Study On Method Of Detecting Transverse Connection Damage Of Fabricated Bridges

Most of fabricated bridges are simple-supported beam bridges,belonging to determinate structures.The fabricated beam bridges were widely used among the medium-small span bridges in vast areas of our country because they are little influenced by geological conditions and convenient for construction,have simple structure and clear force-transmission route.With the high-speed development of national economy in recent years,the level of traffic load has been raised constantly.So the load-bearing capacity of fabricated bridges,which were constructed early,cannot meet the growing demand of modern transportation.Some of fabricated bridges in service have shown different kinds of damage with different levels at present.One of the most common diseases is transverse connection damage.However,a systematic and ideal program of identifying the damage of fabricated bridge transverse connection has not been formed.Therefore,the research to identify the damage of fabricated bridge transverse connection has great theoretical significance and important engineering application value.The engineering background of this paper is the Diaoshuiyan Bridge,which is a typical fabricated bridge.At first,transverse distribution characteristics of the structural responses(deflection,stress,bending moment,shear force)caused by lateral distribution of vehicle loads were investigated.Considering the need for real-time monitoring parameters in practical engineering application,the coefficient of transverse distribution of stress was chosen to be the input parameter of the BP neural network.The relationship between transverse connection damage and the coefficient of transverse distribution of stress was acquired through simulating transverse connection damage of different location,different quantity,different level in different load combinations based on the revised structure finite element model of Diaoshuiyan Bridge.The representative sample data was also obtained.A damage detection method of transverse connection of fabricated bridges based on the genetic optimization of neural networks was presented,using the relationship between the transverse connection damage and the coefficient of transverse distribution of stress.The input parameter of the genetic optimization of the neural network is coefficient of transverse distribution of the stress,meanwhile,the output parameter is the damage degree and location.This method employs the genetic algorithm to optimize the weight and threshold of the BP neural network.The combination of the BP neural network and genetic algorithm,which is aimed at overcoming the shortcomings of BP neural network,will considerably improve the success rate of damage detection.The BP neural network trained by the sample data obtained from finite element model of Diaoshuiyan Bridge can precisely identify the location of the damage and the damage degree of transverse connection,proving that the presented method can be used in damage detection of fabricated bridges practically.At last,the damage detection method of transverse connection of fabricated bridge was used in real-time health monitoring system of the Diaoshuiyan bridge based on measured coefficients of transverse distribution of stress.First of all,the feasibility of presented method was verified by a static load test.Comparison between the stress data obtained from the static load test and the stress data from the finite element model verified the reliability of the data measured by the fiber Bragg grating strain sensors.Then the damage detection result of the method of GA-BP neural network was compared with the measured displacement data to verify the feasibility of presented method of GA-BP neural network.Finally,the combination of the presented method and the advanced fiber Bragg grating sensing technology and the IOT technology was proved to be effective and reliable when the health monitoring system was running for a period of time.The result shows that presented method can give some valuable suggestions for the management and maintenance of the fabricated bridges.