Statistical Methods For Mineral Engineers -
Ore grades often exhibit highly skewed distributions (e.g., log-normal distributions in precious metals). Understanding skewness prevents the overestimation of economic reserves and plant recoveries. Common Probability Distributions
Written specifically for mine-site professionals, metallurgists, and assay chemists. It avoids dense "math-speak" and focuses on practical application.
Compares means across three or more groups. Engineers use ANOVA to evaluate the effect of multiple different ore types on throughput.
Foundational statistical concepts support all of the specialized techniques above. Understanding these is non-negotiable for any mineral engineer. Statistical Methods For Mineral Engineers
Covers essential topics like mass balancing, sampling error reduction, and identifying performance improvements. Key areas where these methods make an impact: Calibration & Maintenance:
Data reconciliation using statistics to check for consistency in mass flow across conveyors.
Mean, median, and mode. The median is critical when dealing with skewed environmental or assay data containing extreme outliers. Ore grades often exhibit highly skewed distributions (e
To maximize copper recovery, engineers characterize feed materials mineralogically and then use DoE to compare collector types and dosages. The goal is to maximize efficiency while preventing overdosing, which impacts both cost and the environment. 4. Key Takeaways for Mineral Engineers
Metallurgical accounting ensures accountability for the valuable metals entering, staying within, and leaving the processing plant. However, physical measurements (flow rates, assays, densities) always contain measurement errors. Mass balancing utilizes statistical optimization to resolve inconsistencies in raw plant data. Two-Product Formula
Instead of trial and error, methods like Central Composite Design (CCD) help optimize leaching or flotation variables (like temperature and pressure) using the fewest possible samples. It avoids dense "math-speak" and focuses on practical
Once the variogram has been modeled, the next step is to use it to perform spatial interpolation through a process called . Named after the South African mining engineer Danie Krige, Kriging is a generalized linear regression method that provides Best Linear Unbiased Estimates (BLUE) . This means it minimizes the variance of the estimation error (the "kriging variance").
Statistical Design of Experiments (DoE) helps identify the optimal parameters (e.g., pH, dosage) to improve flotation recovery and grade.
Once the critical variables are identified, RSM is used to map the mathematical space and locate the absolute optimum operational settings.
