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 | Size | Format | |
---|---|---|---|---|
ci70.pdf | DNB | 427.15 kB | Adobe PDF | View/Open |
ci70.ps | 1.14 MB | Postscript | View/Open |
This item is protected by original copyright |
This item is protected by original copyright rightsstatements.org