Deterministic global process optimization: Accurate (single-species) properties via artificial neural networks
Authors:
- Artur M. SchweidtmannASArtur M. Schweidtmann
- Wolfgang R. HusterWHWolfgang R. Huster
- Jannik T. LüthjeJLJannik T. Lüthje
- Alexander MitsosAMAlexander Mitsos
- 1 February 2019
- journal article
- research article
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 121, 67-74
Abstract
No abstract availableKeywords
Funding Information
- Bundesministerium für Wirtschaft und Technologie (19U14010C)
- Bundesministerium für Forschung, Technologie und Raumfahrt (19U14010C)
- Bundesministerium für Wirtschaft und Energie (19U14010C)
This publication has 37 references indexed in Scilit:
- An algorithm for the use of surrogate models in modular flowsheet optimizationAIChE Journal, 2008
- Modeling of thermodynamic properties of refrigerant/absorbent couples using data mining processEnergy Conversion and Management, 2007
- Thermodynamic analysis of absorption systems using artificial neural networkRenewable Energy, 2006
- A polyhedral branch-and-cut approach to global optimizationMathematical Programming, 2005
- Investigation of thermodynamic properties of refrigerant/absorbent couples using artificial neural networksChemical Engineering and Processing - Process Intensification, 2004
- Use of artificial neural networks for calculating derived thermodynamic quantities from volumetric property dataFluid Phase Equilibria, 2003
- Modeling of thermodynamic properties using neural networksFluid Phase Equilibria, 2002
- Global Optimization of Modular Process FlowsheetsIndustrial & Engineering Chemistry Research, 2000
- Potential applications of artificial neural networks to thermodynamics: vapor–liquid equilibrium predictionsComputers & Chemical Engineering, 1999
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989