Research On Bridge Damage Identification Method Based On Neural Networks And Vibration Modal Analysis Technique

With the rapid development of communication industry in our country, density of highways network improves constantly and the large span bridge is emerging constantly. But structural damages such as cracking and aging etc. to some degree during the bridge structures'service life occur from time to time. Some invisible damages do not alert the engineers in time and may result in disastrous consequences and ultimately cause substantial loss of life and property. Therefore, it is important to command the health status of bridge in commonly using state in time and to detect damages at the earliest possible stage.On the basis of collection and analysis of the data about bridge structural health monitoring system ,structural damage identification and artificial neural networks, vibration modal analysis theory is integrated with BP neural networks so as to detect bridge damage with the help of ANSYS and a program written with VB. The result shows the method works well.Firstly, several damage identification methods used to identify the bridge structural damage theory are discussed and analyzed. Various theoretical methods, formula and use are introduced mainly from the static, dynamic recognition, and artificial intelligence .Secondly, the basic theory of BP neural networks is discussed and the basic tenets of damage identification using BP neural networks are analyzed. A new visual program is compiled with VB software. And one simple supported rectangle steel beam model is presented as calculated example for the above-mentioned method application.Thirdly, the damage identification method based on curvature modal shape and flexibility curvature are discussed in this paper. The relationship between structural damage and modal changes is expounded and a three-span continuous beam mode is used to study on the damage identification method based on vibration modal theory .Both single and multiple damage identification are studied.Finally, on the background of the project of Lujing Road Overpass Bridge in Guangzhou ,the technique based on curvature modal shape analysis theory and BP neural networks is used to identify the damaged position and extent likely occurring. The result shows the effectiveness of this method used in bridge structures.The result indicates that the method based on BP neural networks and vibration modal analysis theory can detect not only the damage position but the damage degree of concrete bridges. The method will have good application perspective. It is important to forecast the health status of bridge structures.