Identyfikacja obciążenia powodującego uplastycznienie ramy z zastosowaniem bayesowskich sieci neuronowych

This paper presents the application of Bayesian Neural Networks (BNN) in the identification of parameters of a load causing partial yielding of a cross-section of a portal frame. As the source of the data in the identification procedure the eigenfrequencies and eigenvectors are used. The applied BNN are either of SSN/MAP (Maximum A Posteriori) or of T-BNN (True Bayesian Neural Networks) type, the results are compared with the results of the identification performed using Standard Neural Networks (SNN).