Abstract
A method is proposed to estimate the joint damages of a steel structure from modal data using the neural networks technique. The beam-to-column connection in a steel frame structure is represented by a zero-length rotational spring of the end of the beam element, and the connection fixity factor is defined based on the rotational stiffness so that the factor may be in the range 0~1.0. Then, the severity of joint damage is defined as the reduction ratio of the connection fixity factor. Several advanced techniques are employed to develop the robust damage identification technique using neural networks. The concept of the substructural indentification is used for the localized damage assessment in the large structure. The noise-injection learning algorithm is used to reduce the effects of the noise in the modal data. The data perturbation scheme is also employed to assess the confidence in the estimated damages based on a few sets of actual measurement data. The feasibility of the proposed method is examined through a numerical simulation study on a 2-bay 10-story structure and an experimental study on a 2-story structure. It has been found that the joint damages can be reasonably estimated even for the case where the measured modal vectors are limited to a localized substructure and the data are severely corrupted with noise.
프레임 구조물의 접합부 손상을 평가하기 위하여 접합부 손상모델과 신경망기법을 이용한 손상평가기법을 제안하였다 구조물의 보-기둥 접합부를 접합부의 회전강성을 갖는 등가의 스프링요소로 표현하였으며 접합부의 손상도는 손상 전 후의 고정도계수의 감소비율로 정의하였다 손상평가를 위하여 다층퍼셉트론즈 신경망 기법을 제안하였으며 손상평가성능을 향상시키기 위하여 부분구조추정법, 노이즈첨가학습, 자료교란법등의 기법을 적용하였다 10층 프레임 구조물에 대한 수치 예제해석과 2층 프레임 구조물에 대한 실험 예제해석을 통하여 제안기법의 유용성을 평가하였다 계측지점이 일부분으로 제한되어 있고 계측자료에 심한 계측오차가 포함되어 있는 경우에도 손상평가가 합리적으로 이루어질수 있음을 알 수 있었다.
