Artificial intelligence estimation of vapor pressure

In this study, an Artificial Neural Network (ANN) modeling for estimation of vapor pressure is proposed. Different data from several pure materials have been collected. Temperature and acentric factor have been considered as network inputs. Vapor pressure is the network outputs. 70 percent of the data have been used for training of ANN. Among the multilayer feed-forward architectures a preprocessing and post processing network with 16 hidden neurons has been found as best feed-forward predictor. The result of network has successfully been validated with experimental data.

کلیدواژه ها:

M-Z equation ، Vapor pressure ، Equation of state