Journal
CHEMICAL ENGINEERING AND PROCESSING-PROCESS INTENSIFICATION
Volume 44, Issue 12, Pages 1269-1276Publisher
ELSEVIER SCIENCE SA
DOI: 10.1016/j.cep.2005.04.001
Keywords
sterilization; artificial neural networks; canned food
Categories
Ask authors/readers for more resources
In 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 t(i), and at previous times t(i-1) and t(i-2). The output variable was the temperature of the cold point at the time ti,,. 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. (c) 2005 Elsevier B.V. All rights reserved.
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