Process Digitalization

Driving Digital Transformation in Manufacturing at LKR: The digitalization of industrial processes presents new opportunities to enhance efficiency, product quality, and sustainability. At LKR, we are at the forefront of this transformation, combining physics-based simulations with advanced data-driven methodologies. Our mission is to virtually model, understand, and optimize complex manufacturing processes—faster and more accurately than ever before.

• Model Order Reduction – High-Fidelity in Compact Form: High-resolution simulations offer deep insights into manufacturing processes but often come with high computational costs. Through Model Order Reduction (MOR) techniques, we distill complex models down to their essential degrees of freedom. This enables the creation of compact yet highly accurate models, ideal for rapid parameter studies, process optimization, and the development of digital twins.
• Machine Learning for Process Simulation and Control: By integrating machine learning algorithms into our simulation workflows, we unlock new capabilities in process prediction and adaptive control. AI-driven models learn from both simulation and real-world process data to identify patterns, forecast critical states, and support intelligent decision-making.
• Applications Across the Manufacturing Process Chain: Our methodologies are applied across a wide range of industrial processes, including:
  • High-pressure and low-pressure die casting
  • Continuous casting
  • Extrusion
  • Wire-based Additive Manufacturing
  • Deep drawing and forming processes

By combining physics-based modeling, reduced-order techniques, and data-driven approaches, we lay the foundation for robust digital twins that enable continuous process monitoring and real-time optimization.

Explore Our Research: Discover how LKR leverages simulation, data analytics, and AI to make aluminum production smarter, more efficient, and future-ready.

Publication

Horr, A., Hovden, S. & Kronsteiner, J. (2025). Application of real-time models for multi-scale predictions during material processes. The International Journal of Advanced Manufacturing Technology, 140, 5189–5205. https://doi.org/10.1007/s00170-025-16575-8