Journal
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
Volume 171, Issue -, Pages 198-206Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.chemolab.2017.11.004
Keywords
Response surface methodology (RSM); Artificial neural networks (ANN); Desirability function
Categories
Funding
- Universidad Nacional de Rosario [19/B487]
- CONICET (Consejo Nacional de Investigaciones Cientificas y Tecnicas) [PIP 2015-111]
- ANPCyT (Agencia Nacional de Promocion Cientifica y Tecnologica) [PICT 2014-0347, 2016-1122]
Ask authors/readers for more resources
SRO_ANN, a MatLab (R) toolbox for implementing multiple surface response optimization by artificial neural networks (SRO_ANN) is presented. Radial basis functions, a type of artificial neural networks, are applied through an easily managed graphical user interface. A detailed description of the interface is provided, including a simulated and two literature examples which allow one to show the potentiality of the software. The discussed experimental examples correspond to: (1) the maximization of the research octane number (RON) of fuels, influenced by three factors (reaction temperature, operating pressure and low liquid hourly space velocity), and (2) the optimization of the calcification process for diced tomatoes, evaluated through three different responses (calcium content, firmness and pH), which are affected by three factors (calcium concentration, solution temperature and treatment time). The results show that the application of a nonparametric tool can enhance the performance of optimization modeling tasks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available