From Mystery to Mastery
Datwyler operates a sophisticated fleet of 20+ injection molding machines producing precision components for demanding industries. Yet despite years of operational experience, a critical question remained unanswered: Where was downtime actually coming from?
Production managers could see that machines were down, but lacked the granular data needed to systematically address the root causes. Without clear visibility into whether downtime stemmed from material changes, shift handoffs, equipment failures, setup issues, or other factors, improvement efforts were reactive and scattered.
This lack of insight meant:
- Operational blind spots - no systematic way to identify which downtime categories were costing the most
- Reactive problem-solving - addressing symptoms rather than root causes
- Missed optimization opportunities - unable to track progress on improvement initiatives
- Limited accountability - difficulty attributing downtime to specific processes or procedures
- Lost learning - each shift and month treated in isolation with no trend analysis
The Turning Point
Datwyler deployed IoTFlows SenseAi across their injection molding fleet to capture granular downtime data. But the real innovation came next: they made downtime classification a core operational discipline.
The system automatically categorizes common downtime causesmaterial changes, shift transitions, equipment maintenance, cleaning cyclesbut the secret sauce is what Datwyler does with the gaps: operators and supervisors manually classify any downtime the system doesn't automatically recognize, creating a continuously improving knowledge base.
The Culture Shift: By involving the production team in downtime classification, Datwyler transformed data collection from a IT exercise into a collaborative improvement process. Every shift handoff, every material change, every unexpected pause now generates actionable intelligence.
Building Historical Intelligence
Rather than focusing on real-time dashboards, Datwyler strategically invested in weekly and monthly historical reporting. This approach revealed patterns invisible in daily operations:
Week-over-week analysis showed:
- Which days consistently experienced longer shift changeovers
- Whether material change procedures were improving week to week
- How new operators performed during their first weeks
- Seasonal patterns in downtime categories
Month-over-month analysis enabled:
- Tracking cumulative impact of improvement initiatives
- Identifying persistent problems worthy of engineering intervention
- Comparing performance across production teams
- Setting data-backed targets for the next operational cycle
The Results: From Knowledge to Impact
Within six months, Datwyler's data-driven continuous improvement program delivered significant results:
Downtime Transformation
Shift Changeover Downtime: 50% Reduction
- Root cause analysis revealed handoff procedures that could be streamlined
- Clear visibility into which shifts and transitions caused delays
- Team accountability driving better execution
Material Changeover Downtime: 30% Reduction
- Historical reports identified material types requiring longer setups
- Process improvements targeting high-impact changeovers
- Preventive actions to minimize setup delays
Overall Fleet Efficiency: 20% Gain
- Accumulated impact of focused improvements across multiple categories
- Compounding returns from systematic problem-solving
- 20+ machines operating at noticeably higher throughput
"IoTFlows didn't just give us datait gave us a method. By tracking downtime categorization week to week and month to month, we could see exactly where our biggest problems were and track whether our fixes actually worked. The 50% reduction in shift changeover time came directly from acting on patterns we saw in the historical reports. That's not luck; that's discipline meeting data."
Brien Stevenson, Site Director, Datwyler
Why Historical Reports Matter More Than You Think
Most manufacturers focus on real-time alerts and live dashboards. Datwyler discovered that the real value is in the rear-view mirror.
Historical reporting enabled:
Pattern Recognition
Live data shows you what's happening now. Historical data reveals what keeps happening. Datwyler identified that Tuesday shift transitions consistently added 8-10 minutes of downtimeinvisible in daily operations but devastating over months.
Trend Validation
You can make one improvement and see immediate results. But is it sustainable? Datwyler's monthly reports showed which improvements stuck and which needed reinforcement.
Evidence-Based Prioritization
Rather than arguing about which downtime matters most, Datwyler built charts showing cumulative impact over weeks and months. This shifted resource allocation from opinion to evidence.
Team Engagement
When supervisors see their shift's performance improving in the weekly report, accountability increases. When they see a 30% reduction in material changeover time over 6 months, they become advocates for the process.
The Competitive Edge
While competitors optimize individual metricsa faster setup here, better equipment thereDatwyler built something more valuable: a systematic process for continuous improvement powered by self-generated operational intelligence.
Their injection molding operation is now 20% more efficient, not because of a major capital investment, but because they converted invisible downtime into actionable data, and then acted on it week after week.
