Condition Monitoring Foundations Create Informed Decision-Making

At Absolute Energy, a new condition monitoring approach targeted many process variables, including sound pressure loop data, process information from accelerometers, and manual measurements of actual sound levels.

A recent post on Efficient Plant’s Industrial Internet of Things (IIoT) channel delved into the topic of higher throughput for Absolute Energy — ethanol facility — and how the company invested resources into building out their condition monitoring program to ultimately find better production reliability. The ethanol producer employed an enhanced monitoring project of the main steam letdown system and the actionable data created informed decision-making, eliminating guesswork. The end result was their ultimate goal: Higher throughput due to less downtime.

While convincing executives of spending more on enhanced monitoring services is a tough nut to crack, so is explaining plant downtime. A recent post from Beth Crane, vp of data Sight Machine discusses how manufacturers need to create solid foundations for predictive maintenance investments, namely with serious re-engineering efforts.

Crane focuses on how successful enterprises execute predictive maintenance:

In addition to developing and implementing the models, these predictive models will require constant monitoring and tuning to ensure they continue to accurately represent the physical environment. This ongoing maintenance can also contribute to the significant costs of predictive maintenance efforts.

Cleaning up data in an enterprise can be costly and Crane points to a comprehensive approach before a company considers a proactive maintenance approach. The post lists three criteria needed for a successful move to Pd’M: System stability; system monitoring; and real-time process engineering.

In the case of Absolute Energy and Emerson Automation application, the added monitoring process targeted many variables to suss out the real cause of failure, including sound pressure loop data, process information from accelerometers, and manual measurements of actual sound levels.

With such granular monitoring, Absolute Energy could identify a correlation between high vibration areas back to the high-noise areas as well.

In Crane’s post, she bangs the drum for this approach as well:

Accurate monitoring is only as good as the proactive response by the manufacturer to any potential issue detected…

I’ve discovered, that in the process of building these capabilities, many manufacturers determine that they can achieve significant process improvements without the need for an expensive predictive maintenance models. Even in situations where predictive maintenance models do make sense, investing in the tools to build system stability, monitoring, and real-time process reengineering will ensure that predictive maintenance efforts have the required prerequisites to deliver long-term impact.

The roadmap to a more proactive maintenance approach has many turns, and continuous improvement in process engineering and monitoring is a good start. For Absolute Energy, the addition of thorough condition monitoring processes on top of process engineering best practices created higher throughput and wins for the plant.

>> Read the full post from Sight Machine’s Beth Crane