Numerical simulation, clustering, and prediction of multicomponent polymer precipitation

Abstract

Multicomponent polymer systems are of interest in organic photovoltaic and drug delivery applications, among others where diverse morphologies influence performance. An improved understanding of morphology classification, driven by composition-informed prediction tools, will aid polymer engineering practice. We use a modified Cahn–Hilliard model to simulate polymer precipitation. Such physics-based models require high-performance computations that prevent rapid prototyping and iteration in engineering settings. To reduce the required computational costs, we apply machine learning (ML) techniques for clustering and consequent prediction of the simulated polymer-blend images in conjunction with simulations. Integrating ML and simulations in such a manner reduces the number of simulations needed to map out the morphology of polymer blends as a function of input parameters and also generates a data set which can be used by others to this end. We explore dimensionality reduction, via principal component analysis and autoencoder techniques, and analyze the resulting morphology clusters. Supervised ML using Gaussian process classification was subsequently used to predict morphology clusters according to species molar fraction and interaction parameter inputs. Manual pattern clustering yielded the best results, but ML techniques were able to predict the morphology of polymer blends with ≥90% accuracy.

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

“…Kriging has been successfully used to classify and cluster data with accuracy [302]. Considering the simplicity and reduced computational time of Gaussian process and kriging, in recent years this methodology has been used extensively to model the physical properties of different polymer composites with fairly good accuracy [303][304][305][306][307][308][309][310][311][312][313][314][315][316][317].…”

Continuum-scale modelling of polymer blends using the Cahn–Hilliard equation: transport and thermodynamics

“…First, all the approximations resulted in numerical instability especially with the variable mobility model for Case 2. The exception to note is for the cases involving the symmetric double-well potential where 3/4 of the simulations terminated early not because of numerical instability during the emergence of a pattern, but rather because no pattern was forming 11 .…”

“…Correspondingly, κ needs to be accounted for in the flux expression. Often, in isothermal cases, D i j is taken as a constant and treated as the scaling for M i j , resulting in the following expression for M 12 which has been used in studies involving polymer blends 6,8,10,11 :…”

“…This result is not entirely unexpected as there are only two phases present, which severely restricts the complexity of the observable morphologies. For ternary or multicomponent mixtures, the morphology can be significantly more complex 10,11 and 3D simulations may be necessary to resolve important structural details.…”

“…A common method to model the formation of these polymer blends at continuum length scales is to adopt a modified Cahn-Hilliard framework. This approach has previously been used to model binary 8,9 or ternary polymer blends 6,10,11 , or systems consisting of polymers and solvents. 12 This framework can also be readily coupled to other equations such as the Stokes 9 or Navier-Stokes equations 13 for modelling more-complex processes involving flow-induced shearing effects.…”