Sensing Opportunities in Predictive Maintenance Technology Innovation

We have expressed previously that predictive maintenance (PdM) is one of the most promising areas of the industrial internet of things (IIoT) and that there are a number of startups developing innovative sensor-based and/or software solutions. To identify where these technology developers are innovating, we took a look at the patent activity on PdM. During the past 20 years, there have been approximately 4,400 patents focused on PdM applications, and companies are filing more patent applications every year to differentiate themselves and protect their models, algorithms, or hardware-based solutions. In our “Predictive Maintenance: The Art of Uptime” report, we mentioned that innovations in connected sensing technologies and analytics are driving better operations, enabling users to gather and process real-time data on machine health to decrease downtime. For example, a study related to the oil and gas (O&G) industry revealed that performing PdM using a data-driven approach with sensors experienced 36% less unplanned downtime. There is still significant space for companies to decrease their unplanned downtime, and one method to do that is by adding more data streams from sensors. Therefore, we filtered our search to focus only on developments in PdM using sensing technologies, and we can see in Figure 1 that the IP space has been increasingly more active since 2014. Nonetheless, the patents aiming to protect sensor-based PdM are roughly 30% of the total amount of IP seeking protection for PdM applications.

Figure 1. Patent activity on predictive maintenance using sensor technology by years

Since there are multiple sensing technologies that can provide valuable information on the status of specific pieces of equipment or entire systems, we narrowed down the patent search to visualize the number of patents filed that aim to protect innovations using a particular sensor type (e.g. temperature, pressure). Figure 2 shows that out of all the patents filed over the past 20 years, temperature, noise, and pressure are the top three sensor types chosen by technology innovators to perform PdM. It’s worth mentioning that over 65% of the patents protecting PdM approaches using noise detection are focusing on ultrasound technology. A number of sources, including the U.S. Department of Energy (DOE), mention the advantages of using ultrasound monitoring for leak detection, pump cavitation, valve wear, and hydraulic system blockage, among others. Startups, such as Augury and 3DSignals, are developing PdM solutions for the industry based on ultrasonic wave detection.

Figure 2. Patent activity on predictive maintenance using specific sensor technologies

Including multiple sensor streams enables a better understanding of machine health and real-time status of industrial equipment. Several patents focused on PdM using sensor data actually involve more than one sensor type; for instance, there are 83 patents filed that include both temperature and pressure sensors. The downside of using multiple sensing technologies is that the cost per machine under monitoring adds up quickly to thousands of dollars. While some industrial sensors are priced around $500, others, such as noise-focused technologies like the one from 3DSignals, cost a few thousands of dollar per month. Therefore, for low-cost equipment, incumbent lower-cost temperature and pressure sensing technologies are good enough to improve operations. For high-end markets, such as O&G, where unplanned downtime translates to roughly $50 million in losses every year, a more complex and accurate set of data streams (and even new sensor data) are required. Readers interested in innovations for PdM solutions are advised to analyze the cost of their unplanned downtime to see what sensor suite fits best. Readers should look for technology integration opportunities leveraging different sensing solutions to maximize uptime of industrial equipment, especially in high-end markets where the sensing technology costs are justified by the significant savings.

By: Jessica Hernández