Page 50 - RC18-EDGE Spring.FINAL

Business Solutions

ADVANCES IN FAULT DETECTION AND

DIAGNOSTICS TECHNOLOGY

PROVIDE TRANSPARENCY AND ON-SITE ANALYSIS

FOR BUILDING OWNERS

BRENDAN WALLACE Some equipment is designed to run at all times, and so
Co-Founder & Managing Partner an alert that a system is no longer drawing any power
Fifth Wall can drastically shorten maintenance resolution times by
directing operators to the right piece of equipment in real
Recent advances in fault detection and diagnostics time. The logic here is simple: If power drops below a
software promise to deliver something that has never defined number, then trigger an alert.
existed in commercial real estate: true transparency
into the health of building systems and the indoor On the other hand, equally damaging issues cannot
environment, regardless of building type or size. be identified with such simple logic. One example is
equipment short cycling, which is when equipment shuts
In many commercial real estate portfolios, fault detection down and starts up in rapid succession. This can be very
requires making judgement calls based on incomplete detrimental to equipment life and wastes energy-related
data. In a good scenario, this data is derived from sensors costs. As the length of each cycle can vary wildly, there
connected to a robust Building Management System is no simple logic for identifying this issue; it requires a
(BMS). In the 90% of buildings that do not have a BMS much more sophisticated analysis.
installed, the only data sets available are pieced together
from spreadsheets, maintenance logs, and utility bills. In addition to advances in the analytical capabilities
of fault detection software in the cloud, the hardware
Now meters and sensors connected to the cloud can deployed to collect data is becoming able to perform
capture real-time data from hundreds of pieces of analyses on-site through a concept known as edge
equipment per building for a fraction of the cost of a computing. Edge computing disperses the analysis of
traditional BMS. These data sets can be analyzed and the mountain of data created by meters and sensors to
synthesized into specific insights about performance. the individual site of collection, instead of a requiring
For a sense of scale of the amount of data: a meter that a centralized analysis in the cloud. This enables faster,
takes readings of equipment performance every second more granular analyses, and reduces the costs involved in
will have generated 86,400 data points in a single day. transferring, storing, and processing data in the cloud.
Multiply that by hundreds of pieces of equipment per
building and operators can now utilize tens of millions of The implications of edge computing are enormous. Not
new data points per day. only will it bring down the costs of implementing fault
detection solutions, it will create the conditions for highly
But millions of data points are worse than useless customized analysis. Every building is operated a little
to building operators. Raw data is time consuming, differently; instead of trying to create rules in a centralized
confusing, and not actionable. That is where the manner that apply to a wide swath of building systems,
advances in fault detection and diagnostics come into edge computing enables software developers to ‘train’ a
play. Enormous data sets, combined with novel analytical device and allow it to ‘learn’ the specifics of its environment.
techniques such as machine learning, are enabling
software programs to identify issues far beyond what This learning can go beyond detecting an issue after it
building operators and engineers are familiar with. occurs. With large, historic data sets, fault detection can
move towards predictive maintenance, advising operators
For example, many traditional fault detection and when data suggests that equipment is on the verge of
diagnostics solutions operate based on thresholds. failure.

48