This use case uses digital twins to accelerate the deployment and commissioning of material handling automation systems. Instead of waiting until systems are physically installed at the customer site, virtual setup, testing, and commissioning can start earlier using digital models. AI methods such as CNNs, ANNs, RCNNs, image classification, diagnostics, and real-time decision-making support these virtual commissioning activities. The expected result is shorter in-house and on-site setup time, reduced scheduled tool downtime, earlier handover to production, and faster realization of automation benefits in semiconductor fabs.
| # |
Technology Name |
Description |
| 1 |
Virtual Commissioning using a Digital Twin |
A Digital Twin of an automation solution is created as a precise virtual representation of the real system. The Digital Twin is connected to the actual PLC, higher-level control systems, and, where applicable, the robotics suite, depending on the automation configuration. From the perspective of connected software systems, the Digital Twin replicates the behavior, responses, and operating logic of the real-world automation setup. This enables engineers and developers to configure, test, and expand software solutions in a realistic environment without requiring access to the physical automation hardware. |
| KPI # |
Related Technology |
KPI Target |
| 1 |
Virtual Commissioning using a Digital Twin |
Reduce the time needed for in-house setup, commissioning, and testing of the demonstrator system by 33%. |
| 2 |
Virtual Commissioning using a Digital Twin |
Reduce the time needed for on-site setup, commissioning, and testing of the demonstrator system by 33%. |
| 3 |
Virtual Commissioning using a Digital Twin |
Reduce the scheduled tool downtime needed for setup and testing at one demonstrator tool by 50%. |
| 4 |
Virtual Commissioning using a Digital Twin |
Enable handover to the customer for productive use 8 weeks earlier compared to current project milestone plans. |
| KPI # |
Baseline |
| 1 |
Baseline time for in-house setup, commissioning, and testing of the demonstrator is set to 100%. It cannot be defined in absolute terms because it depends on the specific product. Typical in-house times vary between 4 weeks for standard products and 6 months for first-of-a-kind solutions. |
| 2 |
Baseline time for on-site setup, commissioning, and testing of the demonstrator is set to 100%. It cannot be defined in absolute terms because it depends on the specific product. Typical on-site times vary between 3 weeks for standard products and 9 months for first-of-a-kind solutions. |
| 3 |
Baseline time for scheduled tool downtime needed for setup and testing at one demonstrator tool is set to 100%. It cannot be defined in absolute terms because it depends on the specific product. Typical downtime varies between several hours and several days. |
| 4 |
Baseline cannot be defined in absolute terms because it depends on the specific product and purchasing times. Typical lead times for automation solutions from purchase order until handover to production are 9–12 months. |
| KPI # |
Validation Method |
| 1 |
Compare the average total time required for in-house setup, commissioning, and testing of the demonstrator, both with and without virtual commissioning using a Digital Twin. |
| 2 |
Compare the average total time required for on-site setup, commissioning, and testing of the demonstrator, both with and without virtual commissioning using a Digital Twin. |
| 3 |
Compare the average scheduled tool downtime needed for setup and testing at one demonstrator tool, both with and without virtual commissioning using a Digital Twin. |
| 4 |
Compare the average total handover time to the customer, both with and without virtual commissioning using a Digital Twin. |
- Reduced re-configuration time of the AI-based system by approximately 30–50%.
- Reduced manufacturing costs in the long term.
- Improved overall productivity of the manufacturing factory by approximately 20%.
- Improved performance and faster time-to-market.
- Industrial process phases made more effective and precise through integrated and tailored AI algorithms, methods, and tools.
The use case contributes to faster and more effective automation deployment by enabling manufacturers to design, test, and optimize automation systems in a virtual environment before physical deployment. Early validation through the Digital Twin reduces costly on-site troubleshooting, shortens commissioning times, and helps prevent design errors from reaching the shop floor. By simulating production scenarios and fine-tuning processes without disrupting operations, the Digital Twin supports continuous improvement, higher throughput, and more efficient use of resources. The ability to develop and validate systems in parallel with physical installation accelerates project timelines, supports earlier handover to production, and lowers total manufacturing costs.
| AI Toolbox Tool |
Use within the Use Case |
| Object detection tool |
Used to detect automation components, tools, or relevant objects within virtual commissioning scenarios. It supported the validation of digital-twin-based automation behavior through computer-vision-enabled inspection and testing. |
| Object detection with YoloV8 |
Used for real-time object detection tasks in virtual commissioning and automation-system validation, supporting fast visual feedback during simulated or test-based commissioning workflows. |
| Image Classification Tool |
Used to classify visual states, automation-system conditions, or commissioning-relevant situations from image data. It supported diagnostics and validation of whether the automation system behaved as expected in the Digital Twin environment. |
| Multi-Object Tracking Tool |
Used to track moving parts, robots, carriers, or material-handling elements across video frames during virtual commissioning tests. It supported the validation of dynamic automation behavior in simulated and real commissioning scenarios. |
| Time-Series Anomaly Detection Tool |
Used to detect abnormal temporal patterns in commissioning, PLC, control, or automation-system signals. It supported diagnostic checks during virtual commissioning and helped identify behavior that differed from the expected Digital Twin response. |
| Tabular Prediction Tool |
Used to analyse structured commissioning, setup, testing, and performance data. It supported comparison of virtual and physical commissioning results and helped quantify reductions in setup time, downtime, and handover duration. |