In the European Union discussions are ongoing to enforce national renovation strategies of buildings to reach low or zero carbon dioxide emissions from the building industry by 2050. Today, the documentation of renovations and changes is inadequate which creates difficulties to predict e.g. a brick façade’s service life. The aim of this project is to develop tools (i.e. checklists) to assess the renovation strategies for a specific building based on the data collected in field (observations and measurements). We use models for service life assessment of buildings to identify performance criteria for the renovation need. This information is used to develop the methodology for early identification of potential performance failures. Thereby, we provide a decision support tool for renovating at the right time with the correct measure. A combination of field inspections using drones and algorithms for machine learning is performed together with data analysis of existing databases which provide basis for training of neural networks and genetic algorithms. We use information from the Swedish National Board of Housing, Building and Planning’s (Boverket) surveys, our own investigations and a large-scale status inventory and documentation of buildings in central Gothenburg. This amount of data has never been available, which gives us a unique opportunity to perform the project now. The project results in better and more adapted renovation strategies for any given building.
Associate Professor at Chalmers, Architecture and Civil Engineering, Building Technology
Associate Professor at Chalmers, Computer Science and Engineering (Chalmers), Networks and Systems (Chalmers)
Professor at Chalmers, Architecture and Civil Engineering, Building Technology
Funding Chalmers participation during 2020–2022
Areas of Advance