运用BP-AdaBoost模型识别随机车载作用下大跨斜拉桥拉索损伤

为了有效地进行大跨结构的损伤识别,提出随机车载作用下利用BP-AdaBoost(Back Propagation neural network,Adaptive Boosting)模型对大跨斜拉桥拉索进行损伤识别的方法。该方法首先依据交通调查数据,建立随机交通荷载模型,再运用提升框架,对结构损伤前后的振动测试信号进行提升小波包分解,将小波包信号分量能量累积变异值作为特征值,识别斜拉索损伤位置,然后以此建立BP-AdaBoost模型,利用AdaBoost算法和BP神经网络相结合的方法对大跨斜拉桥拉索的损伤程度进行识别,并研究噪声对该算法的影响。数值分析结果表明,该方法有较强的抗噪声干扰能力,在随机车载作用下,运用BP-AdaBoost模型能够有效识别大跨斜拉桥拉索损伤。

Damage Identification of Cables of Long-span Cable-stayed Bridges Using BP-AdaBoost Model under Random Vehicle Load

The cable damage identification method of long-span cable-stayed bridge is proposed using BP-AdaBoost model under random vehicle load in this paper. Firstly,the random traffic load model is established according to the traffic survey data,?and the vibration signal is decomposed using lifting wavelet packet (WP) analysis based on lifting scheme, then the corresponding characteristic vector is established by the energy accumulating variation value of the lifting WP component energy, which can be used to identify damage location of cable of cable-stayed bridge.Finally, the BP-AdaBoost (Back Propagation neural network, the Adaptive Boosting) model is established, combining AdaBoost algorithm and BP neural network to identify the damage degree of the cable of long-span cable-stayed bridge,and the effect of noise on the algorithm is also studied.The numerical results show that the proposed method can be effectively used to identify the cable damage of long-span cable-stayed bridge under random vehicle load.