Occupant-Based Digital Predictive Management to Improve the Built Environment

Facility management requires the proper management of a set of infor-mation coming from different areas to grant the correct allocation of re-sources for the safety and health of the workplaces. Assuming the varie-ty of domains, different types of data must be combined, integrated and managed to create accessible knowledge and push towards correct deci-sions. The EU has proposed whole lifecycle digital logbooks for buildings as a digital repository supporting building management tasks. However, integrating dynamic occupancy data into this type of digital repositories and using these data to predict the impact of alternative strategies are relatively unexplored fields. A common digital framework for building management, based on common languages/interfaces/data matching methods, is still lacking, as underlined by the EU. DIGITMAN (Occu-pant-based DIGITal predictive MANagement to improve the built envi-ronment) is a PRIN2022-financed project aimed at developing a predic-tive approach based on occupancy data integrated into a common digital framework to improve building stock management by supporting the correct allocation of technical and economic resources during the opera-tion of buildings. In the project, UNIVPM (coordinator), UNIBO, and POLIMI are developing a digital tool to support facility managers and building owners in considering occupancy data collected through BAS (building automation systems) and CMMS (computer maintenance man-agement systems). The proposed approach is based on a set of predictive analytic methods (e.g., ML, MAS) and simulation-oriented multicriteria analysis techniques (e.g., BPS) applied to the main pillars of building management (i.e., operation, maintenance, safety).