Predicting polymer properties using neural networks

Elizabeth R. Collantes, Tamara Gahimer, William J. Welsh, Michael Grayson

Research output: Contribution to conferencePaperpeer-review


Seeking novel approaches for predicting bulk polymer properties directly from a knowledge of molecular-level properties, values of Tg and tensile modulus for the subject polyimides were calculated based on input of seven molecular descriptors using both partial-least-squares (PLS) multivariate regression and artificial neural networks (ANNs). The residual standard deviation (RSD) between calculated and experimental values of Tg was 17 K from PLS and 22 K from ANN. The corresponding RSD for tensile modulus was 0.15 GPa from PLS and 0.12 GPa from ANN. For both Tg and E, the molecular descriptor with the major contribution to the PLS and ANN models was the `number of rotational degrees of freedom' within the repeat unit.

Original languageEnglish (US)
Number of pages4
StatePublished - 1997
Externally publishedYes
EventProceedings of the 1997 55th Annual Technical Conference, ANTEC. Part 3 (of 3) - Toronto, Can
Duration: Apr 27 1997May 2 1997


OtherProceedings of the 1997 55th Annual Technical Conference, ANTEC. Part 3 (of 3)
CityToronto, Can

All Science Journal Classification (ASJC) codes

  • Chemical Engineering(all)
  • Polymers and Plastics


Dive into the research topics of 'Predicting polymer properties using neural networks'. Together they form a unique fingerprint.

Cite this