Subscribe and listen to AW’s podcast!
Subscribe and listen to the Automation World Gets Your Questions Answered podcast!
Listen Here

The Smart Sensor/Predictive Maintenance Connection

Understanding how smart sensors and the coupling of their data with machine learning algorithms enables the transition from condition monitoring to predictive maintenance is key to reaping the benefits of IIoT.

648823021

For several years now, case studies have been showing that predictive maintenance delivers the most bang for the buck for manufacturers of all sizes. This is hardly surprising given that adding a few additional sensors and access to predictive maintenance software—much of which is cloud-based and can be purchased on a monthly or annual basis—can very quickly deliver insights into equipment health to help avoid unplanned downtime and improve scheduled maintenance activities.

The money saved here goes directly to the company’s bottom line, providing a quick return on investment on these new sensor and software technology purchases.

This graph shows the extent to which revenues in the predictive maintenance technology market are being driven by emerging predictive maintenance technology, such as smart sensors, dedicated software, and dedicated gateways. According to Interact Analysis, the term “dedicated” is used to describe a product designed to aid predictive maintenance in motor driven applications; more general-purpose analytics software are not included here.This graph shows the extent to which revenues in the predictive maintenance technology market are being driven by emerging predictive maintenance technology, such as smart sensors, dedicated software, and dedicated gateways. According to Interact Analysis, the term “dedicated” is used to describe a product designed to aid predictive maintenance in motor driven applications; more general-purpose analytics software are not included here.In fact, industry’s uptake of these sensor and software technologies can be seen in the rapid growth of the predictive maintenance technology market. Interact Analysis, an international technology research firm, expects the predictive maintenance technology market to reach a valuation of nearly $1 billion by 2024 (see chart).

Understanding smart sensors

Considering the critical role smart sensors play in this growing predictive maintenance market, it helps to understand how they differ from traditional, legacy industrial sensors. According to Blake Griffin, senior analyst with Interact Analysis,most smart sensors utilize a capacitive MEMS (micro electro-mechanical systems) technology to take readings. These sensors are placed on equipment to gather various data points, most commonly vibration and temperature measurements. Smart sensors then transmit this information wirelessly to a data collector or gateway. When analyzed, this data is particularly useful for assessing the health of equipment as the level of vibration and temperature usually increases as equipment becomes faulty.”

Griffin added that these smart sensors were first largely used in consumer electronics. Their widespread use in consumer technologies helped suppliers achieve “economies of scale in these applications, enabling the smart sensor concept [to be adapted] for industrial applications. The result is a product with a low price point which allows users to cost-effectively expand the amount of equipment monitored in their facilities.”


   FInd out how your peers across industry are using sensor technologies and artificial intelligence to improve their operations.


The low cost and ease of implementation due to wireless communication capabilities in smart sensors make it easy for industrial companies to deploy many more sensors than has been typical with legacy wired sensor technologies. This eases the transition from condition monitoring to predictive maintenance.

How smart sensors enable predictive maintenance

Predictive maintenance requires analysis of historical data to assess if equipment is trending towards a failure. Griffin notes that machine learning (ML) algorithms are increasingly being used by analytics software providers to “enhance the understanding of the application being measured” based on the historical data produced by the smart sensor.

Blake Griffin, senior analyst, Interact AnalysisBlake Griffin, senior analyst, Interact Analysis“This not only expands the number of applications able to be monitored beyond well understood ones, it also increases the amount of time operation managers have to resolve a piece of equipment that is trending towards failure,” he says.

While these ML algorithms are predominantly used in predictive maintenance analytic software, Griffin says Interact Analysis is seeing some cases where these algorithms are being embedded in the smart sensor to “determine what data is relevant before transmitting that data to the software for deeper analysis.”

Griffin expects this trend of embedding ML algorithms on the sensor as an important future trend for the sensor technology market.

“Since the advent of smart sensors, major automation vendors like ABB, Siemens, WEG, and Nidec have all released their own versions,” Griffin says. “We expect this trend to continue as the product is desperately needed for manufacturers to begin generating tangible benefits from IIoT technology.”


   A smart sensor example from Petasense.


Discover New Content
Access Automation World's free educational content library!
Unlock Learning Here
Discover New Content
Test Your Machine Learning Smarts
Take Automation World's machine learning quiz to prove your knowledge!
Take Quiz
Test Your Machine Learning Smarts