Indirect training of Gray-Box Models using LS-SVM and genetic algorithms
- Resource Type
- Conference
- Authors
- Acuna, Gonzalo; Moller, Hans
- Source
- 2016 IEEE Latin American Conference on Computational Intelligence (LA-CCI) Computational Intelligence (LA-CCI), 2016 IEEE Latin American Conference on. :1-5 Nov, 2016
- Subject
- Bioengineering
Engineering Profession
General Topics for Engineers
Geoscience
Power, Energy and Industry Applications
Robotics and Control Systems
Training
Genetic algorithms
Mathematical model
Support vector machines
Sociology
Statistics
Data models
Gray Box models
Continuous Stirred Tank Reactor
Support Vector Machine
Genetic Algorithms
- Language
Gray-Box Models which combine a phenomenological model with a black box tool are useful for determining the values of not well known parameters of the model. In this work an indirect strategy for training these gray box models using least-square support vector machine and genetic algorithms is presented. The gray box model was tested in a Continuous Stirred Tank Reactor process with good results (Index of Agreement for the model output variable and the estimated time-varying parameter > 0.90).