Production Without Pause.
Case Study: Industrial OEM for Packaging Machinery
At a Glance:
Industry:
Machinery Manufacturing
Use Case:
Early detection of mechanical misalignments in rotary cutting machines to prevent production disruptions.
Technologies Used:
- Ultrasonic sensors
- AI-based machine learning
- Real-time acoustic monitoring
Impact:
70% reduction in unplanned downtime
Lower maintenance costs
Improved operational efficiency
The Challenge
A leading European OEM specializing in rotary window patching machines faced recurring production disruptions due to misalignments in their mechanical cutting systems. Precision blade alignment on rotating cylinders was critical to maintaining cut quality; even slight deviations led to defects and unplanned downtime. Resolving these issues typically required dispatching factory technicians for on-site realignment or part replacement-prolonging downtime and driving up operational costs for both the OEM and its customers.
Our Approach
To solve the root cause of the disruptions, we deployed an advanced acoustic sensor system designed to capture ultrasonic frequencies far beyond human hearing. Unlike periodic manual inspections, the sensor delivered continuous monitoring, analyzing operational sound signatures in real time.
Sensors were strategically placed near the cutting blades to pick up subtle shifts in acoustic patterns that indicate early-stage mechanical misalignments. These signals were processed by Spur’s Al-driven machine learning models, trained to recognize patterns associated with degradation and future failure risks.
This shift from reactive troubleshooting to predictive insights enabled maintenance teams to intervene proactively-transforming emergency repairs into scheduled, low-impact service windows.
What we uncovered
Hidden degradation patterns
The real issue wasn’t just blade misalignment-it was the lag in detection. By the time traditional inspections caught a problem, damage had already impacted production quality and uptime. Symphony uncovered hidden degradation patterns much earlier, giving teams the visibility they needed to act ahead of failure.
Minor deviations brought production to a halt
The solution also revealed that many unplanned outages stemmed from minor deviations that could be resolved without technician dispatch-insight that opened the door to new preventive workflows.
The Results
70% Reduction in Unplanned Downtime: Early detection of mechanical issues dramatically lowered instances of machine stoppages.
Significant Cost Savings: Preventive maintenance minimized emergency technician calls and unscheduled production halts, preserving output and reducing service expenses.
Higher Operational Efficiency: Maintenance was aligned with planned downtimes, improving machine availability and product quality across runs.
What’s Next?
Future upgrades will pair predictive insights with automated adjustments, minimizing the need for manual intervention.