Moneo Solutions

Air compression

Stop wasting compressed air with AI-assisted maintenance tool

The cost of air compressor leaks can be significant for any processing facility – not only is compressed air wasted, but the energy bills and toll on the equipment can be expensive. Leaks trigger a drop in system pressure, preventing air tools from working and impacting production. Additionally, leaks will cause an air compressor to cycle more regularly, incurring more maintenance and potential unplanned downtime.

Which is why Freddie Coertze, National IoT Business Manager at ifm Australia, says the modern plant needs predictive maintenance tools to get the insights required to protect assets and prevent waste.

“Why does the modern plant need data science tools to prevent compressed air waste? Because a compressor doesn’t run on load all the time,” explains Freddie. “It runs on variable load depending how much the factory or processing facility needs. To fully understand how the asset is performing, data needs to be collected from the equipment and analysed – but this is where there is a difference between solutions available.”

The ifm moneo, platform has been designed to provide the type of real-time insights into an air compressor that usually come with the employ of data science experts – by utilising artificial intelligence (AI) and other in-built smarts.

Moneo solutions for air compressors

“This is an AI-assisted, self-service predictive maintenance tool,” says Freddie. “It makes it very easy to harvest the data from a complex system, putting the power back into the hands of the business so they can achieve better productivity at their plant.”

To elaborate on his point, Freddie refers to a real example of where moneo has been used to monitor and improve an air compressor. Firstly, he describes the set up.

“All that is required for this set up is the moneo platform, which comes in the form of an IPC unit that we provide. This is very easy to install and doesn’t require going via an IT network to install device software,” he explains. “This links to an IO Link master which collects data from the sensor devices, and on this air compressor example we have flow meters, humidity, temperature, pressure and vibration sensors as well as a current transmitter to see how hard the compressor is working.”

According to Freddie, the moneo software will draw on historical data to create set parameters in which the compressor should be working, along with the live streamed data to provide an analysis. It does this through the use of AI algorithms and machine learning.

“In the case where we monitored an air compressor at a site, the moneo platform determined that the compressor was running at a loss and consuming more energy than it should, which was especially evident when the plant was shut for the weekend,” says Freddie. “Because the solution gives a holistic picture of the whole asset, we were also able to predict a future failure. This was easily remedied without any major consequences.”

While an air compressor is a strong example of where efficiency gains can be easily obtained, Freddie stresses that the moneo data science tool will provide greater predictability of all assets in a plant. Importantly, he notes that the moneo platform is agnostic and can be integrated with existing systems.

“To protect, you need to predict, but the difference is that now we can harness the benefits of AI to make this a simpler process for any manufacturing or processing facility,” he summarises. “With moneo, we provide a pre-packaged self-service kit that you can expand on, depending on your changing requirements. Significantly, this platform is a middleware that can sit between your sensor level and a higher end system such as Scada. And with the in-built AI and automated machine learning, you don’t need to involve a data scientist to get real-time, actionable insights.”

To learn more about the moneo platform please click here.
Or to access a free trial, you can register here.

Leave a Reply

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