the other types of rock bolts used in the industry such as cable bolts and split set bolts. In conclusion, the paper highlights various methods of studying rock bolt failure initiated by strain, corrosion, and improper installation of the grouts. It also explores the research advancement made for the study of rock bolt failure. This investigation is specifically beneficial to the mining and tunneling industry for better understanding and prediction of rock bolt failure.

Geomechanical analysis plays a major role in providing a safe working environment in an active mine. Geomechanical analysis includes but is not limited to providing active monitoring of pit walls and predicting slope failures. During the analysis of a slope failure, it is essential to provide a safe prediction, that is, a predicted time of failure prior to the actual failure. Modern-day monitoring technology is a powerful tool used to obtain the time and deformation data used to predict the time of slope failure. This research aims to demonstrate the use of machine learning (ML) to predict the time of slope failures. Twenty-two datasets of past failures collected from radar monitoring systems were utilized in this study. A two-layer feed-forward prediction network was used to make multistep predictions into the future. The results show an 86% improvement in the predicted values compared to the inverse velocity (IV) method. Eighty-two percent of the failure predictions made using ML method fell in the safe zone. While 18% of the predictions were in the unsafe zone, all the unsafe predictions were within five minutes of the actual failure time, all practical purposes making the entire set of predictions safe and reliable.

Understanding the behavior of weak rock masses is important for predicting the stability of structures under different loading conditions. Traditional models such as the generalized Hoek–Brown and Coulomb weak plane are widely used; however, they often fail to capture the nonlinear and irreversible behavior of weak rock masses. This study offers a comprehensive overview of a critical analysis of constitutive models’ strengths and limitations for simulating weak rock masses. By comparing traditional and advanced novel approaches such as the strength degradation of rock (SDR) masses and continuous damage mechanics (CDM), this investigation shows that the new advanced methods significantly enhance the quality and accuracy of simulations. Moreover, SDR models address the limitations of classical plasticity models by incorporating nonlinear stress paths and irreversible stress changes, while CDM offers detailed insights into microstructural defect progression. These advancements allow for more accurate and practical predictions of long-term stability in geomechanical engineering tailored to specific requirements of each project.

Slope failures represent one of the most serious geotechnical hazards, which can have severe consequences for personnel, equipment, infrastructure, and other aspects of a mining operation. Deterministic and stochastic conventional methods of slope stability analysis are useful; however, some limitations in applicability may arise due to the inherent anisotropy of rock mass properties and rock mass interactions. In recent years, Machine Learning (ML) techniques have become powerful tools for improving prediction and risk assessment in slope stability analysis. This review provides a comprehensive overview of ML applications for analyzing slope stability and delves into the performance of each technique as well as the interrelationship between the geotechnical parameters of the rock mass. Supervised learning methods such as decision trees, support vector machines, random forests, gradient boosting, and neural networks have been applied by different authors to predict the safety factor and classify slopes. Unsupervised learning techniques such as clustering and Gaussian mixture models have also been applied to identify hidden patterns. The objective of this manuscript is to consolidate existing work by highlighting the advantages and limitations of different ML techniques, while identifying gaps that should be analyzed in future research.

Energy consumption represents a significant operating expense in the mining and minerals industry. Grinding accounts for more than half of the mining sector’s total energy usage, where the semi-autogenous grinding (SAG) circuits are one of the main components. The implementation of control and automation strategies that can achieve production objectives along with energy efficiency is a common goal in concentrator plants. However, designing such controls requires a proper understanding of process dynamics, which are highly complex, coupled, and have non-deterministic components. This complex and non-deterministic nature makes it difficult maintain a set-point for control purposes, and hence operations focus on an optimal control region, which is defined in terms of desirable behavior. This paper investigates the feasibility of employing machine learning models to delineate distinct operational regions within in an SAG mill that can be used in advanced process control implementations to enhance productivity or energy efficiency. For this purpose, two approaches, namely k-means and self-organizing maps, were evaluated. Our results show that it is possible to identify operational regions delimited as clusters with consistent results.