Comparison of Neural Networks, Evolutionary Techniques and Thermodynamic Group Contribution Methods for the Prediction of Heats of Vaporization
| dc.contributor.author | Geyer, Hannes | de |
| dc.contributor.author | Mandischer, Martin | de |
| dc.contributor.author | Ulbig, Peter | de |
| dc.date.accessioned | 2004-12-07T08:20:07Z | |
| dc.date.available | 2004-12-07T08:20:07Z | |
| dc.date.created | 1999 | de |
| dc.date.issued | 2001-10-16 | de |
| dc.description.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. | en |
| dc.format.extent | 1170327 bytes | |
| dc.format.extent | 437403 bytes | |
| dc.format.mimetype | application/pdf | |
| dc.format.mimetype | application/postscript | |
| dc.identifier.uri | http://hdl.handle.net/2003/5375 | |
| dc.identifier.uri | http://dx.doi.org/10.17877/DE290R-5015 | |
| dc.language.iso | en | de |
| dc.publisher | Universität Dortmund | de |
| dc.relation.ispartofseries | Reihe Computational Intelligence ; 70 | de |
| dc.subject | chemical engineering | en |
| dc.subject | evolution strategies | en |
| dc.subject | hybrid-learning | en |
| dc.subject | neural networks | en |
| dc.subject.ddc | 004 | de |
| dc.title | Comparison of Neural Networks, Evolutionary Techniques and Thermodynamic Group Contribution Methods for the Prediction of Heats of Vaporization | en |
| dc.type | Text | de |
| dc.type.publicationtype | report | |
| dcterms.accessRights | open access |