AI waste intelligence expert Greyparrot has presented an OEE dashboard from live composition AI data, patent pending, for materials recovery facilities (MRFs) and plastics recovery facilities (PRFs), described as a “step change” in how operators track Overall Equipment Effectiveness.
OEE has been measured in manufacturing for decades, standardized under ISO 22400-2. The same is true for recovery facilities, but the data is reportedly often assembled in spreadheets and comes from weighbridge tickets, downtime logs and periodic bale audits, pulled from separate systems after the shift by different departments.
Due to this, the quality metric is the weakest link: Quality is good output divided by total output, and until now that equation could reportedly not be closed live. It takes a continuous mass balance of the site - what arrives at the infeed, what leaves in every outfeed, and where material is lost in between. Manual sampling covers less than 1% of material. Typically, manual logs reported OEE 8 to 15 points higher than the true figure.
OEE is the product of three metrics: Availability, performance and quality. The Greyparrot OEE dashboard scores all three shift by shift, across the facility, from live composition data.
On the availability point, it offers uptime against scheduled production time, surfacing unplanned downtime, jams and “black belt” periods where the line runs empty.
Performance is measured as actual throughput against design capacity, which exposes bottleneck stages and shift-based tonnage variance.
Finally, quality is checked against contamination and purity swings on every output stream, protecting bale quality, offtake prices and customer contracts.
“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. The Greyparrot OEE dashboard will better align our team with a single source of truth,” said Ian McSpirit, Operational Support Manager - Recycling, Biffa.
In other news, back in May TOMRA Recycling revealed its new AI platform from PolyPerception and three deep learning applications for its GAINnext technology, coinciding with TOMRA increasing its investment in PolyPerception to a 51% majority stake.
If you liked this story, you might also enjoy:
The ultimate guide to global packaging sustainability regulation in 2026
PPWR timeline: the key dates to know
No comments yet