Case study · Manufacturing
Predictive maintenance for a global manufacturing fleet
Lumen Manufacturing
- Industry
- Manufacturing
- Client
- Lumen Manufacturing
- Stack
- Python, Rust, Kafka, TimescaleDB, Kubernetes, AWS
Challenge
What we were solving.
Lumen's production lines were generating 14TB of sensor data per day, with no way to act on it before a failure. Unplanned downtime was costing the company $4.2M per quarter and the maintenance team was drowning in false alarms from the existing anomaly detection system.
Solution
What we built.
We built an edge-to-cloud predictive maintenance platform that runs anomaly detection at the line and surfaces only validated events to operators. The platform uses time-series foundation models trained on three years of historical data, with a feedback loop that learns from each confirmed alert.
Results
What changed.
Unplanned downtime reduced by 38% in the first six months
False alarm rate reduced from 71% to 6%
Maintenance cost per line decreased by 22%
ML pipeline scales to 240 production lines without re-architecting
Technologies
Related projects
Northwind Health
Clinical decision support for a 14-hospital network
1.2M patients now have a unified clinical record across the network Clinician reconciliation time reduced from 40 minutes to 4 minutes per shift Risk score accuracy validated at 92…
Atlas Federal Credit Union
Migrating a regional bank to a multi-account AWS platform
CI/CD pipeline duration dropped from 90 minutes to 7 minutes On-call coverage expanded from 3 engineers to a 22-engineer rotation Cloud spend visibility improved to per-product lin…
Granite Public Services
Citizen-facing benefits platform for a state government
Application abandonment dropped from 23% to 6% Median processing time reduced from 14 days to 3 days WCAG 2.2 AA accessibility validated by a third-party audit NPS of 31 from appli…
Want a similar outcome?
Tell us about your system and we’ll share a relevant engagement model in a 30-minute call.