Machine Modeling Enables a Predictive Maintenance Transformation
Grant Gerke | July 12, 2018
One of the major themes for manufacturing in 2018 has been machine modeling and recognition by management that it can replace capital purchases by moving to data baselines of processes. Case in point, Deschutes Brewery’s use of OSIsoft’s PI System to gain insight into their fermentation process and then further the application by using OSIsoft’s PI Integrator tool for Azure. This tool creates analysis-ready data for Microsoft’s Cortana Intelligence Suite to make predictions on when to transition between phases in the brewing process.
In essence, Deschutes Brewery automated this transition without buying more automation devices or equipment, and expanded the operators’ bandwidth by removing monitoring responsibilities.
The underlying theme in the Deschutes Brewery solution points to the need for more capacity utilization for the small brewer, as it tries to create new beer flavors/product to meet the consumers need for the “next new beer.”
A new white paper from sensor supplier Banner Engineering delivers insights on how to start a smart predictive maintenance solution. The white paper, “Predictive Maintenance Trends: How Machine Learning is Transforming Machine Maintenance,” features a quick five-step primer using machine learning, continuous monitoring, wireless communication, data logging, and local and remote indication.
From the white paper:
Condition monitoring plays a key role in predictive maintenance by allowing users to identify critical changes in machine performance. One important condition to monitor is vibration. Machine vibration is often caused by imbalanced, misaligned, loose, or worn parts. As vibration increases, so can damage to the machine. By monitoring motors, pumps, compressors, fans, blowers, and gearboxes for increases in vibration, problems can be detected before they become severe and result in unplanned downtime.