BY CLAIRE SWEDBERG
AGING BUILDINGS AND SENSOR-BASED
technology developments are creating unique opportunities
for contractors and integrators to help building managers track the health of their facilities, the efficiency of the
equipment and their usage of space.
Traditionally, predictive maintenance was a task that only some facility managers took part in. The complexity of tracking the health of the
building’s many functions is still there, but now sensors, the internet and
smartphones are changing the amount of information that can be gathered
and who can help manage it.
On paper, manual inspections and maintenance are still the bread and
butter of a building’s management, but solutions based on the internet of
things (Io T) bring a building’s systems onto the web, which enables con-
tractors to help take a headache away from building managers.
FOCUS | ON THE MARKET
Maintenance With Intelligence
The IoT keeps
A growing number of companies offer sensors integrated on or in a
device along with apps or software to analyze data and detect a potential
failure. Today’s sensors include everything from infrared temperature to
The Io T is having a major, permanent impact on the building management industry and puts the potential for building maintenance in the hands
of a variety of sources, including electrical contractors.
Today, companies offer the services around installing and managing
those sensors and the data they capture. Companies that own a large
amount of real-estate in the building-management market are offering
predictive maintenance solutions as well as sensor-based intelligence to
increase a building’s efficiency.
IBM, for instance, offers IBM Watson, a system that promises to help
companies save energy, automate inspections and maintenance tracking,
and help predict safety and maintenance issues, said Claire Penny, global
industry leader, Watson Io T for buildings.
“IBM Watson is helping companies expand augmented intelligence,
drive innovation and unlock business transformation,” she said.
IBM Watson employs machine-learning models to analyze energy consumption based on details such as time and day of the week, weather and
building occupancy. Building operators then learn and predict behaviors in
energy utilization at the building level, at speed and at scale. If anomalies
are detected, they can be tracked down to the submeters that caused the