Analytical Prediction of Steel Grid-Shell Stability and Dynamic
Behaviors Using Neural Networks -- Part 1
Abstract
Artificial Intelligence is a cutting-edge technology expanding very
quickly into every industry. It has made its way into structural
engineering and it has shown its benefits in predicting structural
performance as well as saving modelling and experimenting time. This
paper is the first one (out of three) of a broader research where
artificial intelligence was applied to the stability and dynamic
analyzes of steel grid-shells. In that study, three Artificial Neural
Networks (ANN) with 8 inputs were independently designed for the
prediction of a single target variable, namely: (i) the critical
buckling factor for uniform loading (i.e. over the entire roof), (ii)
the critical buckling factor for uniform loading over half of the roof,
and (iii) the fundamental frequency of the structure. This paper
addresses target variable (i). The ANN simulations were based on
1098-point datasets obtained via thorough finite element analyzes.
The proposed ANN for the prediction of the critical buckling factor in
steel grid-shells under uniform loading yields mean and maximum errors
of 1.1% and 16.3%, respectively, for all 1098 data points. Only in
10.6% of those examples (points), the prediction error exceeds 3%.