TY - GEN
T1 - Indirect training with error backpropagation in gray-box neural model
T2 - Application to a chemical process
AU - Naranjo, Francisco Cruz
AU - Leiva, Gonzalo Acuña
PY - 2010
Y1 - 2010
N2 - Gray-box neural models mix differential equations, which act as white boxes, and neural networks, used as black boxes, to complete the phenomenological model. These models have been used in different researches proving their efficacy. The aim of this work is to show the training of the gray-box model through indirect back propagation and Levenberg-Marquardt. The gray-box neural model was tested in the simulation of a chemical process in a continuous stirred tank reactor (CSTR) with 5% noise, responding successfully.
AB - Gray-box neural models mix differential equations, which act as white boxes, and neural networks, used as black boxes, to complete the phenomenological model. These models have been used in different researches proving their efficacy. The aim of this work is to show the training of the gray-box model through indirect back propagation and Levenberg-Marquardt. The gray-box neural model was tested in the simulation of a chemical process in a continuous stirred tank reactor (CSTR) with 5% noise, responding successfully.
KW - chemical processes
KW - gray-box neural model
KW - neural networks
KW - time-varying parameters
UR - https://www.scopus.com/pages/publications/79955942327
U2 - 10.1109/SCCC.2010.41
DO - 10.1109/SCCC.2010.41
M3 - Conference contribution
AN - SCOPUS:79955942327
SN - 9780769544007
T3 - Proceedings - International Conference of the Chilean Computer Science Society, SCCC
SP - 265
EP - 269
BT - Proceedings - 29th International Conference of the Chilean Computer Science Society, SCCC 2010
PB - IEEE Computer Society
ER -