Predictive Maintenance

Fewer breakdowns, lower repair cost.

OEE

82%

from 68 %

MTBF

160index

from 100 index

Problem & Capability

What & how

Executive problem

Unplanned breakdowns disrupt throughput and quality.

Capability

AI predicts equipment failure, adhesive system degradation and print line performance issues.

Outcome & Strategic Impact

Why it matters

Business outcome

Fewer breakdowns, lower repair cost.

Strategic impact

Foundation for plant-level OEE.

KPI trajectory · Baseline → Target

Exhibit

AI explainability — drivers, risks, next 90 days

Deploying AI-driven predictive maintenance will materially reduce unplanned equipment downtime, directly improving OEE from 68% toward 82% and extending MTBF by 60%. This initiative establishes a scalable foundation for plant-level performance, cost control, and quality assurance across Avery Dennison’s global manufacturing footprint.

Drivers

Granular sensor data enables early detection of failure modes
AI models continuously learn from plant-floor events and outcomes
Integration with existing MES/SCADA systems streamlines adoption

Risks

Data quality gaps may limit model accuracy
Change management resistance from plant teams
Upfront integration complexity with legacy equipment

Next 90 days

Select two pilot plants with highest breakdown rates for initial rollout
Establish cross-functional team to validate data sources and integration points
Define baseline OEE and MTBF metrics and set up executive dashboard for tracking

Test it in a scenario

1 modelers for Head of Manufacturing

Scenario

Plant OEE Lift

Maintenance + yield + energy on the line.

Ask about this initiative

Single-turn