Publications / CCC 2025 - Zadar, Croatia
In recent years, the construction industry has undergone a profound transformation thanks to the integration of advanced parametric modelling methodologies and the adoption of increasingly sophisticated digital technologies. These tools have redefined design, construction and management processes, improving operational efficiency and opening new perspectives for predictive maintenance and infrastructure resilience. Advanced data analysis, combined with the simulation of future scenarios, now makes it possible to develop more effective intervention strategies, optimizing energy performance and significantly reducing the environmental impact of the AEC sector. However, despite huge investments in digitization and sensor technology applied to buildings, the effective management of the large amount of data collected still represents an open challenge. Currently, there is a lack of an established paradigm to transform this data into concrete operational information and optimized decision-making processes. In this scenario, Artificial Intelligence (AI) emerges as a revolutionary element, capable of filling this gap and offering advanced tools for real-time data processing and interpretation. Indeed, the use of predictive algorithms and machine learning techniques makes it possible to improve the life cycle management of buildings and infrastructures, optimize the use of resources and increase the overall sustainability of the sector. This research explores the role of AI in the evolution of the AEC sector, outlining a methodological framework that transforms digitization into a concrete operational advantage, with tangible impacts in terms of efficiency, sustainability and innovation. A further added value of this approach lies in the possibility of optimizing the distribution and installation of sensors, avoiding waste and unnecessary investments. Through AI-based analysis, it will be possible to accurately identify structures requiring advanced sensor integration and develop reliable predictive models for the design and maintenance of similar buildings. This method will not only improve maintenance strategies, but also contribute to a more intelligent and sustainable management of the building stock, rationalizing economic and material resources.