Application Of Fuzzy Neural Network To Assessment About The Concrete Bridge

The bridge is the hinge of the highway. The carrying and transitable capability of the bridge is the key to keep the line smoothly. With time going on, more and more bridges will reach or approach their design reference period and the structural damages will appear because of kinds of reasons. So the assessment and prediction of damage in bridges is a necessary part in bridge conservation, maintenance and technical reconstruction of today, which is also one of the most heated problems that are being discussed by scientists in engineering area and scholars at home and abroad, and along with the increment of old bridges, the problem attracts more attention.Because there are many and complex factors that affect assessment about the damage rating of concrete bridges and the connection among the factors is fuzzy. So assessment about the damage rating of concrete bridges is a typical question of indeterminacy. To reasonably assess concrete bridges, this paper introduces a kind of method that is applicable to assess concrete bridges. It is fuzzy neural network method (adaptive neuro-fuzzy inference system), which can deal with fuzzy information and automatically design and adjust rules and membership functions of fuzzy system. Thus it combines advantages of neural network and fuzzy logic. So this provides a new way of assessing the damage rating of concrete bridges. This article has mainly done following several aspects work:1. The connotation and character of the assessment of existing bridge is expounded. The status of research on assessment of existing bridge has been summarized and reviewed. Based on summarizing domestic and foreign results about the assessment of existing bridges, more research on the assessment of concrete bridge has been accomplished in this thesis. The paper indicates the actual problems of assessment of highway bridges in China and a new assessment model is established based on the "Code for Maintenance of Highway Bridges and Culvers".2. The paper has compiled training process of adaptive fuzzy neural network in MATLAB language and classified the data which come from the bridges in XiBao and Xi Tong highway and used them as two groups of different specimens. Average value of the two groups of accuracy of classification for bridges is used to estimate validity of the method. The results indicate that classification effect of the method is good and error is small. Fuzzy neural network method will be a potent method of classification for the damage rating of concrete bridges.3. BP neural network is used for reference method. Finally, the paper does some deeply comparison on the method of fuzzy neural network with the reference method. Then the study and analysis are put forward in the paper. Some examples proved that the method of fuzzy neural network is more practicable and efficient in the field of classification about the damage rating of concrete bridges, and it is worthy of making further research and promoting in future.