GreeceChemicals and materials2026 – ongoingHELLENiQ ENERGY
HYPPOS soft sensors for polypropylene quality prediction
HELLENiQ ENERGY reported 20% less off-spec polypropylene after deploying AI soft sensors
Problem
Laboratory testing left gaps in operators' knowledge of polypropylene quality during production. Those gaps mattered when the plant changed product grades.
Approach
Hyperion commissioned HYPPOS AI at HELLENiQ ENERGY's Thessaloniki polypropylene plant. Machine-learning models used existing process data to predict melt flow rate and xylene solubles every few minutes. The rollout included comparison with laboratory results before operators received the live predictions.
Results
Takeaway
The plant added quality predictions using its existing data infrastructure without installing new analyzer hardware.
Categories
- Industry
- Chemicals and materials
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Vendor solution
- Evidence
- Company's own claim
Sources
Source summaries
Hydrocarbon Processing reported that Hyperion had commissioned HYPPOS at the Thessaloniki plant. It attributed a 20% reduction in off-spec material and 25% shorter grade transitions to figures presented by HELLENiQ ENERGY.
Full details are in the original sources.
