Use of Neural Networks as a Method of Correlating Thermal Fluid Data to Provide Useful Information on Thermal Systems

摘要

A study on the use of neural networks as a method of correlating thermal fluid data to provide useful information on thermal systems was conducted using a neural network code package. Two separate thermal fluid systems were analyzed: tube bank data with variable geometries and tube bank boiling data with variable parameters. Both studies show the effectiveness of neural networks as a viable alternative to the current practice of correlating data. This is achieved by displaying a reduction in error, requiring fewer assumptions, and providing an easier method of devising predictions and correlations.