基于RBFNN钢桁架模型桥的损伤预警研究

Research on Radial Basis Function Neural Network Application in Steel Truss Girder Bridge Damage Alarming

损伤预警是结构损伤检测较为关键的一步,目的是判断结构是否发生损伤并发出警告信号.已有的损伤预警方法大多数采用BP网络,并且没有考虑测试噪声的影响.因此,提出采用一种混合算法的径向基神经网络(RBFNN)作为损伤预警系统,结果表明:RBFNN能显著判别损伤是否出现且预警效果要明显优于BP神经网络,更适合作为判断损伤是否出现的预警系统.

Damage alarm is an important step among structure damage identification. Its objective is to evaluate the structure health. The existing damage alarm methods are mostly based on BPNN without thinking over testing noise. Therefore, a new method based on hybrid algorithm RBFNN is proposed for structure damage alarm system in this paper. The experiment results of steel truss girder bridge show that the new method is better than BPNN for structural damage alarm.