Ore blending plays a critical role in ensuring feed consistency and optimizing downstream processes in the mining industry. Despite its importance, effective blending remains challenging due to ore variability and operational constraints. This review focuses exclusively on modern, data-driven blending methodologies, with particular emphasis on the application of data science and machine learning (ML) in predicting key process variables and supporting real-time decision-making. It discusses core challenges such as data quality, feature engineering, and model generalization, alongside enabling technologies including sensor integration, automation platforms, and real-time data acquisition systems. By consolidating the recent literature and highlighting emerging trends, this work outlines future directions for advancing intelligent blending systems and underscores the importance of standardized, high-quality data in the development of robust digital solutions for mineral processing.

Frost heave is a most common form of tunnel defect in cold regions. Installing an insulation layer is a key solution. However, the insulation layer deteriorates with freeze-thaw cycles and temperature changes. These significantly impact tunnel reliability in these areas. To determine the influence of insulation layer deterioration and temperature change to reliability of cold region tunnel, this paper examines a tunnel in the Qinghai-Tibet Plateau. It uses projected temperature increases of 2.6 °C and 4 °C over the next 50 years as boundary conditions. The study analyzes the evolution of freeze-thaw thickness, temperature fields, and stress fields in the surrounding rock. It considers both scenarios: with and without insulation layer deterioration. Using the Monte-Carlo method, the study investigates the variation in tunnel reliability. The results indicate that, with insulation layer deterioration, freeze-thaw thickness, temperature fields, and stress fields in the surrounding rock increase under both temperature scenarios. Consequently, tunnel reliability decreases. Specifically, with temperature increases of 2.6 °C and 4 °C, tunnel reliability decreases by approximately 4.5% and 6.3%, respectively, when considering insulation layer deterioration.

The Heimaguan Tunnel in China serves as a case study to exemplify the variation laws related to surface settlement, deformation, and stress characteristics in a shallow-buried soft-rock tunnel, while emphasizing in the tunnel support requirements. The first stage of this study begins with monitoring the time-varying characteristics of surface settlement, vault subsidence, and the horizontal convergence of Grade V rock. In the second stage, Peck theory is used to calculate the distribution characteristics of surface settlement. The results of both stages are compared to create a vault settlement model, thus establishing the horizontal convergence based on exponential function, logarithmic function and hyperbolic function, and determining the optimal time of secondary lining construction. On this basis, the time-dependent variation laws and characteristics of vertical and horizontal displacement and principal stress of surrounding rock are studied. After this, using simulation and analysis, the proper support is recommended. The study reveals that the surface settlement, vault subsidence, and horizontal convergence of the shallow-buried soft-rock tunnel stabilize within 25–30 days. Peck theory closely aligns with predictions based on exponential functions, with only a 0.72% difference. The recommended time for secondary lining application is 26–27 days.