Key Takeaways
- For blasthole logging, the most mature AI is in the drill itself. Hexagon Drill Assist puts AI into the drilling algorithm and manages drill parameters from rig-sensor data as it drills, with no manual parameter entry.
- Operators report training time dropping from years to about 15 minutes with Drill Assist, alongside real gains in fragmentation, ore dilution reduction and energy use per metre.
- Fully automated computer-vision lithology/cuttings logging is still research-stage. Sensor-while-drilling systems from IMDEX and Epiroc are the more mature adjacent capability.
TL;DR
AI blasthole logging today mostly means letting AI run the drill: Hexagon Drill Assist sets parameters from live rig-sensor data and captures consistent logs as a byproduct. Add a measurement-while-drilling (MWD) system to log rock properties from drill response. Vision-based cuttings logging is worth watching, but it is not a deployable product yet.
What Is Blasthole Logging?
Open pits drill hundreds of blastholes on each bench before a blast. Blasthole logging records what each hole tells you about the rock: hardness, lithology, water, voids and depth. Geologists and blast engineers use that record to design the charge and to refine the grade-control model.
Traditionally, someone logged cuttings by eye or sampled them for assay. However, every drill already measures useful signals while it works. Penetration rate, torque, rotation speed and pull-down pressure all change with rock strength. Turning those signals into a reliable log is where AI and automation come in.
How Do I Automate Blasthole Logging With AI?
There are three practical routes, from most to least mature. Start with the first and add the others as your data improves.
Automating the drill for consistent blasthole logging
The clearest AI capability here isn’t logging after the fact. It is AI managing the drill while it works, which produces better, more consistent logging data as a side effect. Hexagon Drill Assist is an OEM-agnostic automation layer that sits above existing rig control systems. It uses AI to set and adjust drilling parameters from sensor data, rather than requiring an operator to dial them in.
That removes a huge source of variability in blasthole quality. Hexagon reports operators reaching productive competence in about 15 minutes instead of the traditional three to five years. It also reports better penetration rate, fragmentation and ore dilution, all of which depend on consistent, accurate hole logging.
Logging rock properties while drilling
Beyond drill automation, several vendors, IMDEX and Epiroc among them, offer AI-assisted MWD systems. They log rock properties from drill response data in real time. As a result, every hole becomes a data point on rock hardness, without extra sampling. Probe-based tools such as IMDEX BLASTDOG add physical hole measurements on top.
Watching vision-based cuttings logging
Fully automated computer-vision systems that classify lithology or cuttings from downhole imagery are an active research area. They are not yet a mature commercial product. Therefore, track them, but don’t plan a deployment around them yet.
How Blasthole Logging Connects to the Rest of the Mine
Better logs feed decisions on both sides of the blast. Upstream, hardness data from each hole can adjust the charge in AI-optimized blast design. Downstream, the same data helps grade control separate ore from waste and predicts how the rock will fragment.
Expect some integration work. Drill data arrives in vendor formats, and it needs to be tied to hole IDs, collar coordinates and your block model. If you are evaluating this space, start with drill automation (Hexagon, or MWD systems from IMDEX/Epiroc). Then build the data link to your geological model before waiting for vision-based cuttings classification to mature.
FAQs
What is blasthole logging used for?
Blasthole logging records rock properties in each blast hole, such as hardness, lithology, water and voids. Blast engineers use it to design charges. Geologists use it to refine grade-control boundaries and the local geological model.
How does AI improve blasthole logging?
AI improves it mainly by making drilling consistent and by interpreting drill sensor data. Systems like Hexagon Drill Assist set drill parameters automatically. MWD systems then convert penetration rate, torque and pressure into rock property logs in real time.
What is measurement-while-drilling?
Measurement-while-drilling (MWD) records drill performance signals such as penetration rate, torque, rotation speed and pull-down pressure. Because these respond to rock strength, they act as a proxy for rock properties. AI models help calibrate that proxy against known geology.
Can AI log blasthole cuttings automatically?
Not reliably yet. Computer vision for cuttings and lithology classification is still at research stage. For now, MWD data and drill automation are the practical, deployed options.
Try It With Geocluster
Turning MWD and drill-automation sensor streams into a logging record that ties cleanly back to your geological model is a data-integration problem. Geocluster is built to handle exactly that. Read how the Geocluster Research Harness works to see where it fits.