The importance of predictive maintenance in IoT diagnostics

The importance of predictive maintenance in IoT diagnostics Saar Yoskovitz is CEO and co-founder of Augury.


Every device, no matter how connected, has the potential to break. As the Internet of Things (IoT) continues to permeate every sector of manufacturing, from transportation and logistics to automotive and utilities, businesses are turning to predictive maintenance (PdM) to reduce downtime and maximise efficiencies.

Recent advances in technology have made PdM more affordable and available to manufacturers of all sizes. By using data that connected machines provide to measure damage, wear and tear, and other indicators of operational success, unprecedented insight into machine health is changing popular methods of maintenance. This “Maintenance-as-a-Service” approach allows equipment to be monitored and fixed remotely, with the potential capability to even repair itself.

The impact of IoT

IoT is a concept in which ‘things’ utilise embedded technology to communicate and interact with the external environment via the Internet. The sensors provided by IoT allows users to monitor an infinite number of objects, from household appliances to security systems to industrial equipment. While sensors have been used for equipment maintenance for a number of years, the emergence of mobility and IoT have led to greater system efficiencies.

The Industrial Internet of Things (IIoT) incorporates machine learning and big data technology to consistently capture and communicate data, quickly alerting companies of inefficiencies  and avoiding costly breakdowns. In manufacturing specifically, IIoT holds great potential for capacities like quality control, sustainable and green practices, supply chain traceability and overall supply chain efficiency.

Emerging technologies like the IoT provide businesses with the ability to build intelligent connected equipment that continuously monitors itself to ensure that operational efficiency is above the threshold for optimum performance. Using sensor technology and on-board electronics that have the capability to communicate with the manufacturer’s cloud-based analytics system, product vendors can predict and address potential problems and breakdowns. This combined use of sensors, embedded electronics and analytics services, and cloud based systems result in increased productivity and a significant savings in maintenance costs.

Advances in PdM

PdM first surfaced about 20 years ago in the military sector, eventually being adopted into high-end industries such as gas and oil companies, utilities and aviation. According to the U.S. Department of Energy, past predictive maintenance studies have shown that a program using PdM can result in a savings of eight to twelve percent over a program utilising preventive maintenance alone. Predictive maintenance can reduce energy and maintenance costs by up to 30%, eliminate breakdowns 35% to 45%, and reduce downtime by up to 75%. In addition, optimising a working machine can cut energy consumption by 20% to 25%. This is attributed to the fact that when a machine is in a non-optimal state, it uses more power or energy to get to the final outcome.

Yet despite the clear benefits of predictive maintenance, only 12% of commercial buildings employ this type of technology. One reason is that the high cost of implementing PdM has made it unaffordable for the lower-end market. Maintaining hardwired systems that required highly-trained technicians to analyse results is an expensive proposition. But with the advent of mobile hardware and cloud-based computing, PdM has become more cost-effective, allowing it to trickle down into new markets.

Studies estimate that a properly functioning predictive maintenance program can provide a savings of 8% to 12% over a program utilising preventive maintenance alone. Commercial facilities can save approximately $1 per square foot annually by implementing Predictive Maintenance, resulting in a total savings of up to 13% of their operational budget.

The shift in maintenance strategies

Equipment maintenance has come a long way in the past decade, with many businesses adopting smarter strategies to improve efficiency. It began with reactive maintenance, a “fix-it-after-it’s-broken” concept where little or no maintenance was conducted. This segued into preventive maintenance (also known as scheduled maintenance), based on the repair and/or replacement of an item at a fixed calendar interval regardless of its condition at the time. This approach can lead to excessive replacement of components that may still be in good working condition, as well as increased amount of downtime to service the equipment on a fixed schedule.

The philosophy central to predictive maintenance arose out of the need for businesses to sustain optimal manufacturing productivity while reducing overhead costs. With PdM, a maintenance plan is developed based on the prediction results derived from condition-based monitoring, resulting in greater equipment reliability and improved planning. This self-maintenance approach allows a machine to monitor and diagnosis itself through an attached device that collects vibration and ultrasonic sensor data. The data is sent to an app on a smartphone and compared with other recordings made in the past of either that same machine or other similar machines. Once the analysis is complete, a technician can take the appropriate action.


The blending of IoT, smart devices and cloud computing have given industry the opportunity to explore new maintenance strategies in today’s competitive market. Through shared information, real-time monitoring, and data analytics, the IoT boosts PdM’s ability to empower businesses of all sizes achieve optimum functionality and cost savings. As advances in technology continue to evolve, so too will the power of PdM and IoT diagnostics. in hearing industry leaders discuss subjects like this and sharing their IoT use-cases? Attend the IoT Tech Expo World Series events with upcoming shows in Silicon Valley, London and Amsterdam to learn more.

View Comments
Leave a comment

Leave a Reply

Your email address will not be published. Required fields are marked *