Prediction of Mining Conditions in Geotechnically Complex Sites
Abstract
:1. Introduction
1.1. Technology for Implementing the Causal Model
1.2. Choice of the ANN
- Support the use of non-binary, continuous variable based, historical training data as are readily available to the mining engineer;
- Support unsupervised training, mitigating the need for the continual labelling of new training datasets as mining conditions change. The labelling of training data is generally recognised as one of the main barriers to the implementation of neural networks in industrial applications, e.g., [9];
- Tolerant of missing data, which can be a problem, particularly when accessing legacy datasets for the training phase;
- Be as interpretable as possible through the support of dimensionality reduction.
2. Materials and Methods
2.1. Rock Engineering System (RES)
- Decomposition of the study problem into its constituent variables;
- Semi-quantitative assessment of variable significance and relative importance;
- Construction of an appropriate causal model accounting for binary interactions and, as in this research, global interactions.
- Binary: the mechanisms in the off-diagonal boxes are either switched on or off, so the coding is either as 1 or 0;
- Expert semi-quantitative (ESQ): a number from 0 to 4 is allocated as follows: 0—no interaction; 1—weak interaction; 2—medium interaction; 3—strong interaction; 4—critical interaction;
- According to the slope of an assumed linear relation;
- More numerically via a partial differential relation;
- Explicitly via complete numerical analysis of the mechanism.
2.2. Neural Network: Self-Organising Maps
2.3. Proposed Algorithm
- Support construction of a model capturing complex multi-variable interactions between geotechnical conditions and mining production;
- Prediction of future production based on this model.
2.4. Implementation of Algorithm
3. Results: Semi-Synthetic Analysis
3.1. Production Data Provided by the Site
- Data corresponding to bulk movements as a function of time and/or mining progress per strip;
- Operational data (highwall inspection reports, blast engineer reports, dozer operation reports) and other data that detail operational delays, once again as a function of time and/or mining progress per strip.
- Rock mass characterisation (geological model, hydrogeological model, structural mapping, potentially geophysics and slope design modelling, and analyses);
- Site characterisation and production data (design parameters, drill and blast reports, production data (including deviations from planned), and hazard reports).
3.2. Semi-Synthetic Production Data Analysis
3.2.1. RES for System Decomposition
- Weather, blast, dozer, overburden removal, and access have critical interactions with deviation from planned;
- Structure, RMPD, and rock type have strong interactions with the blast success;
- Structure, RMDI, rock type, hydro, weather, and blast have strong interactions with dozer operations’ success.
- The rock quality parameter is a function of rock type and structure properties such as fracture intensity (itself a function of structure orientation and persistence);
- Deviation from the plan is a function of other production variables such as overburden removal, dozer effectiveness, and ramp access.
3.2.2. RES for Model Simulation
- The binary interaction matrix (BIM) was used to establish a reasonable causal model, and a global interaction matrix (GIM) was computed (Section 2.1);
- Input parameters were modelled as random variables;
- Perturbations (e.g., rainfall event) were modelled as Gaussian ‘wavelets’;
- A total of 100 samples across a highwall were modelled, assuming each sample corresponds to 1 day of operations.
- Structural complexity increased gradually peaking around day 50;
- Weather conditions were favourable for most of the time but degraded, peaking on day 80;
- Geotechnical hazard events peaked on day 50.
- Structural complexity peaks on two occasions, days 15 and 75;
- Weather is good throughout but degrades for final 30 days;
- As with structural complexity, event frequency also peaks twice, increasing from days 20 to 40 and 90 to 100.
- Cluster 1 n = 34;
- Cluster 2 n = 10;
- Cluster 3 n = 20;
- Cluster 4 n = 11;
- Cluster 5 n = 25.
4. Discussion and Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Jele, R.; Dunn, M. Economic significance of geotechnical uncertainties in open pit mines. In Mining Geomechanical Risk; Australian Centre for Geomechanics: Perth, Australia, 2019. [Google Scholar]
- Read, J.; Stacey, P. Guidelines for Open Pit Design; CSIRO Publishing: Clayton, Australia, 2009. [Google Scholar]
- Arrieta, A.B.; Díaz-Rodríguez, N.; Del Ser, J.; Bennetot, A.; Tabik, S.; Barbado, A.; García, S.; Gil-López, S.; Molina, D.; Benjamins, R.; et al. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 2020, 58, 82–115. [Google Scholar] [CrossRef] [Green Version]
- Chattopadhyay, A.; Manupriya, P.; Sarkar, A.; Balasubramanian, V.N. Neural Network Attributions: A Causal Perspective. In Proceedings of the 36th International Conference on Machine Learning (ICML2019), Long Beach, CA, USA, 9–15 June 2019. [Google Scholar]
- MathWorks. SimulLink. MathWorks. Available online: https://au.mathworks.com/products/simulink.html (accessed on 31 October 2021).
- ORE. Integrated Extraction Simulator. CRC ORE. Available online: https://www.crcore.org.au/ies (accessed on 31 October 2021).
- GoldSim. Available online: https://www.goldsim.com/ (accessed on 31 October 2021).
- Abiodun, O.I.; Jantan, A.; Omolara, A.E.; Dada, K.V.; Mohamed, N.A.; Arshad, H. State-of-the-art in artificial neural network applications: A survey. Heliyon 2018, 4, e00938. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Karimi, D.; Dou, H.; Warfield, S.K.; Gholipour, A. Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis. Med. Image Anal. 2020, 65, 101759. [Google Scholar] [CrossRef] [PubMed]
- Hudson, J. Rock Engineering Systems: Theory and Practice; Ellis Horwood Ltd.: Chichester, UK, 1992. [Google Scholar]
- Hudson, J. A review of Rock Engineering Systems applications over the last 20 years. In Rock Characterisation, Modelling and Engineering Design Methods; Taylor & Francis Group: London, UK, 2013; pp. 419–424. [Google Scholar]
- Jiao, Y.; Hudson, J. The Fully-Coupled Model for Rock Engineering Systems. Int. J. Rock. Mech. Min. Sci. Geomech. 1995, 32, 491–512. [Google Scholar] [CrossRef]
- Kohonen, T. Self-Organizing Maps: Third Extended Edition; Springer Series in Information Sciences: Berlin, Germany, 2001; Volume 30. [Google Scholar]
- Agarwal, P.; Skupin, A. Self-Organising Maps: Applications in Geographic Information Science; Agarwal, P., Skupin, A., Eds.; John Wiley & Sones Ltd.: Chichester, UK, 2008; p. 214. [Google Scholar]
- Fraser, S. Proposal for Pilot Study into the Effectiveness of “CSOM” as a Predictive Tool for Forecasting Seismicity at the Mine Design Stage at Mt Charlotte, Kalgoorlie, Western Australia; CSIRO Exploration and Mining: Clayton, Australia, 2004. [Google Scholar]
- Fraser, S.; Mikula, P.; Lee, M.; Dickson, B.; Kinnersly, E. Data Mining Mining Data: Ordered Vector Quantization and its Application to Mine Geotechnical Data Sets. In Proceedings of the 6th International Mining Geology Conference, Rising to the Challenge, Darwin, Australia, 21–23 August 2006. [Google Scholar]
- Lersisi, J.; Sonjonen-Ward, P.; Fraser, S.; Ruotsalainen, A. Assessment of hydrothermal processes associated with Proterozoic mineral systems in Finland using self-organizing maps. In Proceedings of the EGU General Assembly Conference Abstracts, Vienna, Austria, 19–24 April 2009. [Google Scholar]
- Brunton, I.D.; Fraser, S.J.; Hodgkinson, J.H.; Stewart, P.C. Parameters influencing full scale sublevel caving material recovery at the Ridgeway gold mine. Int. J. Rock Mech. Min. Sci. 2009, 47, 647–656. [Google Scholar] [CrossRef]
- Zhou, B.; Fraser, S.; Borsaru, M.; Aizawa, T.; Sliwa, R.; Hashimoto, T. New Approaches for Rock Strength Estimation from Geophysical Logs. In Proceedings of the Bowen Basin Symposium, Yeppoon, QLD, Australia, 12–14 October 2005. [Google Scholar]
- Hodgkinson, J.H.; Fraser, S.J.; Donchak, P. Using self-organising maps to derive lithological boundaries from geophysically-derived data in the Mt. Isa region, Queensland. In Proceedings of the 22nd ASEG Conference, Brisbane, Australia, 26–29 February 2012. [Google Scholar]
- Mathworks, MATLAB Mathworks. Available online: https://au.mathworks.com/products/matlab.html (accessed on 31 October 2021).
- CSIRO. SiroSOM, CSIRO. Available online: https://www.csiro.au/en/work-with-us/industries/mining-resources/exploration/self-organising-maps (accessed on 31 October 2021).
Code | Description | Set |
---|---|---|
STRUC | Structure type present | R |
RMDO | Rock mass defect orientation | R |
RMDP | Rock mass defect persistence | R |
RMDI | Rock mass defect intensity | R |
ROCK | Rock type | R |
ROCKQ | Rock strength, RQD, weathering | R |
REG | Regional stress/structure change | R |
HYDRO | Hydrology and Hydrogeology | R & S |
WEATH | Weather influence | S |
GEOMORPH | Landscape physiology | S |
SLOPEOL | Slope orientation and Locations | S |
SLOPEDIM | Slope dimensions (bench geometry) | S |
BLAST | Blast success | P |
DOZE | Dozer/dragline ops success | P |
OBREM | Overburden removal | P |
EVFR | Event frequency | P |
ACCESS | Access to/from ramp | P |
DEV | Deviation from Planned (tonnes) | O |
Set Codes | |
---|---|
R | Rock |
S | Site |
P | Project Engineering |
O | Output |
Scoring | |
0 | No interaction |
1 | Weak interaction |
2 | Medium interaction |
3 | Strong interaction |
4 | Critical interaction |
Code | Description | Set |
---|---|---|
STRUC | Structure type present | R |
ROCKQ | Rock strength, RQD, Weathering | R |
REG | Regional stress/structure change | R |
HYDRO | Hydrology and hydrogeology | R & S |
WEATH | Weather influence | S |
SLOPEOL | Slope orientation and Locations | S |
SLOPEDIM | Slope dimensions (bench geometry) | S |
BLAST | Blast success | P |
EVFR | Event frequency | P |
DEV | Deviation from planned (tonnes) | O |
SOM Parameter | Value | Description |
---|---|---|
Input data dimensions | 10 | Number of variables to train the SOM |
Number of training samples (N) | 100 | 1 sample per day of mining |
Map grid dimensions | 12 × 7 | Recommended to be greater than 5 × √N [22] |
Map topology | Hexagonal lattice, sheet | Matches input data topology and assists in visualisation |
Neighbourhood function | Gaussian | Determine coupling of neighbouring neurons, equivalent to a smoothing kernel |
Clusters | 5 | K-means algorithm parameter |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Elmouttie, M.; Hodgkinson, J.; Dean, P. Prediction of Mining Conditions in Geotechnically Complex Sites. Mining 2021, 1, 279-296. https://doi.org/10.3390/mining1030018
Elmouttie M, Hodgkinson J, Dean P. Prediction of Mining Conditions in Geotechnically Complex Sites. Mining. 2021; 1(3):279-296. https://doi.org/10.3390/mining1030018
Chicago/Turabian StyleElmouttie, Marc, Jane Hodgkinson, and Peter Dean. 2021. "Prediction of Mining Conditions in Geotechnically Complex Sites" Mining 1, no. 3: 279-296. https://doi.org/10.3390/mining1030018
APA StyleElmouttie, M., Hodgkinson, J., & Dean, P. (2021). Prediction of Mining Conditions in Geotechnically Complex Sites. Mining, 1(3), 279-296. https://doi.org/10.3390/mining1030018