Delivering 7:1 ROI from high-speed diagnostics

PurpleSector Digitally Observed Insights Technology

Background

A high-throughput manufacturing line was operating at more than 200 products per minute, but downtime was being triggered roughly every 15 minutes. The frequency of disruption created significant Overall Equipment Effectiveness losses and a major cost burden.

Challenge

The failures occurred too quickly and too randomly for operators to observe or diagnose.

At more than 200 products per minute, events happened faster than manual observation could follow
Irregular timing made it impossible to anticipate when a failure would occur
Existing monitoring could not capture events in enough detail to reveal the root cause
Variation introduced through the supply chain created synchronisation problems, making the line's behaviour appear intermittent and difficult to control

Solution

PurpleSector deployed an automated high-speed vision system that captured 4,000 events in the first 24 hours.

Machine-learning analysis then mapped the correlations between operating conditions and different failure modes. A digital twin of the process was used to simulate corrective actions and validate the most effective interventions before any change was applied to the live line.

Engineers testing a sustainable marine powertrain system designed for reduced emissions and faster delivery.

A sustainable marine powertrain system designed for reduced emissions and faster delivery.

Results

The programme delivered a 7:1 return on investment in a high-throughput production environment.

Supply variation and equipment synchronisation were identified as the root causes, and corrective measures were embedded to prevent recurrence. More importantly, a pattern of apparently random failures was converted into a predictable and controllable operating condition.