Comparison between Artificial Neural Network, Multi-variable Regression and Genetic Programming to Obtaining the Required Steel Ratio in Iranian Concrete Design Code

The designs in most countries should be inevitably carried out by their native codes such as Iran. Since the Iranian concrete code does not exist in structural design software, most engineers in this country analyze the structures using commercial software but design the structural members manually. This point, motivated us to make a communication between Iranian code and some other well-known ones by several anticipate methods to determine the best method and also creating facility for the engineers.In this paper, different concrete codes including America, New Zealand, Mexico, Italy, India, Canada, Hong Kong, Euro Code and Britain are compared with both Iranian concrete codes (the differences between these two is described in detail later) which codes of America, Canada, Italy and New Zealand is chosen for a more special comparison with The Iranian ninth issue of national regulation for reasons that will discuss about. Different anticipate methods are used for comparing the codes: Artificial Neural Network (ANN), Multi-variable regression and Genetic Programming (GP) and results show that ANN performes more exactly than the others.

کلیدواژه ها:

concrete design code ، anticipate method ، artificial neural network ، multi-variable regression ، genetic programming