Page 15 - 251119_BJ_ME-Journal_14_digital
P. 15
Technology
Artificial Intelligence in the Field
of Building Automation
The term “AI – Artificial Intelligence” is intensity of use of kitchens, canteens and toilets The “Smart Building” typically builds on this
increasingly associated with buildings and other areas, but can be based on predictions classic building automation with flexible IT-based
and building automation. The question is: drawn from an analysis of usage patterns in the management systems. These offer unrestricted
what is it, where do its tangible benefits previous days and weeks. This kind of forward- programming using modern IT languages and
lie in this field, and how does the building looking building management can be applied in tools, easy integration with other IT systems
infrastructure need to be adapted to realize almost every area of building services, leading to such as workspace/room reservation systems
those benefits? increased energy efficiency, reduced operating or data banks, and data visualization for facility
costs, improved space utilization and other managers and for “ordinary” users.
Today’s building automation systems in the advantages.
main operate ‘statically’ in response to fixed The growing assimilation of sensor-generated
time programs or simple control parameters. All this – and much more – is possible when data into the IT-based management level opens
Room temperature control is based on a preset data on building system status and conditions the way for more advanced data processing
temperature that is the same throughout the day. is intelligently evaluated. This requires intensive solutions to come into play – such as AI tools.
Lighting is operated manually, with switches, or processing of large amounts of data, with many This is the pre-condition for the implementation
on the basis of simple presence switches. None variables to be considered. Artificial Intelligence of any prognosis-based form of building
of this is truly ‘intelligent’. The new dimension (AI) offers many new, tailor-made solutions management. The sophisticated processing
that AI can add into the building automation which are eminently suited to efficient building of sensor-generated data makes the Smart
environment is to use autonomous analysis management. Building into a “Cognitive Building”. (Fig. 1)
of the data as a basis for optimized operation.
Thus, the heating and cooling dynamic of rooms, “Building Automation”, “Smart Building” AI-Learning Process
weather forecasts, predicted room occupancy and “Cognitive Building”
during the course of the day can all be factored The first step in any Artificial Intelligence process
into the operation of the heating. Initially, “Building Automation” was comparatively is system learning. This can take three forms.
“unintelligent”. Systems were programmed to fol- Unsupervised Learning
Similarly, cleaning schedules can be based not low a set of simple rules, allowing for quick system Supervised Learning
only on the current actual values in terms of the start-up and subsequent ease of maintenance. Reinforcement Learning
Fig. 1: Building Automation – Smart Building – Cognitive Building (source: IBM)
15
BACnet Middle East Journal 14 11/25 15
