Neural network-particle swarm modeling to predict thermal properties

Seven thermal properties: melting point temperature, boiling point temperature, critical temperature, autoignition temperature, flash point temperature, lower flammability limit temperature and upper flammability limit temperature, were estimated using a hybrid method that includes an artificial neural network (ANN) with particle swarm optimization (PSO). A database of 530 substances was used in the training of this hybrid algorithm. To discriminate the different substances the molecular structures were given as input parameters. Different topologies of the neural network were studied and the best architecture was determined. The optimal condition of the network was obtained adjusting the PSO parameters by trial-and-error. The results show that the proposed ANN+PSO method represent an excellent alternative for the estimation of thermophysic properties with acceptable accuracy.

► 530 substances were studied with the hybrid ANN+PSO algorithm.
► Different topologies of the ANN were studied.
► The optimal weights were obtained adjusting the PSO parameters.
► The results show that the incorporation of structural groups as input was crucial.