An LSTM Approach for SAG Mill Operational Relative-Hardness Prediction
Ore hardness plays a critical role in comminution circuits. Ore hardness is usually characterized at sample support in order to populate geometallurgical block models. However, the required attributes are not always available and suffer for lack of temporal resolution. We propose an operational rela...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Minerals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-163X/10/9/734 |
| _version_ | 1797556812311953408 |
|---|---|
| author | Sebastian Avalos Willy Kracht Julian M. Ortiz |
| author_facet | Sebastian Avalos Willy Kracht Julian M. Ortiz |
| author_sort | Sebastian Avalos |
| collection | DOAJ |
| description | Ore hardness plays a critical role in comminution circuits. Ore hardness is usually characterized at sample support in order to populate geometallurgical block models. However, the required attributes are not always available and suffer for lack of temporal resolution. We propose an operational relative-hardness definition and the use of real-time operational data to train a Long Short-Term Memory, a deep neural network architecture, to forecast the upcoming operational relative-hardness. We applied the proposed methodology on two SAG mill datasets, of one year period each. Results show accuracies above 80% on both SAG mills at a short upcoming period of times and around 1% of misclassifications between soft and hard characterization. The proposed application can be extended to any crushing and grinding equipment to forecast categorical attributes that are relevant to downstream processes. |
| first_indexed | 2024-03-10T17:08:16Z |
| format | Article |
| id | doaj.art-d06549a5afe74f9cb77adc1ea0ecf38e |
| institution | Directory Open Access Journal |
| issn | 2075-163X |
| language | English |
| last_indexed | 2024-03-10T17:08:16Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Minerals |
| spelling | doaj.art-d06549a5afe74f9cb77adc1ea0ecf38e2023-11-20T10:45:13ZengMDPI AGMinerals2075-163X2020-08-0110973410.3390/min10090734An LSTM Approach for SAG Mill Operational Relative-Hardness PredictionSebastian Avalos0Willy Kracht1Julian M. Ortiz2The Robert M. Buchan Department of Mining, Queen’s University, Kingston, ON K7L 3N6, CanadaDepartment of Mining Engineering, Universidad de Chile, Santiago 8370448, ChileThe Robert M. Buchan Department of Mining, Queen’s University, Kingston, ON K7L 3N6, CanadaOre hardness plays a critical role in comminution circuits. Ore hardness is usually characterized at sample support in order to populate geometallurgical block models. However, the required attributes are not always available and suffer for lack of temporal resolution. We propose an operational relative-hardness definition and the use of real-time operational data to train a Long Short-Term Memory, a deep neural network architecture, to forecast the upcoming operational relative-hardness. We applied the proposed methodology on two SAG mill datasets, of one year period each. Results show accuracies above 80% on both SAG mills at a short upcoming period of times and around 1% of misclassifications between soft and hard characterization. The proposed application can be extended to any crushing and grinding equipment to forecast categorical attributes that are relevant to downstream processes.https://www.mdpi.com/2075-163X/10/9/734semi-autogenous grinding milloperational hardnessenergy consumptionminingdeep learninglong short-term memory |
| spellingShingle | Sebastian Avalos Willy Kracht Julian M. Ortiz An LSTM Approach for SAG Mill Operational Relative-Hardness Prediction Minerals semi-autogenous grinding mill operational hardness energy consumption mining deep learning long short-term memory |
| title | An LSTM Approach for SAG Mill Operational Relative-Hardness Prediction |
| title_full | An LSTM Approach for SAG Mill Operational Relative-Hardness Prediction |
| title_fullStr | An LSTM Approach for SAG Mill Operational Relative-Hardness Prediction |
| title_full_unstemmed | An LSTM Approach for SAG Mill Operational Relative-Hardness Prediction |
| title_short | An LSTM Approach for SAG Mill Operational Relative-Hardness Prediction |
| title_sort | lstm approach for sag mill operational relative hardness prediction |
| topic | semi-autogenous grinding mill operational hardness energy consumption mining deep learning long short-term memory |
| url | https://www.mdpi.com/2075-163X/10/9/734 |
| work_keys_str_mv | AT sebastianavalos anlstmapproachforsagmilloperationalrelativehardnessprediction AT willykracht anlstmapproachforsagmilloperationalrelativehardnessprediction AT julianmortiz anlstmapproachforsagmilloperationalrelativehardnessprediction AT sebastianavalos lstmapproachforsagmilloperationalrelativehardnessprediction AT willykracht lstmapproachforsagmilloperationalrelativehardnessprediction AT julianmortiz lstmapproachforsagmilloperationalrelativehardnessprediction |