TY - JOUR
T1 - Training based, moving digital filter method for real time heat flux function estimation
AU - Kowsary, Farshad
AU - Mohammadzaheri, Morteza
AU - Irano, Saeed
PY - 2006/12
Y1 - 2006/12
N2 - In this paper the neural networks is utilized to estimate the "filter coefficients" needed to estimate heat flux in a particular system. In developing the training phase of the network inspiration is drawn from the Burgraff's exact solution of the IHCP as well as the filter method. Thus, the estimation phase neither requires any temperature field nor the sensitivity coefficients calculations. The neural network used in this work is a 2-layer perceptron. It is shown via classical triangular heat flux test cases that the method can yield very accurate, very efficient as well as stable estimations.
AB - In this paper the neural networks is utilized to estimate the "filter coefficients" needed to estimate heat flux in a particular system. In developing the training phase of the network inspiration is drawn from the Burgraff's exact solution of the IHCP as well as the filter method. Thus, the estimation phase neither requires any temperature field nor the sensitivity coefficients calculations. The neural network used in this work is a 2-layer perceptron. It is shown via classical triangular heat flux test cases that the method can yield very accurate, very efficient as well as stable estimations.
KW - Artificial neural networks
KW - Heat flux estimation
KW - Inverse heat conduction
UR - http://www.scopus.com/inward/record.url?scp=33750834473&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33750834473&partnerID=8YFLogxK
U2 - 10.1016/j.icheatmasstransfer.2006.08.013
DO - 10.1016/j.icheatmasstransfer.2006.08.013
M3 - Article
AN - SCOPUS:33750834473
SN - 0735-1933
VL - 33
SP - 1291
EP - 1298
JO - International Communications in Heat and Mass Transfer
JF - International Communications in Heat and Mass Transfer
IS - 10
ER -