Application of the hierarchical Bayesian models to analyze semi-autogenous mill throughput
Bibliographic record
Abstract
• The aim is to provide a robust statistical framework for improving process control strategies in SAG milling operations. • Bayesian Hierarchical Models capture the causalities between geological and operational variables for SAG mill throughput. • The hierarchical framework accounts for nested data structures, enabling partial pooling of information across campaigns. • This research also detects causal inference in SAG mill performance. Optimizing throughput in semi-autogenous grinding (SAG) mills is a critical challenge in mining and mineral processing, directly influencing energy efficiency and operational costs. While mill speed, power, dimensions, ball charge, and feed rate can be controlled, uncertainties in ore hardness, particle size distribution, and liner wear create significant variability in performance. These challenges necessitate a modeling approach that not only captures operational dependencies but also accounts for hierarchical data structures and uncertainty. This study employs a Bayesian Hierarchical Model (BHM) to quantify the relationships between geological, blasting, and mill operational factors, providing a structured probabilistic framework for throughput prediction and decision-making. A systematic variable selection process using Bayesian inference identifies ore hardness, SAG mill rotation speed (RPM), and the tonnage of crushed material as the most influential predictors. The model also accounts for liner wear across multiple operational liner age periods, capturing its cumulative effect on power consumption and grinding efficiency. Unlike conventional statistical techniques, which assume fixed variable relationships, the Bayesian approach allows partial pooling across operational contexts, improving predictive accuracy and adaptability. The findings highlight the advantages of Bayesian methods over traditional regression techniques through uncertainty quantification and hierarchical structure. Integrating domain knowledge with probabilistic modeling enhances SAG mill prediction, enabling data-driven decision-making in complex mining environments. The results provide a foundation for improving energy efficiency, reducing operational variability, and refining throughput predictions under diverse geological and equipment conditions. This study advances statistical methodologies in mining process optimization, demonstrating the practical benefits of Bayesian modeling in industrial applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".