Data Fusion-Based Structural Damage Identification Approach Integrating Fractal and RCPN

In order to improve the identification accuracy of damage detection and evaluation based on vibration response, this paper presents a structural method fractal dimension, data fusion revised counter-propagation network (RCPN). Firstly, dimensions original signal response are extracted through preprocessing. Secondly, first-time (i.e., feature-level fusion) is carried out, after which these used as input for RCPN, identify decide initial damage. Finally, second-time decision results leading decision-level fusion. verify validity proposed method, four-storey benchmark structure ASCE comparison, using single RCPN respectively. The show that more accurate reliable than decision, has good noise resistance robustness.