Industry News & Technical Perspective · Digital Thermoforming
WM Thermoforming Machines is bringing machine monitoring, AI-assisted support and automated inspection together in its WM Empower ecosystem. But can more machine data actually improve production efficiency?
Modern thermoforming lines already generate a considerable amount of information. Cycle times, heater settings, alarms, temperatures and production counters are often available. The challenge is turning this information into practical decisions that reduce downtime, scrap and unnecessary operating costs.
WM Empower, first presented at K 2025 and demonstrated again around PLAST 2026, is an example of the industry’s growing focus on connected production. According to WM, the platform combines a redesigned operator interface, production analytics, an AI assistant, inspection technology and digital maintenance documentation.
What Is WM Empower?
WM Empower is a digital ecosystem developed by WM Thermoforming Machines. Its components address different parts of machine operation, production monitoring and technical support.
| Module | Manufacturer-described function | Potential operational relevance |
|---|---|---|
| FlowView | Redesigned human-machine interface (HMI) | Setup consistency and operator onboarding |
| WMind | Cloud-based machine monitoring, analytics and software agents | Performance visibility and maintenance planning |
| Form.AI | Multilingual, 24/7 virtual assistant | Access to troubleshooting and operational guidance |
| WM Vision | Automated in-line product inspection | Defect detection and quality data |
| WM Explora | Interactive 3D machine views, manuals and spare parts information | Faster identification of parts and service documentation |
These are WM’s stated product functions, not independently verified performance results. Their actual benefit depends on installation, available data, integration and the way the production team uses them.
1. Machine Data: Visibility Is Not the Same as Understanding
A production dashboard can show that a thermoforming line is operating below its target speed. It may also reveal repeated stops, fluctuating cycle times or changing reject rates.
However, knowing when performance is lost does not automatically explain why.
For example, a reduction in cycle speed might be related to inadequate tool cooling, slow forming-air pressure build-up, material behavior, unstable product transfer or downstream stacking limitations. The correct diagnosis requires a technical understanding of the complete machine–tool–process interface.
DTC Perspective
Production data should guide the investigation. Measurements at the right points in the process are what help distinguish symptoms from root causes.
2. Form.AI: A Useful Assistant, Not a Substitute for Process Knowledge
WM describes Form.AI as a multilingual virtual assistant available around the clock to support operators, maintenance teams and technical service.
Easy access to machine-specific information can be valuable, especially when experienced technicians are not available on every shift. It may help teams find procedures, understand alarms and access relevant support information more quickly.
There is nevertheless an important distinction between retrieving instructions and diagnosing a physical process. An assistant cannot reliably determine whether an air supply is undersized, a cooling channel is restricted or a tool passage is limiting performance without appropriate measurements and validated information.
Key Question
Does the digital assistant help operators identify the next useful measurement, or does it simply suggest another parameter adjustment?
3. WMind: Connecting OEE with Real Production Bottlenecks
WMind is positioned as a cloud-based platform for real-time machine data collection, monitoring and analytics, including tools supporting predictive maintenance.
OEE can help structure discussions about availability, performance and quality. But OEE alone is not a root-cause analysis. Two lines with identical OEE values can require entirely different corrective actions.
- Availability: What causes unplanned stops and how frequently do they occur?
- Performance: Is the line running slower because of cooling, forming, punching or handling?
- Quality: Which defects occur, under which operating conditions, and how many good parts are produced?
Meaningful analysis requires consistent definitions, reliable data and a clear link between production events and technical conditions.
4. WM Vision: Detecting Defects and Preventing Their Recurrence
WM presents WM Vision as an in-line system for automated product inspection. In principle, automated inspection can help detect recurring visual defects and make quality trends visible earlier.
However, inspection and prevention are different tasks. Detecting a deformed tray or a sealing-rim defect is useful; understanding whether it results from temperature, material distribution, cooling or tooling is what allows a lasting process correction.
For producers, the most valuable outcome is not simply collecting more reject images. It is connecting defect patterns with the process conditions that created them.
5. WM Explora: Making Maintenance Information Accessible
WM Explora adds interactive 3D machine views, spare-parts identification and access to technical documentation. Such tools can reduce the time required to locate the correct component or procedure, particularly on complex equipment.
Still, the practical result should be measured: Does it reduce diagnosis time, repair time or repeat failures? These are more meaningful metrics than the number of digital functions installed.
6. What Could a Small Improvement Be Worth?
Consider a simplified production example with 24 cavities per cycle, a nominal speed of 25 cycles per minute and a 16-hour operating day.
| Production metric | Before | After |
|---|---|---|
| Cycles per minute | 25 | 26 |
| Cavities | 24 | 24 |
| Theoretical parts/hour | 36,000 | 37,440 |
| Theoretical parts/16 hours | 576,000 | 599,040 |
| Additional theoretical parts/day | — | 23,040 |
This illustration is not a WM performance claim. It shows why identifying and eliminating a small process bottleneck can matter financially. Actual saleable output depends on uptime, cavity utilization, scrap and product demand.
7. From Smart Machines to Smart Production Lines
WM has also described Smart Factory integration with Mac Due and Smartlogistix, linking thermoforming, material handling and end-of-line operations. This broadens the conversation beyond individual machine parameters.
In a connected production line, the forming station, stacking system, film supply and packaging operation must work together. A digital platform can improve visibility and coordination, but the physical limitations of the equipment still determine what is achievable.
DTC Perspective
The objective is not maximum machine speed on a screen. It is a stable flow of good products through the complete production process.
Final Thoughts: Data Becomes Valuable When It Leads to Action
WM Empower illustrates an important direction in thermoforming: machine builders are increasingly combining mechanical engineering with connected data, operator assistance and automated quality monitoring.
These technologies can support faster decisions and more consistent operation. Their business value, however, should be evaluated against measurable outcomes such as downtime, scrap, changeover time, maintenance effort and good products per hour.
AI can help identify patterns. Process knowledge turns those patterns into measurable improvements.
At Dobringer Thermoforming Consulting, the focus is on identifying real production bottlenecks across the machine, tool, material and process—and translating improvements into economic results.
Fresh Eyes. Fast Impact.
Sources & Further Reading
Editorial note: This is an independent technical commentary based on publicly available WM manufacturer information and general thermoforming engineering principles. No independent performance test of WM Empower, Form.AI or WM Vision is implied.