Abstract
Recently, a variety of intelligent structural damage identification algorithms have been developed and have obtained considerable attention worldwide due to the advantages of reliable analysis and high efficiency. However, the performances of existing intelligent damage identification methods are heavily dependent on the extracted signatures from raw signals. This will lead to the intelligent damage identification method becoming the optimal solution for actual application. Furthermore, the feature extraction and neural network training are time-consuming tasks, which affect the real-time performance in identification results directly. To address these problems, this paper proposes a new intelligent data fusion system for damage detection, combining the probabilistic neural network (PNN), data fusion technology with correlation fractal dimension (CFD). The intelligent system consists of three modules (models): the eigen-level fusion model, the decision-level fusion model and a PNN classifier model. The highlight points of this system are these three intelligent models specialized in certain situations. The eigen-level model is specialized in the case of measured data with enormous samples and uncertainties, and for the case of confidence level of each sensor is determined ahead, the decision-level model is the best choice. The single PNN model is considered only when the data collected is somehow limited, or few sensors have been installed. Numerical simulations of a two-span concrete-filled steel tubular arch bridge in service and a seven-storey steel frame in laboratory were used to validate the hybrid system by identifying both single- and multi-damage patterns. The results show that the hybrid data-fusion system has excellent performance of damage identification, and also has superior capability of anti-noise and robustness.
Highlights
Structural damage identification is an essential approach to prevent a sudden collapse of structures and avoid casualties and heavy economic losses [1,2,3]
In order to make full use of the massive nonlinear characteristic data and integrate FD, this paper focuses on the integration of correlation fractal dimension and probabilistic neural network (PNN) with the data fusion technique to detect structural damage, presenting a novel hybrid damage detection system which contains three intelligent models and is exactly powerful for largescale and complex structures
Since feature-level data fusion fully considers the importance of individual features and multi-sensor mutual information features, it is convinced beyond doubt that the eigen-level damage detection model can obtain more Fiagcucruer2a.teSiindgelentPiNficNatciloanssrifeiesur mltsodtheal nfoar ndyaminadgeivdidetuecatliofenature can
Summary
Structural damage identification is an essential approach to prevent a sudden collapse of structures and avoid casualties and heavy economic losses [1,2,3]. Since neural network (NN) possess powerful abilities, such as nonlinear processing, self-organizing, self-learning and self-adaption, it had obtained good results in the structural damage detection by integrating NN with fractal theory [17,18,19,20] Most of these existing studies focused on the application of FD in extracting features, fault diagnosis and damage identification. It is still a concerning issue how to make full use of the large volume of nonlinear characteristic data and integrate FD for damage detection and state assessment [17,18,19]. The filtering and averaging method were used for data preprocessing
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
