Big Data Analytics: Lessons We Have Learned and Case Studies, 2021 TAPPICon Live (21TAPL)

Big data and artificial intelligence is all the rage today.   The premise is simple: with the right software, you can glean insights into your process that have gone undiscovered in over 100 years of making paper.  But the enemy of operational efficiency is not failure to understand what drives the process, it is failure to recognize the events that cause problems.   

To be sure, every process has a historical “sweet spot” in which performance was wonderful. But unless there are engineering reasons to explain why, the data is most likely happenstance and replicating it will not produce superior performance.  Complicating big data is the fact that historical data is distorted by human and control policies – for example, an operator faced with low STFI might increase basis weight but if fiber alignment is the issue, STFI will still be low.  Classic statistical methods will conclude the way to increase STFI is to decrease weight – the opposite of what we know to be true.   

This presentation will discuss why event detection is so important, why identifying the timing of a change is more important than the statistical modeling, and why it is critical that data scientists understand the processes they are working on.  

TAPPI conference proceedings and presentations, technical papers, and publication articles provide technical and management data and solutions on topics covering the Pulp, Paper, Tissue, Corrugated Packaging, Flexible Packaging, Nanotechnology and Converting Industries.

Simply select the quantity, add to your cart and your conference paper, presentation or article will be available for immediate download.