Using Artificial Intelligence in Mining Excavators: Automating Routine Operational Decisions
Bibliographic record
Abstract
Worldwide mining operations, which account for nearly 11% of global power consumption, are 28% less productive today than a decade ago. Meanwhile, mobile equipment was present in nearly 40% of mining fatalities and more than 30% of injuries in 2017. Building intelligence into existing mining excavators improves the safety, productivity, and energy efficiency of mining. This can provide perception, monitoring, and control capabilities that produce accurate, actionable data for mines. The intelligent excavator has an in-cab monitor that provides real-time status updates and guidance to operators as well as a remote monitoring portal. Multiple sensors, including a rugged camera that overlooks the excavator bucket, high-resolution surveillance cameras, radar, arm geometry, hydraulic pressure monitoring, and electric motor power measurement, sensors are integrated. Additionally, a set of human labeled video frames is used as training inputs to train an artificial neural network (NN) to perform multiple object localization via an optimization process, which (combined with other sensory data) is used to monitor the wear and breakage of sacrificial ground engaging tools (GETs), detect foreign objects, analyze the size distribution of the material inside the bucket, measure the bucket payload, and augment the operator's skill and experience. This information is vital to mining operations aiming to optimize dig, load, and dump cycles for energy consumption, downtime, and operator efficiency. Aside from improving operational efficiency, intelligent excavator solutions enable us to develop highly perceptive shovels with decision-making modules that pave the way for fully autonomous excavator operation.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".