The rise of Internet of Things (IoT) technology has added new dimensions to maintenance planning. Data from IoT devices can provide facilities managers insights to run and maintain their properties effectively and, when combined with smart building platforms that provide analytics, identify and resolve problems more efficiently.
Analytics are more than reactive equipment alarms or reports. They are results-based findings based on relevant data that are clearly presented in an understandable format that explains the issue, when it occurred, its duration, the status of related operating conditions, and even its cost impact. Analytics show how building systems are working in reality instead of relying on operating assumptions.
Smart building system operators use predictive or data-driven maintenance strategies that incorporate analytics to ensure efficient maintenance practices.
Reactive, preventive, and—better yet—predictive
Historically, building personnel would correct issues as they occurred, otherwise known as reactive, corrective, or run-to-failure maintenance. Personnel would fix items when they were broken and leave them alone when they weren’t.
This strategy can be costly. According to a 2012 HVAC Benchmarking Report by the Professional Retail Store Maintenance Association (now ConnexFM), reactive service calls after equipment breaks average three times as expensive as proactive calls, a difference of approximately $400 more per call.
Preventive or planned maintenance was introduced in the early 20th century with the advent of the mass production of automobiles. This spurred other industries to develop their own practices. Planned maintenance largely relies on guessing how much equipment time or usage must occur before maintenance is due based on manufacturers’ specifications. This strategy also is not feasible or cost-effective in predicting every failure, so its use is limited to issues based on runtime or interval time.
Though preventive maintenance does keep reactive costs down, it can also increase standard operating costs by initiating unnecessary inspections or repairs. Based on estimates for when equipment might need to be serviced, preventive maintenance neither predicts equipment degradation based on actual condition and utilization nor prevents equipment failures.
On the other hand, predictive maintenance, also known as data-driven or condition-based maintenance, injects intelligence into building maintenance by using objective data to identify issues that may impact future equipment performance. It avoids many of the costly problems associated with reactive maintenance while allowing stakeholders to develop a strategy for monitoring and maintaining equipment, comfort, and cost.
[P]redictive maintenance ... injects intelligence into building maintenance by using objective data to identify issues that may impact future equipment performance.
The Benefits of Predictive Maintenance
System maintenance should be performed when specific indicators show signs of decreasing performance, increasing energy usage, or impending failure. Predictive maintenance can detect when things go wrong before anyone notices—and before repair and operational costs escalate. It can pinpoint the root cause of issues, easing their diagnosis and repair, and reduce second visits. This strategy can also identify design issues, such as the incorrect sequence of operations, undersized duct or piping, mismatched components, or inappropriate zoning.
Predictive maintenance helps determine the exact nature of the issue and assists in dispatching the right technician with the correct information and parts. Other benefits of predictive maintenance include the following:
- Reduction in truck rolls.
- Decrease in total time to resolution.
- Increase in first-time fix rates.
- Reduction in retro commissioning with ongoing commissioning.
- Reduction in overall maintenance costs.
- Decrease in risk of major malfunctions.
- Increase in direct fixes, as problems are caught in the earliest stages.
- Decrease in downtime, delays, and disruption.
- Consistent comfort and environment for end users.
- More accurate allocation of maintenance budget and resources.
- Better equipment performance and longer equipment lifespan.
- Decrease in maintenance costs.
- Easier compliance with regulatory requirements.
- Improved energy efficiency.
A preventative maintenance plan requires adequate and reliable building data. The best way to get building data is through IoT sensors.
Enter IoT sensors
Available in many shapes and sizes, IoT sensors can be fitted on a multitude of systems during or after their initial install. These systems include HVAC, energy, lighting, access control, irrigation, and occupancy.
Smart building management platforms use machine-learning (ML) algorithms to analyze equipment and IoT data to identify performance trends, enabling targeted maintenance and early intervention to prevent significant problems. However, a macro approach is required to combine the mass amount of data ingested from different environments and conditions to create a big picture that predicts failure probability and possible improvements in operational performance.
All buildings are unique, and many issues go undetected in scheduled maintenance. Arming a vendor with cases detected via analytics and ML provides a comprehensive plan to fix and maintain equipment showing signs of distress, wear and tear, and reduced efficiency. This ultimately reduces the impact of downed equipment, including the cost and disruption to facility managers and occupants.
All buildings are unique, and many issues go undetected in scheduled maintenance.
The real differentiator between predictive and preventive maintenance is that the former uses a real-time, data-driven approach specific to the actual condition of the equipment. That means manual inspection, replacement, and repair occur only when necessary. Predictive maintenance anticipates problems based on data, allowing action to be taken to prevent equipment malfunctions. Additionally, an ML-driven smart building management platform will produce increasingly accurate and specific predictions as it learns more about the building and its use.
Predictive maintenance goes beyond building systems. For example, accurate occupancy forecasts allow operators to anticipate each area’s cleaning and sanitation needs and allocate resources accordingly.
More on occupancy
The proliferation of hybrid work means workplaces must behave in new ways to meet changing needs and to remain effective and safe. Occupancy forecasting is a powerful tool in predictive maintenance. An intelligent building management platform can predict future occupancy using data gathered from sensors. This information helps make office square footage more efficient and ensures building automation strategies support a healthy indoor environment, even when occupancy varies drastically.
With occupancy forecasts, a smart building management platform can:
- Automatically adjust HVAC settings to maintain comfort and air quality at a level appropriate for the number of occupants.
- Automatically adjust the lighting to occupant needs.
- Eliminate unnecessary heating, cooling, ventilation, and illumination of unoccupied areas.
- Identify areas that need improvement.
- Provide information to improve space utilization.
Occupancy forecasts can provide valuable data for workplace apps through which employees reserve cubicles, conference rooms, desks, and offices. These forecasts are similar to how hotels use daily, monthly, quarterly, and annual models of occupancy to allocate rooms based on their predictions.
Knowing actual occupancy versus scheduled occupancy allows buildings to run more efficiently. For example, lights can turn on only as needed, and HVAC systems can come out of setback when an occupant needs conditioned air. Having historical data based on actual occupancy scenarios allows for proper forecasting.
Predictive maintenance is the future
Analytics and machine learning are the future of building maintenance. A data-driven predictive maintenance plan can revolutionize how buildings function by replacing extraneous routine inspections and preventing equipment degradation. It allows for more proactive monitoring of system health, opportunities to optimize performance, and robust decision-making overall. In addition, it prioritizes the impact of maintenance on performance, energy, and comfort.
A data-driven predictive maintenance plan can revolutionize how buildings function by replacing extraneous routine inspections and preventing equipment degradation.
Incorporating a predictive maintenance plan requires investment in a smart building platform. A mobile-first platform that features cutting-edge fault detection and diagnostics, machine learning, IoT devices, applications, and user-friendly interfaces ensures that teams can take building maintenance to the next level.
Any analytic or smart building platform is only as good as the data received. The more IoT sensors and integrated system data collected, the better the outcome. Deep domain expertise in open communication protocols, data integration, and system interoperability is necessary for designing and implementing a specific solution. Individual project needs must be assessed with a partner that understands smart buildings’ complexities to obtain the full benefits of a data-driven, future-focused solution with a practical, predictive maintenance approach.
