Authors: Geyer, Hannes
Mandischer, Martin
Ulbig, Peter
Title: Comparison of Neural Networks, Evolutionary Techniques and Thermodynamic Group Contribution Methods for the Prediction of Heats of Vaporization
Language (ISO): en
Abstract: In this paper we report results for the prediction of thermodynamic properties based on neural networks, evolutionary algorithms and a combination of them. We compare backpropagation trained networks and evolution strategy trained networks with two physical models. Experimental data for the enthalpy of vaporization were taken from the literature in our investigation. The input information for both neural network and physical models consists of parameters describing the molecular structure of the molecules and the temperature. The results show the good ability of the neural networks to correlate and to predict the thermodynamic property. We also conclude that backpropagation training outperforms evolutionary training as well as simple hybrid training.
Subject Headings: chemical engineering
evolution strategies
hybrid-learning
neural networks
URI: http://hdl.handle.net/2003/5375
http://dx.doi.org/10.17877/DE290R-5015
Issue Date: 2001-10-16
Provenance: Universität Dortmund
Appears in Collections:Sonderforschungsbereich (SFB) 531

Files in This Item:
File Description SizeFormat 
ci70.pdfDNB427.15 kBAdobe PDFView/Open
ci70.ps1.14 MBPostscriptView/Open


This item is protected by original copyright



This item is protected by original copyright rightsstatements.org