Back to Search
Start Over
Deterministic global process optimization: Accurate (single-species) properties via artificial neural networks
- Source :
- Computers & Chemical Engineering. 121:67-74
- Publication Year :
- 2019
- Publisher :
- Elsevier BV, 2019.
-
Abstract
- Global deterministic process optimization problems have recently been solved efficiently in a reduced-space by automatic propagation of McCormick relaxations (Bongartz and Mitsos, J. Global Optim, 2017). However, the previous optimizations have been limited to simplified thermodynamic property models. Herein, we propose a method that learns accurate thermodynamic properties via artificial neural networks (ANNs) and integrates those in deterministic global process optimization. The resulting hybrid process model is solved using the recently developed method for deterministic global optimization problems with ANNs embedded (Schweidtmann and Mitsos, J. Optim. Theory Appl., 2018). The optimal operation of a validated steady state model of an organic Rankine cycle is solved as a case study. It is especially challenging as the thermodynamic properties are given by the implicit Helmholtz equation of state. The results show that modeling of thermodynamic properties via ANNs performs favorable in deterministic optimization. This method can rapidly be extended to include properties from existing thermodynamic libraries, based on models or data.
- Subjects :
- Organic Rankine cycle
Mathematical optimization
TheoryofComputation_COMPUTATIONBYABSTRACTDEVICES
Optimization problem
Helmholtz equation
Artificial neural network
Computer science
Property (programming)
020209 energy
General Chemical Engineering
Process (computing)
02 engineering and technology
Computer Science Applications
020401 chemical engineering
0202 electrical engineering, electronic engineering, information engineering
Process optimization
State (computer science)
0204 chemical engineering
Subjects
Details
- ISSN :
- 00981354
- Volume :
- 121
- Database :
- OpenAIRE
- Journal :
- Computers & Chemical Engineering
- Accession number :
- edsair.doi...........fa9aa4818c3a75db807b5a54a0209814