A cooperation scenario for multiagent systems

Pozna, Claudiu; Precup, Radu‐Emil; Kóczy, László T.; Minculete, Nicuşor; Ballagi, Áron

doi:10.1109/afrcon.2011.6071961

Cited by 1 publication

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The association of polymerization reactions with neural networks is frequently encountered due, on the one hand, to the difficulties of modeling these complex processes and, on the other hand, due to the benefits brought by neural networks. [3][4][5] Also, different other strategies can be applied in polymer engineering for process or property simulation: simulations based on Newtonian flow model, [6] applications of signatures to expert systems modeling, [7] or machine learning techniques such as support vector machine, decision tree, random forest, extra tree or gradient boosted trees. [8] In this work, free radical polymerization of styrene is chosen as an example.…”

Section: Introductionmentioning

confidence: 99%

Neural network‐based hybrid models developed for free radical polymerization of styrene

Ghiba

Drăgoi

Curteanu

2020

Polymer Engineering & Sci

View full text Add to dashboard Cite

In the present work, the free radical polymerization of styrene is modeled by considering the phenomenology of the process (a simplified model, which does not include the diffusional effects, gel, and glass effects) in combination with an empirical model represented by an artificial neural network. Differential evolution (DE) algorithm, belonging to the class of evolutionary algorithms, is applied for developing the neural models in optimal forms. For improving the results—predicted conversion and molecular weights as function of time, temperature, and initiator concentration—different combinations between phenomenological model and neural network are tested; also, individual and stacked neural networks have been developed for the polymerization process. This methodology based on hybrid models, including neural networks aggregated in stacks, provides accurate results.

show abstract