Paper Number
AM12 

Session
AI and ML Based Rheological Characterization

Title
Physical insights from machine learning tools

Presentation Date and Time
October 10, 2022 (Monday) 3:45

Track / Room
Track 6 / Mayfair

Authors (Click on name to view author profile)

1. Caggioni, Marco (Procter & Gamble)
2. Hipp, Julie (The Procter & Gamble Company, Complex Fluids)
3. Tozzi, Emilio (The Procter & Gamble Company, Complex Fluids)
4. Lindberg, Seth (The Procter & Gamble Co)
5. Hartt, William H. (The Procter & Gamble Co)

Author and Affiliation Lines (in printed abstract book)
Marco Caggioni, Julie Hipp, Emilio Tozzi, Seth Lindberg and William H. Hartt
The Procter & Gamble Co, West Chester, OH 45069

Speaker / Presenter 
Caggioni, Marco

Keywords
AI based; colloids; glasses; ML based

Text of Abstract
Machine learning (ML) and artificial intelligence (AI) are proving powerful data analysis tools in many different fields, including rheology. Sometimes, at least at the level of industrial applications, these tools are proposed as replacement for more standard, first principle approaches: “black-box machine learning”. It has been shown however that this does not need to be the case and insight into the system under study can be gained from ML models. In this contribution we focus on recently developed ML tools (1) for the superposition of data sets and we demonstrate how this tools can provide objective metrics to assist fundamental development of rheological models and data analysis.

1. Lennon, K. R., Mckinley, G. H. & Swan, J. W. A Data-Driven Method for Automated Data Superposition with Applications in Soft Matter Science. arXiv:2204.09521 (2022).