Application of BP Artificial Neural Network in Structure Damage Identification

摘要：

The application of the neural network in the structure damage identification is studied using a combination of theoretical and experimental methods. A multilayer neural network models based on the BP algorithm is designed for the damage identification of existing model structure. The model is trained with the data from an engineering beam to filter different transfer function, train function and the unit number of hidden layer by contrast to determine the best network model for detect damage. At last, the model is used to detect the damage of cable-stayed bridge with an improved method of Data pre-processing using the square rate of change in Frequency as input date of network. The satisfied test result shows that the model is effective to reflect the injury status of the existing structure.

关键词： Artificial neural network BP algorithm Data preprocessing Damage identification

作者: Chen Xiang-jun Gao Zhan-feng Wang Wei

作者单位: Shijiazhuang Railway Institute, Shijiazhuang, Hebei, 050043, China

会议类型: 国际会议

会议名称: 2010 International Conference on Intelligent Computation Technology and Automation(2010 智能计算技术与自动化国际会议 ICICTA 2010)

会议地点: 长沙

会议语种:英文

页码: 733-737

在线出版日期: 2010-05-11（万方平台首次上网日期，不代表论文的发表时间）