Description:

INV-21050

Background

 Many complex and structured fluids exhibit a wide range of rheological responses to different flow characteristics. The ability to predict this complex rheological behavior is essential in better understanding and designing these complex fluids and their processing conditions. Despite the increasing trend in using artificial intelligence and machine learning algorithms in many avenues of science, technical issues in material science and fluid mechanics cause this field to lag. 

Over the past few decades, software packages have been developed to perform fluid mechanical and rheological simulation of a given condition however, none of these find the same success in the industrial setting as they do in academic environments. This is due to lack of accuracy, adaptability, and ease of use. A new methodology that utilizes machine learning algorithms in prediction and design of rheological behavior of complex fluid with higher accuracy and adaptability is needed.

Technology Overview

Researchers at Northeastern leverage advances in artificial intelligence and machine learning in solving complex problems in materials science and complex fluids. In this technology, they recruited two interconnected neural networks, each consisting of hidden layers and neurons. In one of the two neural networks, synthetic data generated from conventional models are used as input, and the other one uses actual experimental data on the problem under investigation. This new methodology significantly reduces the number of data points required to perform meaningful machine-learning predictions. Also, this new algorithm incorporates physical intuition into the neural network to capture the experiment conditions, including temperature, salinity, and aging, which significantly enhances the prediction reliability. In contrast to usual deep learning platforms, using physical models enables this technology to predict behaviors outside the training window. This technology accelerates material design and discovery, and for predicting the rheological behavior of complex systems across a wide range of conditions. 

Benefits

  • Fast and accurate modeling of material flow and stability conditions over time
  • Requires fewer inputs to provide reliable predictions
  • Agile and adaptable model for new materials/processes 

 

Applications

Material design and prediction of rheological behavior of complex fluid in:

  • Chemical companies 
  • Oil/gas industry 
  • Plastic and polymer industry 
  • Consumer cosmetics and cleaners producers
  • Pharmaceutical industry 

Opportunity

  • License
  • Partnering
  • Research collaboration
Patent Information:
For Information, Contact:
Mark Saulich
Associate Director of Commercialization
Northeastern University
m.saulich@northeastern.edu
Inventors:
Mohammadamin Mahmoudabadbozchelou
Safa Jamali
Keywords:
3D Printer
Adaptive
Artificial intelligence
Biotech
Computational Modeling
Deep learning
Fabrication
Machine Learning
Manufacturing
Materials
Oil/petroleum
Process Engineering