Analytics & dashboardsIndustry
Mining process quality
Which plant settings give the purest iron, from sensor data taken every 20 seconds
9.8–10.2pulp pH where the best iron yield happens
Watch part 1 (opens in a new tab)Watch part 2 (opens in a new tab)
Proof you can check:Video walkthroughPublic data
Analytics & dashboards
Iron yield peaks in one narrow pH band
pH 9.8–10.2 where the best 20% of runs happened
Lubo Bali · lubobali.com
The problem
A flotation plant has dozens of dials (pH, chemicals, air, foam). Operators need to know which ones really move iron purity, and where to set them.
What I built
A Python analysis of the plant's sensor data, sampled every 20 seconds and hourly: correlations, the best and worst 20% of runs compared, and a close look at a single day.
Tech & why
Python (Pandas, plots) in a notebook, so every step is visible and the plant team can rerun it on new data.
- Python
- Pandas
- Deepnote
The result
For process optimization: the best 20% of runs clustered at pulp pH 9.8–10.2; poor runs used more starch and amina and ran higher foam early. No single dial controls yield, so it has to be managed as a system.
Data: Quality Prediction in a Mining Process (Kaggle) (public dataset).
Similar projects
- Analytics & dashboardsEmployee sentimentSpot unhappy employees early, from the tone of their work emails2,191 work emails read for tone
- Analytics & dashboardsContractor performance (modeled on CVS)Which maintenance contractors cost the most and miss their deadlines18% of work orders overdue, on average
- AI agentsThis site and its AI BlueprintDescribe a business problem and get a first AI plan in about 30 seconds, on this site30 s from your problem to a first plan, measured live
Have a problem like this? Get your free AI blueprint in about a minute.
