Hybrid Method to Predict Melting Points of Organic Compounds Using Group Contribution plus Neural Network plus Particle Swarm Algorithm

The melting points of organic compounds were estimated using a hybrid method that includes a simple group contribution method (GCM) implemented in an artificial neural network (ANN) replacing standart backpropagation with particle swarm optimization (PSO). A total of 439 compounds have been used to train the network developed using MatLab. Then, the melting points of 100 other Compounds have been predicted and results compared to experimental data and other models availables in the literature. The study shows that the proposed GCM + ANN + PSO model represents an excellent alternative for the estimation of melting points of organic compounds (average absolute relative deviation (AARD) = 7%) from the knowledge of the molecular structure.