Please use this identifier to cite or link to this item:
|Type:||Capítulo de livro|
|Title:||Neural Network Based Software Sensors: Application To Biosurfactant Production By Candida Lipolytica|
|Abstract:||This paper showed that on-line estimation and multi-step ahead prediction of emulsification activity and biomass concentration could be satisfactorily carried out employing well-trained feedforward backpropagation neural networks with one hidden layer. The results showed that neural 'software sensors' supplied for biomass concentration and emulsification activity on-line estimation and prediction within an acceptable variation of 5% of the experimental values. Coefficients of determination higher than 0.90 indicated excellent agreement of the neural network models with experimental test values, obtained for biomass concentration and emulsification activity. © 2006 Wiley-VCH Verlag GmbH & Co. KGaA.|
|Editor:||John Wiley and Sons|
|Appears in Collections:||Unicamp - Artigos e Outros Documentos|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.