Optimization of the chain transfer agent incremental addition in SBR emulsion polymerization

Abstract

The incremental addition of chain transfer agent (CTA) in an emulsion styrene-butadiene polymerization reaction was optimized, using a chemometric approach that involves (a) an experimental design, in which the amount of CTA in each addition were the factors; (b) an artificial neural network modeling to obtain responses for each required processability property (i.e., Mooney viscosity and number-and weight-average molecular weight); and (c) a simultaneous desirability response, due to several properties had to be optimized at a time. As a result, an 8% increase in productivity was accomplished, and some relationships were derived among CTA additions and polymer evolution, Mooney viscosity and molecular weights. The study was carried out to further apply this strategy in the production plant. The challenge was to keep the quality of the produced polymer, particularly in terms of processability.

Surrogate Models for Online Monitoring and Process Troubleshooting of NBR Emulsion Copolymerization

“…Otherwise, their performance will be limited and their predictions will be different from the expected dynamics [11]. With sufficient training data, ANN can efficiently be used for prediction of steady state properties as reported by Vijayabhaskar et al [12], Assenhaimer et al [13], and Delfa and Boschetti [14]. For emulsion copolymerisation systems.…”

Bringing the On‐Line Control and Optimization of Semibatch Emulsion Copolymerization to the Pilot Plant

“…Concerning in silico process optimization, some authors employed artificial neural networks in order to reduce complexity of the problem, while others connected first‐principle models with iterative dynamic programming or utilized multivariate statistical process control . Asua suggested utilizing the heuristic knowledge of plant operators to build an optimization system based on fuzzy logic.…”

Prediction of the Styrene Butadiene Rubber Performance by Emulsion Polymerization Using Backpropagation Neural Network

“…e scienti�c workers are looking for a model to simulate the relationship between the polymerized styrene butadiene rubber performance and formula, what can provide reference to adjust formula and predict the product properties [4][5][6][7]. e arti�cial neural network (ANN) is composed of a large number of neurons by communicating through the adjustable metric.…”