Related Concept Videos
Polymers: Molecular Weight Distribution
Molecular Weight of Step-Growth Polymers
As the step-growth polymerization involves step-wise condensation of monomers, the molecular weight also builds up eventually. Consequently, high molecular weight polymers are obtained at the late stages of the polymerization, where 99% of monomers have been consumed.
The extent of the...
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Detection and Dispersion Analysis of Water Globules in Oil Samples Using Artificial Intelligence Algorithms.
Nonlinear Rheological Processes Modeling in Three-Layer Plates with a Polyurethane Foam Core.
Related Experiment Video
Updated: Aug 25, 2025

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants
Published on: March 1, 2019
Determining the Rheological Parameters of Polymers Using Artificial Neural Networks.
1Strength of Materials Department, Faculty of Civil and Industrial Engineering, Don State Technical University, 344003 Rostov-on-Don, Russia.
Artificial neural networks can predict polymer properties from stress relaxation curves. This method accurately determines rheological parameters without data smoothing, offering a versatile alternative to standard techniques.
Area of Science:
- Polymer Science
- Materials Science
- Computational Modeling
Background:
- Predicting polymer properties is crucial for material design.
- Traditional methods for analyzing stress relaxation data can be complex and require data preprocessing.
- Artificial neural networks (ANNs) offer a promising computational approach for complex material behavior analysis.
Purpose of the Study:
- To investigate the efficacy of ANNs in determining polymer rheological parameters from stress relaxation curves.
- To develop and validate an ANN model for this purpose.
Main Methods:
- Utilized the nonlinear Maxwell-Gurevich equation as the governing deformation law.
- Developed an algorithm for generating training data from theoretical stress relaxation curves using the Euler method.
- Trained ANNs in the MATLAB environment, using Mean Square Error (MSE) as the training performance criterion.
- Validated the ANN model against experimental stress relaxation data of recycled polyvinyl chloride.
Main Results:
- The ANN model demonstrated good approximation quality for experimental relaxation curves.
- The performance of the ANN model was comparable to standard data processing methods.
- A key advantage of the ANN approach was the elimination of the need for preliminary data smoothing.
Conclusions:
- ANNs provide a viable and efficient method for determining polymer rheological parameters from stress relaxation data.
- The proposed technique is adaptable for analyzing creep curves and various testing conditions (tension, bending, torsion, shear).
- This approach offers a robust alternative to conventional methods, simplifying data analysis and expanding applicability.

