A new way to measure OEE in a recovery facility

Today we launched our OEE dashboard, patent pending, for materials recovery facilities and plastics recovery facilities. It is available initially to Greyparrot Analyzer customers with site-wide installation of the AI-camera system.

Why the old number arrived too late

Manufacturing has measured Overall Equipment Effectiveness for decades, standardised under ISO 22400-2. Recovery facilities measure it too, but after the fact - assembled in spreadsheets from weighbridge tickets, downtime logs and periodic bale audits, pulled from separate systems after the shift by different departments.

Within this measure, the quality metric is the weakest link: quality is good output divided by total output, and until now that equation could not be measured live. Closing it takes a continuous full mass balance of the site - what arrives at the infeed, what leaves in every outfeed, and where material was lost in between. Manual sampling covers less than 1% of material, and plants running on manual logs typically differ from their true OEE by 8 to 15 points.

What the dashboard scores

OEE is the product of three metrics.

A plant at 90% availability, 90% performance and 90% quality scores 73%, not 90% - which is why estimating any single component undermines the whole figure.

The dashboard scores all three shift by shift, across the facility, from live composition data:

• Availability - uptime against scheduled production time, surfacing unplanned downtime, jams and "black belt" periods when the line runs empty
• Performance - actual throughput against design capacity, exposing bottleneck stages and shift-based tonnage variance
• Quality - contamination and purity swings on every output stream, protecting bale quality, offtake prices and customer contracts

Also in the dashboard:

• Live scoring - the facility figure updates continuously and breaks down on demand
• Alerting - notification the moment a component falls outside its expected range
• Comparison - performance benchmarked across shifts, lines and sites on a common measure

Every movement in the score breaks down into plain language: which loss, on which line, on which shift, what it costs, and what to do next. The OEE score updates continuously and alerts the moment a component falls outside its expected range.

"Recovery facilities are industrial plants, competing with virgin production of materials. For the past seven years, we've listened closely to our customers and built from understanding what is happening on a single belt to seeing how an entire facility is performing. Live OEE tracking brings recovery plants the same level of precision, immediacy and operational efficiency as any modern factory."

Mikela Druckman, Co-founder and CEO, Greyparrot

"Our teams have never been short of operational expertise. What continuous data changes is how quickly that expertise can be pointed at the right problem — we can act on the actual cause of a loss on the same shift, rather than reconstructing it from different sources of information. This will better align our team with a single source of truth."

Ian McSpirit, Operational Support Manager, Recycling, BIFFA