If you’ve been paying attention to buzzwords in the building maintenance world, chances are you’ve heard of Predictive Maintenance. In recent years, the term has risen to prominence in the industrial and manufacturing sectors regarding industrial equipment. However, the term’s implications are much broader than that. As the Internet of Things (IoT) expands across the entirety of the built environment sector, predictive maintenance is paving the way to revolutionizing how we address the maintenance needs of building systems and equipment.
What is predictive maintenance in buildings?
Predictive maintenance is an equipment maintenance strategy that relies on real-time monitoring of equipment conditions and data to predict equipment failures. Advanced data models, analytics, and machine learning (ML) can reliably assess when and where failures are most likely to occur, including which components are most likely to be affected.
How does predictive maintenance work?
Predictive maintenance technology uses historical and real-time data from connected building systems and equipment to model performance, monitor conditions, and anticipate equipment or system failure before it occurs. Historical data from equipment, systems, sensors, and environmental factors is used to model what is called the P-F curve.
The P-F curve depicts the performance of a piece of equipment or system over time and represent the point at which that equipment could fail – the potential failure or “P” in the equation – and the point at which that equipment does fail – the functional failure or “F” in the equation. The more data that is available to inform this model, the better equipped a predictive maintenance program is to identify the interval between the potential failure point and the functional failure point.
To achieve this, building system integration is a critical component of the predictive maintenance strategy. Namely, a successful program works through the strategic convergence of the Internet of Things (IoT), ML, and system integration.
When these technologies work together, they leverage the vast amounts of data produced to model a P-F curve that can pinpoint the interval when failure is likely to occur with impeccable accuracy. Building engineers and maintenance teams then access this information via software, such as an integrated building management platform (IBMP) to address failures when they are going to occur.
What's needed for a successful implementation of predictive maintenance?
As mentioned previously, a successful predictive maintenance strategy relies on the strategic convergence of IoT, ML, and system integration. Many predictive maintenance solutions on the market currently lack this strategic convergence, not on purpose, but because buildings are vastly more complex than industrial equipment, vehicles, or any other entity that uses predictive maintenance.
This complexity means that the data needed to influence the P-F curve often remains siloed within its respective systems, making it nearly impossible in its original state to apply advanced machine learning capabilities that rely on multiple factors to inform the P-F curve model. A smart building integration platform with an Independent Data Layer (IDL) solves this problem.
These middleware technologies serve as the brain and nervous system behind predictive maintenance by simplifying and normalizing the data from disparate entities within a building’s ecosystem. Once data is simplified and normalized, machine learning can begin to analyze data from the entire building’s ecosystem to identify events that signify the potential failure point.
In order to implement a predictive maintenance solution that leverages a smart building integration platform and IDL, you’ll need to first determine whether your building is digitally ready and which systems and technologies can be easily integrated into your predictive maintenance software.
If your building is digitally ready, you should be able to begin reaping the benefits of a predictive maintenance strategy relatively quickly. However, if you find your building lacks the necessary requirements for onboarding to a smart building integration platform, you’ll most likely require the assistance of a trusted master system integrator.
Ready to find out if your building is digitally ready for a predictive maintenance program? Contact us for a quick assessment of your building.
Gina Elliott is Chief Services Officer with Buildings IOT where she oversees the customer onboarding, digital services, and customer success. Gina has held positions with Schneider Electric, EasyIO, and Switch Automation. She has been recognized in the industry as Person of the Year nominee (2017), 100 People You Should Know, Women of the Year and 2018 nominee for The Power 100: The Most Powerful Women in the Channel and 2019 winner of ControlTrend's Small Business Executive of the Year.