Abstract
The construction industry has a massive environmental impact. Cement and concrete production generate up to 8% of global CO2 emissions. Innovative thinking is needed to make construction materials more sustainable, while keeping them affordable and versatile. This project aims at investigating new types of advanced and smart concrete mixes that can sense the environment and the material status. Novel material formulations will be analysed and tested according to small scale specimens to retrieve data to be used with a digital twin based on a multidisciplinary optimization algorithm based on Artificial Intelligence (AI) and, in particular, Machine Learning (ML) tools. The present implementation will cover not only mechanical and physical material parameters. Nowadays the applications of AI and Machine Learning (ML) have expanded tremendously. Such techniques have been used to model, define, optimize, predict, and manage complex systems. In the present framework, identification and quantification of the economic parameters influencing the material analysis and design will be indicated. This is of paramount importance to consider the process sustainable since life cycle assessment (LCA), life cycle costing (LCC) and life cycle energy analysis (LCEA) are fundamental for the decision-making process in the industry 4.0 within an IoT implementation. This context can be easily implemented as an integration of building information modelling (BIM).
Team di ricerca UNIBO
Nicholas Fantuzzi
Partner di progetto
Pegaso, Sapienza, Tor Vergata