Modeling sterilization process of canned foods using artificial neural networks

dc.creatorGonçalves, E. C.
dc.creatorMinim, L. A.
dc.creatorCoimbra, J. S. R.
dc.creatorMinim, V. P. R.
dc.date2018-10-04T18:08:18Z
dc.date2018-10-04T18:08:18Z
dc.date2005-12
dc.date.accessioned2023-09-27T21:58:33Z
dc.date.available2023-09-27T21:58:33Z
dc.identifier02552701
dc.identifierhttps://doi.org/10.1016/j.cep.2005.04.001
dc.identifierhttp://www.locus.ufv.br/handle/123456789/22147
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8968893
dc.descriptionIn order to model the thermal processing of canned foods, the neural networks technique was applied, whose aim was to determine the cold point temperature based on the initial process conditions and the retort's temperature. The network had the following input variables: the processing time, the retort's and cold point's temperature at the current time ti, and at previous times ti−1 and ti−2. The output variable was the temperature of the cold point at the time ti+1. For training the network, a time/temperature data set was obtained through the product processing in a vertical retort. The back-propagation through time and Jordan networks were trained and its generalization performance were compared. In this work, a better generalization capacity were obtained using the back-propagation through time network, which presented an average relative error of 2.2% between the calculated and predicted F values. The architecture of the selected network was the 5-8-9-1.
dc.formatpdf
dc.formatapplication/pdf
dc.languageeng
dc.publisherChemical Engineering and Processing: Process Intensification
dc.relationv. 44, n. 12, p. 1269- 1276, dez. 2005
dc.rightsElsevier B.V.
dc.subjectSterilization
dc.subjectArtificial neural networks
dc.subjectCanned food
dc.titleModeling sterilization process of canned foods using artificial neural networks
dc.typeArtigo


Este ítem pertenece a la siguiente institución