When a plant or unit operation is not performing at its optimal efficiency, it is useful to track downtime and quantify the gap between equipment operation and perfect production. Opportunities to improve production can be understood using the Overall Equipment Effectiveness (OEE) metric.
When out of specification material is produced, organizations can spend precious time and money trying to identify the root cause. Machine learning allows users to compare process data to known periods of good and/or bad production to identify aberrant periods and key contributors.
In this workshop, we will walk through OEE and ML for pharmaceutical processes. We will use example process data to
1. Demonstrate techniques to identify downtime and build out OEE metrics to identify production opportunity
2. Use machine learning to compare process data to a predefined baseline to isolate the key contributor to process upsets.
Note: This is a hands-on workshop; participants are encouraged to bring their own laptops to be able to walk through OEE and ML practice examples led by the workshop instructors.