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.

This content is only available via PDF.
You do not currently have access to this content.