Project focus

Semiconductor manufacturer Infineon is further developing its Industry 4.0 supply chain solution. The goal: to strengthen the resilience of its global production network to volatility and order fluctuations. The aim is to integrate the process know-how of the employees, which is distributed across several organizational units.



The Supply Chain Business Ecosystem of Infineon is based on physical make flexibility and its daily optimization in a highly automated planning process. To further enhance the performance of the Industry 4.0 supply chain solution in these areas, the company is pursuing two digitalization initiatives: one focuses on demand-driven aspects, while the other creates the infrastructure for a global, flexible virtual factory.

Highlight: COB (Customer Order Behavior)

Visualization of customer ordering behavior in heat maps on a weekly basis. The two-dimensional representation generates images that experts can use to assign predefined categories to customers, such as over- or under-scheduling. A deep learning (DL) tool uses these assignments as a source of information.

Highlight: DFC 4.0 (Demand Forecaster 4.0)

The tool uses historical time series data and “future data” to forecast demand. A mix of statistical and DL/KI tools optimized for the individual product shall achieve the best forecast accuracy.

Highlight: GPN (Global Production Network)

In GPN, global quarantine of defective material is possible within minutes. The system also traces batches that have been split during the process. The complete traceability of goods or products from the front end to the back end in the GPN also reduces errors due to manual handling and achieves significant savings. In addition, supply chain planning with the GPN improves physical flexibility and thus overall capacity utilization by several percentage points.

Highlight: HAI Game

To support change management during the introduction of DFC 4.0, Infineon developed the HAI (Human & Artificial Intelligence) Game. This improves the cooperation with the “digital colleague” in a playful way. After all, an AI usually delivers better and quicker forecasts than a human; however, cannot explain them and is occasionally grossly off the mark if information is missing. In a half-hour game of 20 rounds, you learn to trust the machine quickly – without intervening.

  • significant improvement of the prediction accuracy per product line
  • majority of all products forecast better than before
  • significant increase in the degree of automation of forecasts, increase in their accuracy
  • full traceability from frontend to backend through GPN, better physical flexibility and thus increases overall capacity utilization by several percentage points

Infineon Technologies AG

Winner Category:
Smart Supply Chain
Semiconductor industry
Employees worldwide: