MaxMine machine learning at Australian mine sites: haulage data lessons for engineers
Reviewed by Tom Sullivan
First reported on International Mining – News
30 Second Briefing
MaxMine has rolled out a production-grade machine learning system for load and dump classification across Australian mine fleets operated by Glencore, NRW Holdings and Macmahon, with the platform now running continuously for six months. The edge-deployed models automatically tag truck payload events in near real time, sharply cutting missed or misclassified loads and reducing manual data cleaning by site engineers. Early results point to tighter haulage cycle control and more reliable production reporting, giving dispatch and planning teams higher-confidence payload and cycle-time data.
Technical Brief
- Consistent load/dump tagging improves temporal resolution of haul cycle datasets for bottleneck and queuing analysis.
- Cleaner payload event streams support more stable short-interval control KPIs and exception-based reporting workflows.
- Similar edge ML architectures could be extended to drill, dozer and ancillary equipment event classification.
Our Take
Glencore’s appearance here alongside MaxMine comes as our recent coverage of Glencore has focused heavily on safety incidents and closure pressures (e.g. Kazzinc in Kazakhstan and Cerrejón in Colombia), suggesting that production-grade machine learning in Australia may also be framed internally as a risk and compliance tool, not just an efficiency play.
A six‑month fully operational period for the machine learning system is long enough to capture seasonal and roster-related variability at Australian sites, which should give contractors like Macmahon and NRW Holdings statistically robust baselines for cycle-time, fuel and maintenance optimisation before any wider rollout decisions.
Prepared by collating external sources, AI-assisted tools, and Geomechanics.io’s proprietary mining database, then reviewed for technical accuracy & edited by our geotechnical team.
Related Articles
Related Industries & Products
Mining
Geotechnical software solutions for mining operations including CMRR analysis, hydrogeological testing, and data management.
CMRR-io
Streamline coal mine roof stability assessments with our cloud-based CMRR software featuring automated calculations, multi-scenario analysis, and collaborative workflows.
HYDROGEO-io
Comprehensive hydrogeological testing platform for managing, analysing, and reporting on packer tests, lugeon values, and hydraulic conductivity assessments.
GEODB-io
Centralised geotechnical data management solution for storing, accessing, and analysing all your site investigation and material testing data.
