To say we don’t know exactly what the future holds as AI continues to grow and evolve on a daily basis is, quite frankly, an understatement. AI is positioned to upend nearly everything we do, and process manufacturing is no exception. Yet, while it seems like there is nothing AI cannot do, that’s not entirely true. In a recent article in Plant Engineering magazine, Brian Overton identifies one area where AI desperately needs human assistance:
“There is one key thing AI cannot do: collect data from the field. For AI, data is everything.”
Take special note of the second part of that quote, because it is of critical importance to implementing AI correctly. AI software consumes tremendous amounts of data. It needs to in order to be effective. So, if a plant is still relying on intermittent manual rounds to collect data, even the most powerful AI tools are going to struggle to deliver the insights necessary to enact real change.
A data foundation for AI
Before jumping right into the shiniest new AI technology, it is important to put a data foundation in place. Fortunately, Brian shares, that is not difficult to do. Today, he explains,
“most plants are moving away from manual, route-based data collection in favor of automated online condition monitoring. A combination of both wireless and wired condition monitoring sensors—with a varying array of capabilities—empowers reliability teams to set whatever cadence of data collection best fits their unique circumstances. This type of solution also prepares these teams to implement the modern technologies that will drive operational excellence and competitive advantage in the years to come.”
Continuous condition monitoring comes in many forms. Small, easy-to-install wireless vibration sensors like Emerson’s AMS Wireless Vibration Monitor collect spectrum and waveform data from balance of plant assets and deliver an intuitive health score to technicians. However, that same data can be used to feed AI tools a much steadier flow of information. Not only does the data come in more frequently, but also more reliably, as the sensors are never burdened with other tasks that mean data collection must wait.
Other tools, like Emerson’s AMS Asset Monitor, not only deliver continuous data to both plant reliability personnel and AI tools, but also use built-in software to perform AI-driven edge analysis right at the source.
“Using built-in analytics, these devices can automatically identify common issues, such as imbalance and under-lubrication, in the most common assets: fans, motors, gearboxes, pumps, and other rotating machinery. Additional features, like a hardwired power supply to ensure continuous data collection, and the ability to automatically shut down assets when a problem is detected, make edge analytics devices a critical element of any continuous condition monitoring strategy.”
So, not only can teams have a constant flow of critical data to their enterprise AI software, but they also gain AI insights right at the asset or delivered to their mobile devices.
Data drives success
Most plants are already struggling to maintain the deep bench of personnel necessary to manage regular manual maintenance rounds. Coupled with the need for increased, more continuous data to drive AI tools, that challenge has inspired many organizations to shift their strategy, implementing continuous condition monitoring technologies to free technicians up for more valuable tasks around the plant. But it doesn’t stop there. Those same tools also drive the high-level analytics that promote increased optimization, decision support, and reliability, ultimately driving competitive advantage.
