SCCH Leads Data-Driven Modeling in PRIM-ROCK: Advancing Hybrid Approaches for Process Monitoring and Optimization
As a research institution for applied research in data science, SCCH will be the task lead for data driven model development in the PRIM-ROCK project.
Currently, SCCH is involved in work packages "Simulation-driven design" and "Digitalisation Framework development". Simulations based on first principles can provide a valuable basis for a hybrid simulation and data-based approach to model development. Through such a combined approach, models for monitoring and optimization can achieve increased robustness when dealing with highly varied calcination and roasting processes.
The developed PRIM-ROCK data integration platform will be the framework with which the data-driven models for monitoring and optimization will interact with the physical process, receiving input data from the sensor network and sending output to the process control system.
The following recent publications highlight SCCH’s expertise in data driven modelling for industrial processes, which will be utilized in the PRIM-ROCK project. They are investigating Digital Twins for Process Industry [1], time-series causality [2] and feature selection using causality graphs [3].
[1] Mayr, Michael, Georgios C. Chasparis, and Josef Küng. 2024. “Learning Paradigms and Modelling Methodologies for Digital Twins in Process Industry.” In Big Data Analytics and Knowledge Discovery, edited by Robert Wrembel, Silvia Chiusano, Gabriele Kotsis, A Min Tjoa, and Ismail Khalil, 14912:34–47. Lecture Notes in Computer Science. Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-68323-7_3.
[2] Mayr, Michael, Georgios C. Chasparis, and Josef Küng. 2025. “Causal Time-Series Synchronization for Multi-Dimensional Forecasting.” Procedia Computer Science, 6th International Conference on Industry 4.0 and Smart Manufacturing, 253 (January): 2655–64. https://doi.org/10.1016/j.procs.2025.01.325.
[3] Ammann, Lolita, Jorge Martinez-Gil, Michael Mayr, and Georgios C. Chasparis. 2025. “Automated Knowledge Graph Learning in Industrial Processes.” Procedia Computer Science, 6th International Conference on Industry 4.0 and Smart Manufacturing, 253 (January): 2428–37. https://doi.org/10.1016/j.procs.2025.01.303.
