Professional Documents
Culture Documents
Rodrigo Ghiorzzi Donni, Paulo Smith Schneider and Ivoni Carlos Acunha Jr.
COB9721
Artificial Neural Network (ANN) is used to simulate a condenser behavior on a more controlled base,
allowing for the statistical assessment by Design of Experiments (DoE).
COB9721
2 / 19
Heat exchange efficiency can be increased by the aid of phase change processes;
Simultaneous heat and mass transfer in an evaporative heat exchanger, the process becomes more
complex in comparison to the conventional system;
In the experimental model, controlled parameters are only the volumetric flow of air and mass of sprayed
water . All experimental tests are conducted in steady state.
COB9721
3 / 19
COB9721
4 / 19
Statistical design of experiments refers to the process of planning the experiment allowing appropriate
data are collected and analyzed by statistical methods resulting in valid and objective conclusions;
Experimental design becomes indicated because it allows all the considered parameters to vary allowing
all possible combinations of parameters and levels are possible;
Reduces the experimental effort and allows for obtaining reliable conclusions; The DoE methodology allow us to implement a model of regression to fit the experimental data
considering the effects of interactions of the parameters.
COB9721
5 / 19
Variable (Uncontrolled)
COB9721
6 / 19
An ANN is capable of learning from inputs, and from this point, produces different outputs from those used
in their training;
The process of training an ANN to simulate functions based on input and output data begins by adjusting
the weights and subsequent comparison between the value found and the actual value;
The weights are adjusted iteratively until the difference found between the simulated and actual response
is within an acceptable error value or until it reaches a maximum value of iterations.
COB9721
7 / 19
X1
X2
W1 W2
Bias b
Activation Function
Input Data
Output Data
Xn
...
Wn
Weighs
...
Sum Function
COB9721
8 / 19
Levels
Low Tdb,e Twb,e Tr22,cds Tag,asp mag mar 19.7C 15.5C 28.0C 22.0C High 23.5C 19.3C 31.0C 25.5C
Experiemtnal Setup
Not controlled
Mass flow rate of water(*) Mass flow rate of air in the condenser(*)
(*) Volumetric
flows measured and evaluated at air and water temperatures to get the mass flows.
Heat rejected in the evaporative condenser is the response used to obtained overall heat transfer
coefficient and determinate the performance of each combination of parameters;
Simulation of 64 combinations of all parameters and 1 central point (the mean value between high
and low levels).
COB9721
10 / 19
COB9721
Simulated
11 / 19
Percentual (%)
Observation Order
12 / 19
Parameters
Significance of 5%
COB9721
13 / 19
Standardized Effects
COB9721
14 / 19
COB9721
15 / 19
Predicted Values
COB9721
16 / 19
Observed Values
determinate with classical correlations for external heat transfer coefficient with internal heat transfer coefficient obtained with the correlation of Chato (1930).
Parker e Treybal (1961) Mizushina et al. (1967)
Leidenfrost e Korenic (1982)
Niitsu et al. (1967) Dreyer e Erens (1990) 450 400 350 300
250 Acunha Jr. (2010)
They have been developed only for determining the heat transfer coefficient between the film of water (around the tubes) and the external air flow.
COB9721
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35
200
17 / 19
Experimental Sample
It is noted that mass flow of water spray is a factor of great influence in the global coefficient of heat transfer. This
comes to agree with literature, confirming that the PE model adopted is correct;
The condensation temperature of the refrigerant inside the condenser wasn't directly influential in the global
coefficient of heat transfer, being removed from the model;
The methodology of experimental design enable simulated complex experiments could be performed simply and
with good accuracy with a EMR of 3,69% and maximum error of 8,89%;
The effects of nonlinearity were not significant, demonstrating that relationships are essentially linear;
Since there were no replication of the experiments was not possible to estimate the pure error, i.e. the error related
only to uncertainty of measurement. Only the error of fitting of the model was possible to determinate.
18 / 19
COB9721
COB9721
COB9721
20 / Total