Today, it seems as though everyone has new personnel they need to rapidly upskill. While the expertise crisis resulting from the shrinking industrial workforce is nothing new, it certainly doesn’t seem to be getting better anytime soon. As a result, process manufacturers have had to find new ways to improve their workforces, not only with training, but with day-to-day support to help operators and technicians in the field more confidently make better decisions.
How have companies approached this new normal? The easy answer is automation and digital transformation. But scratch the surface a little bit and it is easy to see that even digital transformation is no simple task. Just as companies are reckoning with the tsunami of data that affordable, accessible sensing devices have created in their plants, a new player has burst onto the scene: AI.
Today, AI technologies are everywhere, and many of them offer powerful capabilities—for those ready to harness such technology. However, as Erik Lindhjem shares in his recent article in Smart Industry, the solution is not to abandon traditional automation and digital transformation initiatives to pursue whatever new AI tool appears on the market next. Rather,
“While AI tools are exciting, they are in their infancy, particularly in the industrial reliability space. Moreover, the comprehensive, integrated asset health systems today’s reliability teams are implementing as part of their digital transformation journeys are built on a strong foundation of machine learning, which itself is the foundation of AI.”
Decisions need data
Before teams can capture value from AI, they need the tools necessary to collect the massive amounts of contextualized data that AI models will consume. Modern sensing technologies are a key enabler of this data collection. Even the largest teams cannot hope to collect enough data to feed AI tools using manual rounds. They need tools like Emerson’s AMS Wireless Vibration Monitor to continuously collect asset health data—both to provide instant insight into the health of assets, and to feed AI tools the information they will need to effectively track and trend asset performance. As Erik explains, this is exactly what today’s modern worker is expecting,
“Wireless vibration monitors assist lean teams by untethering them from their workstations. Today’s more mobile digital natives can instantly and securely check asset health reports from wireless vibration monitors from anywhere—inside or outside the plant—using their mobile devices. Instead of stopping other high value tasks to spend time walking around the plant collecting data, personnel can instead integrate monitoring into their other daily tasks.”
AI at the edge
However, teams don’t have to implement complex new software packages to take advantage of the benefits of industrial AI. Emerson’s AMS Asset Monitor already provides AI capabilities at the edge to help operators and technicians quickly and easily identify common issues with their assets regardless of experience level. Like the AMS Wireless Vibration Monitor, AMS Asset Monitor automatically collects health data, but then it goes a step further,
“After collecting the data, the edge analytics device applies built-in analysis tools, designed based on decades of…domain knowledge, to automatically identify the most common issues with fans, motors gearboxes, pumps, and other rotating machinery, such as imbalance and lubrication issues.”
Users not only get key information right in the palm of their hand, but they can also quickly and easily add it to an enterprise asset management platform like AMS Optics, where powerful tools like Emerson’s Aspen Mtell® use industrial AI agents to identify anomalies and detect degradation in their assets.
Stay the course
We often refer to digital transformation as a journey, and the rise of AI doesn’t change that sentiment. While AI tools will undoubtedly shape the future of process manufacturing, they are still only a small part of the overall reliability puzzle. Not only are traditional reliability tools still the best way to manage and maintain a plant’s assets, but they also build the critical data foundation necessary to implement AI technologies successfully. Don’t be afraid to adopt new AI technologies, but be sure they are purpose-built to support your existing (and expanding) traditional reliability technology infrastructure.
