Notes on Digitalisation of Greener Material Processes: Ontology and Data Models

The digitalization drive is transforming material processes, enhancing greener and more efficient productivity across various industries. The basis of digitalization for greener industries includes some key components like ontological framework, data analytics, machine learning (ML) and digital twining\shadowing schemes. These are crucial steps in the journey toward a more environmentally friendly and sustainable approach for future material processes. The goals for these greener material processes are to reduce energy consumption, minimize environmental impact, reduce cost\waste, and enhance resource efficiency. The European ontological framework for material development and processes which is a formal representation of material knowledge can help to define concepts, relationships, and knowledge structures related to sustainable materials and processes. Additionally, data science techniques and data models are broad schemes which help to build frameworks for organizing\structuring data and creating fast and real-time models to facilitate information exchange, optimisation and decision-making. In this research work, an overview of the digitalisation steps for material processing has been presented and the performances of data driven models based on a general sampling and snapshot schemes for material processes are briefly examined. Furthermore, the issues of optimized data structures and algorithms for fast prediction models within digital twin\shadow schemes are scrutinised. Finally, the accuracy and reliability of these data models for processes like additive manufacturing and extrusion processes are investigated using real-world case studies.