Structural Multi-Damage Pattern Recognition Based on Data Fusion and Energy-Damage
JIAO Li1,2;LI Hong-nan2;ZHANG hai1,2;YI Ting-hua2
1. School of Civil Engineering, Shenyang Jianzhu University, Shenyang 110168,China;2. School of Civil and Hydraulic Engineering, Dalian University of Technology, Dalian 116024, China
Abstract:A structural multi-damage identification method is presented based on consensus data fusion, eigenvalue extraction by energy-damage and the powerful pattern recognition function of ART2. The method can make full use of more structural status information in different site and recognize structural damage better. The traditional consensus data fusion algorithm is improved. The improved algorithm can overcomes the shortcoming of the traditional consensus algorithm with two sensors, which has different confidence distance for different measuring precision. And the supporting matrix is fuzzified, which can avoid the subjective error in determining the threshold value. Eigenvector of multi-sensor measured data after fusion are constructed using eigenvalue extraction technology of energy-damage. ART2 network is adopted as the pattern recognition to identify structural multi-damage. The numerical simulation results of a five-layer frame structure show that this method can identify structural multi-damage and it is more robust, stable and adaptive.