Autor(en): Geyer, Hannes
Mandischer, Martin
Ulbig, Peter
Titel: Comparison of Neural Networks, Evolutionary Techniques and Thermodynamic Group Contribution Methods for the Prediction of Heats of Vaporization
Sprache (ISO): en
Zusammenfassung: 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.
Schlagwörter: chemical engineering
evolution strategies
hybrid-learning
neural networks
URI: http://hdl.handle.net/2003/5375
http://dx.doi.org/10.17877/DE290R-5015
Erscheinungsdatum: 2001-10-16
Provinienz: Universität Dortmund
Enthalten in den Sammlungen:Sonderforschungsbereich (SFB) 531

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
ci70.pdfDNB427.15 kBAdobe PDFÖffnen/Anzeigen
ci70.ps1.14 MBPostscriptÖffnen/Anzeigen


Diese Ressource ist urheberrechtlich geschützt.



Diese Ressource ist urheberrechtlich geschützt. rightsstatements.org