The application of artificial neural networks in the identification of damage in beams – numerical and experimental studies

Artur Borowiec,

Leonard Ziemiański

Abstrakt

This paper presents the application of Artificial Neural Networks (ANN) in the identification of damage (location, extent) in simple laboratory beam structure. The assessment of the state of a beams relies on the comparison of the structure eigenfrequencies obtained from the systems with additional masses placed in different nodes without knowledge of the natural frequencies of undamaged structures.

Słowa kluczowe: artificial neural networks, damage identification, modal analysis