Using artificial neural networks to predict interior velocity coefficients

A new method is presented for the evaluation of interior velocity coefficients using artificial neural networks. The interior velocity coefficient gives a measure of the relative strengths of interior air movements in the horizontal plane representing an occupied space. Air movements in a building depend not only on the external wind velocity, but also, and indeed principally, on a number of architectural parameters. However, if a meaningful number of such parameters are to be taken into account, the determination of interior velocity coefficients is very difficult. It was therefore decided to look at how artificial intelligence techniques might facilitate the solution of the problems involved. After presentation of the background of the study, an introduction to neural networks is given, with their main properties and methods of implementation. It is shown how these ideas are applied in the present study, and the initial results are presented. The utilization of neural networks as a universal predictor is an interesting subject for investigation, given their ability to provide reliable results in situations where a large number of parameters have to be taken into account simultaneously.