An approximate integral model with an artificial neural network for heat exchangers

Abstract It is now known the generally it can be demonstrated that artificial neural network (ANN), particularly the fully-connected feedforward configuration with backward propagation error-correction routine, can be a rather effective and accurate tool to correlate performance data of thermal devices such as heat exchangers (Sen and Yang, 2000; Kalogirou, 1999). Good examples are the recent demonstrations for the compact fin-tube heat exchangers (Diaz et al., 1999a; Yang et al., 2000; Pacheco-Vega et al., 1999) including those with complex geometries and also two-phase evaporators (Pacheco-Vega et al., 2000) as well as the dynamic modeling of such heat exchangers and their adaptive control (Diaz et al., 1999b; Diaz et al., 2000). Unfortunately, despite such successes, there are still implementation issues of the ANN analysis which lead to uncertainties in its applications and the achieved results. The present paper discusses such issues and the current practices in dealing with them. Those that will be discussed include the number of hidden layers, the number of nodes in each hidden layer, the range within which the input-output data are normalized, the initial assignment of weights and biases, the selection of training data sets, and the training rate. As will be shown, the specific choices are by no means trivial, and yet are rather important in achieving good ANN results in any given application. Since there are no general sound theoretical basis for such choices at the present time, past experience and numerical experimentation are often the best guides. However, many of these choices and issues relating to them involve optimization. As a result. Some of the existing optimization algorithms may prove to be useful and highly desirable in this regard. The current on-going research to provide some rational basis in these issues will also be discussed. Finally, it will also be mentioned that successfully implemented ANNs have many additional uses in practice. Examples include parameter sensitivity analysis, training, design of new experiments, and clustering of data sets.

Download Full-text

Optimal Design of Compact Heat Exchangers by an Artificial Neural Network Method

Heat Transfer: Volume 1 ◽

10.1115/ht2003-47141 ◽

2003 ◽

Cited By ~ 4

Author(s):

Rongguang Jia ◽

Bengt Sunde´n

Keyword(s):

Neural Network ◽

Heat Transfer ◽

Artificial Neural Network ◽

Optimal Design ◽

Heat Exchangers ◽

Measurement Errors ◽

Data Sets ◽

Process Data ◽

Compact Heat Exchangers ◽

Artificial Neural

The artificial neural network (ANN) methods are introduced (mainly for calculation of thermal and hydraulic coefficients) into a computer-aided design code of compact heat exchangers (CCHE). CCHE integrates the optimization, database, and process drawing into a software package. In the code, a strategy is developed for the optimization of compact heat exchangers (CHEs), which is a problem with changeable objective functions and constraints. However, the applicability and/or accuracy of all these methods are limited by the availability of reliable data sets of the heat transfer coefficients (j or Nu) and friction factors (f ) for different finned geometries. In fact, due to expenses and difficulties in experiments, only a limited number of experiments has been carried out for some kinds of heat transfer surfaces. The information, therefore, is usually given by means of correlations. It is well known, however, that the errors in the predicted results by means of correlations are much larger than the measurement errors, being mainly due to the data reduction represented by them. This implies doubts on the optimal solutions. Fortunately, a well-trained network is capable of correlating the data with errors of the same order as the uncertainty of the measurements. This is the main reason for the present introduction of the ANN method to correlate the discrete experimental data sets into continuous formulas. In this study, the ANN method is used to formulate the complex relationship between the thermal and hydraulic coefficients and the other parameters, including the geometry and process data. A specific case on the optimal analysis of a plate-fin heat exchanger (PFH) is presented to show how the trained ANNs can be used for optimal design of heat exchangers. In addition, a case is presented to illustrate how an inverse heat transfer problem is solved by the optimization methodology developed in the present code.

Download Full-text

Prediction of two-phase flow distribution in microchannel heat exchangers using artificial neural network

International Journal of Refrigeration ◽

10.1016/j.ijrefrig.2019.11.028 ◽

2020 ◽

Vol 111 ◽

pp. 53-62 ◽

Cited By ~ 8

Author(s):

Niccolo Giannetti ◽

Mark Anthony Redo ◽

Sholahudin ◽

Jongsoo Jeong ◽

Seiichi Yamaguchi ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Heat Exchangers ◽

Two Phase Flow ◽

Flow Distribution ◽

Phase Flow ◽

Two Phase ◽

Artificial Neural

Download Full-text

Autofluorescence spectroscopy of oral leukoplakia using an artificial neural network

Clinical Otolaryngology ◽

10.1046/j.1365-2273.2000.00358-12.x ◽

2000 ◽

Vol 25 (4) ◽

pp. 325-325

Author(s):

J.L.N. Roodenburg ◽

H.J. Van Staveren ◽

N.L.P. Van Veen ◽

O.C. Speelman ◽

J.M. Nauta ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Oral Leukoplakia ◽

Autofluorescence Spectroscopy ◽

Artificial Neural

Download Full-text

1902: Is Steinstrasse After ESWL of Renal Stones Predictable? Artificial Neural Network Analysis

The Journal of Urology ◽

10.1016/s0022-5347(18)39094-3 ◽

2004 ◽

Vol 171 (4S) ◽

pp. 502-503

Author(s):

Mohamed A. Gomha ◽

Khaled Z. Sheir ◽

Saeed Showky ◽

Khaled Madbouly ◽

Emad Elsobky ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Network Analysis ◽

Renal Stones ◽

Neural Network Analysis ◽

Artificial Neural Network Analysis ◽

Artificial Neural

Download Full-text