Imagine a giant steel factory as a series of connected dominoes; if one step is slightly off, it ruins everything downstream. This project builds a digital brain that watches every step—from heating to cooling—and predicts how a change in one area affects the final product. It's like having a GPS for the entire production line that tells operators exactly how to save energy while keeping the steel perfect.
Steel manufacturers struggle with disconnected processing steps where changes in one station (like reheating) negatively impact the next (like quenching). This lack of integration leads to wasted energy, higher carbon footprints, and inconsistent product quality.
A demonstration platform combining distributed machine learning, soft sensors, and integrated numerical models to predict and optimize the entire steel manufacturing chain.
If you are an integrated steel mill dealing with high carbon footprints and energy waste—this project developed a demonstration platform that predicts the best use of multiple processing steps to increase energy efficiency.
If you are a software provider dealing with fragmented data across different factory stations—this project developed distributed machine learning and soft sensors that integrate data from separate processes like reheating and quenching.
If you are a specialty steel producer dealing with inconsistent product quality across the manufacturing chain—this project developed integrated numerical modelling that captures feedback loops to ensure better product quality.
Based on available project data, no specific pricing or cost information is provided as the project is currently in the development phase.
Yes, the project is specifically designing a demonstration platform using two parallel use cases at Celsa and SSAB to prove industrial scalability.
Based on available project data, the IP and licensing terms are not specified in the project summary.
The system integrates via novel sensors and data integration tools designed for secure and effective sharing of industrial data.
The project runs from 2025-01-01 to 2028-12-31, indicating the platform will be developed and demonstrated by the end of 2028.
The consortium is heavily industry-weighted with a 50% industry ratio, comprising 6 industrial partners and 4 SMEs. This strong commercial presence, combined with 5 research organizations and 1 university across 5 countries, suggests the project is driven by practical application and market needs rather than pure academic research.
Contact SWERIM AB in Sweden for partnership opportunities.
Contact us to track the development of the ProcTwin demonstration platform.
