Specialty fruit grading — 5 grades, 12 t/h, 70% less labor
Multi-spectrum optical sorter with air-knife rejects and tray-pack robotics for premium specialty fruit.
- Client
- Confidential — Specialty Fruit Packer
- Location
- California, USA
- Capabilities
- Machine Vision · Robotics Integration
The challenge
Fruit packer relied on 24 manual graders per shift, with grade-call consistency dropping after hour 5. The packer was losing $2 per pound on misgraded premium fruit shipped at mid-grade prices.
What we built
TOMRA-style multi-spectrum imaging hood classifies into 5 grade bins; air-knife rejects move fruit between lanes; a Yaskawa delta robot picks graded fruit into trays. Training data was captured from 5,000 fruit samples graded by the customer's expert team.
Key equipment
- Multi-spectrum imaging hood
- Air-knife reject array
- Yaskawa MPP3S Delta
- Custom tray former
From the floor
Illustrative image — representative of project scope; customer-identifying details have been removed.
Results
Throughput at 12 t/h, labor down from 24 to 7 per shift, and revenue per pound recovered the premium category previously lost.
See all 20 projects
Food & Beverage•2025Dairy bottling line retrofit — 18% throughput, 62% fewer rejects
Replaced a 1998-era controls stack with modern PLC + vision while keeping the existing filler and capper steel.
+18%Throughput-62%Reject rate11 wkProject lead time
Food & Beverage•2025Robotic palletizing cell — 2 shifts of manual stacking eliminated
Greenfield palletizing cell at end-of-line, sized for 60 cases per minute across 12 SKUs with quick-change tooling.
2Shifts of manual stacking replaced60 cpmCases per minute16 moProjected payback
Food & Beverage•2024AI vision defect detection — escape rate cut from 0.6% to 0.04%
Replaced rule-based blob analysis with a deep-learning model for label crease, low-fill, and cap-tilt defects on PET bottles.
0.04%Customer escape rate+9%OEE points gained<200 msPer-bottle decision time