Skip to content

FusionTool-AI: AI-Driven Tool Optimization in Metal Forming

As part of the FusionTool-AI research project, RISC Software GmbH is working with its partners to develop an AI-powered tool that determines whether forming tools should continue to be used, be remanufactured, or be replaced.

C Mark Metal Products Factory, LLC

Data-Driven Decisions Instead of Relying on Experience

The metalworking industry is Austria’s leading export sector. More than 1,200 companies—mostly small and medium-sized enterprises—use manufacturing processes that are highly prone to wear and tear, in which tools account for approximately 8 to 15% of production costs. Today, skilled workers typically decide whether a tool should continue to be used, repaired, or replaced based on their experience. Wrong decisions lead to increased material wear, longer downtime, and avoidable CO₂ emissions. To date, there is no standardized, scientifically validated methodology for decision support in this sector.

Making Wear Measurable at the Micrometer Level

The functionally relevant wear of hard-coating layers on active tooling elements during multi-stage deep drawing ranges from 1 to 9 µm. Conventional testing methods cannot reliably detect these changes under real shop-floor conditions. FusionTool-AI therefore relies on measurement technology in the sub-micrometer range, thereby providing an objective basis for any further evaluation.

Intelligently Linking Heterogeneous Data

Plant data, CAM/CAW geometry data, metrology measurements, and operator observations are currently stored in separate systems. FusionTool-AI consolidates these sources into a semantically linked database. Multimodal AI methods use this data to derive physically grounded cause-and-effect relationships and distinguish genuine causes of wear from statistical spurious correlations. The result is a concrete recommendation for action: continued operation, laser-based regeneration, or economically justified replacement.

Hybrid Laser Techniques for Regeneration

At the same time, the project team is conducting materials science evaluations of hybrid laser processes (EHLA, LBDED) for high-alloy cold-work steels. This creates a sound alternative to replacing worn-out tools.

Expected Benefits

The project team is validating a functional AI prototype on two pilot lines during ongoing production at MARK. Once fully rolled out, the system is expected to reduce new tool procurement by 30% and repair costs by over 40%, as well as save approximately 23 metric tons of CO₂ equivalents annually. The methodology is designed as a transferable prototype and is therefore available to more than 1,200 companies in the Austrian metal industry.

Project partners

Project details

  • Project Short Title: FusionTool-AI
  • Full Project Title: Prescriptive Tool Optimization in Metal Forming Through AI-Based Data Fusion and Hybrid Laser Processes
  • Call for Proposals: FFG Basic Research Program, 2026 Call (IWI 24/26)
  • Project partners:
    • Mark Metallwarenfabrik GmbH (Consortium Leader)
    • FH OÖ Research & Development GmbH
    • RISC Software GmbH
  • Total budget: 571 ,888 euros
  • Duration: June 2026–May 2027 (12 months)

Ansprechperson

Name(Required)

Project management

Dr. Roxana Holom, MSc

Data Science Project Manager & Researcher