A Multi-Method Machine Learning Framework for Simulating Power Dynamics in an Iron Ore Cone Crusher Plant
Bibliographic record
Abstract
Comminution, particularly post-crushing, is a critical phase in mineral processing that reduces run-of-mine ore to an acceptable particle size before undergoing a downstream beneficiation process. Despite its importance, this stage has been under-investigated probably due to challenges of sampling and data collection and inadequate technical and financial support. This research presents a multi-method machine learning framework designed to simulate the power dynamics within an industrial-scale iron ore cone crusher circuit. The framework integrates advanced artificial intelligence techniques to evaluate energy consumption and estimate cone crushers output K80 accurately. The developed framework spans from different algorithms by data preprocessing techniques such as normalization and Principal Component Analysis (PCA) to standardize and reduce the dataset’s dimensionality, coupled with multiple machine learning algorithms, including Gradient Boosting Machines (CatBoost, LightGBM, XGBoost), Support Vector Regression (SVR), and Long Short-Term Memory (LSTM) networks. The study utilized real-time data collected over six months by considering the key operational parameters such as total tonnage, hopper filling levels, power draw, cone position, and crusher discharge settings. The modeling approach was assessed using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Asymmetric Loss (AL), and the coefficient of determination (R2) as performance metrics. Results indicated that the LSTM model outperformed other methods by achieving the lowest MAE and RMSE and the highest R2 score of 0.92, thereby demonstrating superior precision in estimation. However, XGBoost showed optimal performance in managing asymmetric loss, highlighting its efficiency in error management across different scenarios. Model residual analysis, performance metrics box plots, and scatter plots comparing measured and estimated data across the models are also provided for further analysis. This study demonstrates the transformative potential of machine learning models in refining industrial process simulations, ultimately driving enhanced productivity and sustainability in the mining industry.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".