Digital methods and tools in construction processes for efficient project management workflows: case histories

Buildings are becoming far more than walls, roofs and masonry: thanks to Artificial Intelligence (AI), building systems are becoming able to autonomously integrate the proliferation of data from IoT devices and occupant behavior to apply learning, optimize performance and improve environmental efficiency. As AI is integrated with building systems and Internet of Things (IoT) devices, it has the potential to improve occupant experience, increase operational efficiency and optimize space and asset utilization. A vast array of information from digital devices provides insights about the operations, use and condition of everything from the building’s infrastructure, physical environment, climate, water and energy usage, to an occupant’s experience and satisfaction, then IoT and platforms embedded with Artificial Intelligence and machine learning make it possible to develop innovative new services for engaging with building occupants. These systems have the potential to radically reduce costs through automation and optimization of operations. By taking advantage of powerful analytics and Artificial Intelligence for example, building owners can significantly cut energy consumption and achieve ambitious cost-saving targets. After equipment performance information is collected through sensors and meters, a library of benchmark data is applied, analytics are performed and potential operational improvements are identified. Analytics can also be used to prevent energy waste by isolating inefficient energy use. Sensor-controlled systems can monitor dispensing and water use. Cognitive maintenance systems can help preserve the health of critical building equipment and assets by anticipating asset failure and guiding timely interventions and so on. A comprehensive building optimization system leverages all aspects of building and facility management. These types of systems allow for monitoring the use of space, water and the usage and allocation of energy. Taking this monitoring one step further, building equipment data collected from IoT sensors that is tagged by location or asset type and associated with business rules can trigger algorithms to not only detect but also predict and respond to anomalies. These optimized ecosystems of building technologies identify opportunities for efficiency controls through predictive maintenance. They identify possible root causes, so actions can be prioritized, assigned, monetized and prevented, as recommendations that appear on dashboards or adjustments can be routed directly to the IoT device for action. AI is able to capture data from day-to-day building operations to enable new levels of automation, which enables buildings to “think,” engage and learn. These buildings can autonomously monitor and predict their own maintenance needs. Data transmitted from connected assets, such as boilers, pumps, chillers and elevators, is analyzed and enriched to identify anomalies, such as equipment operating outside of normal parameters. Potential failure modes are identified from tolerance and business rules, and devices are automatically instructed to take corrective action. The building memorizes the result of the intervention so it can improve the accuracy of detection and resolution of future incidents. The integration of cognitive analytics, sensors and existing building systems can also significantly improve occupant experience. Envision going to work in a building that works for you. While you’re there, IoT sensors are constantly monitoring your movement and the temperature. It turns lights on and off for you, adjusts the flow of water in restrooms and listens for your voice commands. Even breaths are monitored for carbon dioxide concentration in case an airflow adjustment is needed. And when the building detects that people have left their assigned workspaces, it turns on the lights in the parking garage, places the building systems into rest mode and checks tomorrow’s weather. This kind of approach to problem solving is related to simulation modelling, which aims at reproducing in a virtual environment the behavior of a non-linear dynamic system. It serves as a digital testbed where one can assess ex-ante different strategies over a simulated time-horizon. The development of the Digital Twin therefore begins with an integrated Information Model, in the case of buildings this is the so-called BIM (Building Information Model), able to contain data and information useful to simulate the process, which in communication with data from sensors becomes a Digital Twin with learning capabilities, able to process the information received. Artificial Intelligence algorithms then allow the Digital Twin to develop predictive capabilities and finally to make and implement autonomous decisions based on the analysis performed. The project aims to investigate, build and test methods and approaches that respond to the challenges proposed by the increasingly necessary digitization of industrial processes, as a true digital management, which combined with the growing potential of Artificial Intelligence and machine learning, allows to manage, optimize and automate the phases of construction processes, with particular regard to the management phase of processes related to the life cycle of the built environment. As already mentioned, the key word is management: in particular it is explored a case history about the Digital Twin-based management of a portion of city, in the specific case of a residential area located in Rome and composed of 16 buildings. The goal is to build a digital process and ecosystem based on three-dimensional information models that are able to replicate physical objects, such as buildings, and especially manage and monitor their interactions with reality. The Digital Twin of a residential system can therefore be a key tool for the storage, visualization, analysis and creation of data useful for the management of urban life and, considering the absolute centrality of data in the realization of digital processes, an important development consists in the integrated use of GIS and BIM, aimed at the information management and processing of information both at the scale of the building and at the geographical and territorial scale. BIM and GIS, although they share the essential concept of description of the real world through the combination of visual representations and information, are conceived and developed as belonging to different domains, and therefore have differences also and especially in the level of detail. BIM can be used to create, manage and share life-cycle data for vertical structures, such as buildings, while GIS can store, manage and analyze data describing the urban environment, distributed horizontally. Therefore, Digital Twins of buildings reproduce their geometric, but above all, informative characteristics, and they appear as 3D models but they have the particularity of being configured and structured as real time three-dimensional databases, where data are contained within objects equipped with specific parameters and attributes that describe the characteristics of the components themselves, thus enclosing useful information for the definition and simulation of processes. The Digital Twin gradually becomes able to improve and enrich its knowledge and improves data, receiving inputs and signals from sensors constantly monitoring the buildings, developing self-learning and above all predictivity capabilities, through the integration with Artificial Intelligence algorithms.