gopal

Fit for Purpose - Layers of Analytics using the PI System – AF, MATLAB, Machine Learning...

Blog Post created by gopal on Jul 11, 2018

The following is from the notes for the hands-on lab "Fit for Purpose - Layers of Analytics using the PI System – AF, MATLAB, Machine Learning..." at PI World 2018, San Francisco, CA.  Lab manual and slides are attached - scroll to the end of the blog post.

 

A talk on this topic is hereAnd slide deck from the talk is here.

 

Briefly, the talk and the lab walks through - with examples -  the Layers of Analytics approach which depends on the use case -  operations, maintenance, quality etc.

 

LayersOfAnalytics.PNG

 

 

In plant floor process operations, the often used "Descriptive, Diagnostic, Predictive, Prescriptive" layer is explored using an oil refinery unit operation (Alkylation Feed Dryer) example.

 

In  asset maintenance/reliability, the UbM, CbM, PdM layer is explored using a motor/pump assembly with degrading health (inferred via vibration measurements) and predicting RUL (remaining useful life).

 

For an extended blog post, see Fit for Purpose - Layers of Analytics using the PI System 

Outcomes