Research On Bridge Damage Detection Based On Particle Swarm Optimization Support Vector Machine

Due to the frequent bearing,overload,collision or severe cold,strong wind,flood and other adverse environment during the service period of the bridge,it is easy to cause damage and local damage of the bridge structure.Timely health detection and accurate damage identification are the key to ensure the safe operation of the bridge,and it is also an important lesson that many engineering and technical personnel at home and abroad urgently need to solve.In this paper,the research status of damage vector,damage identification method based on particle swarm optimization and its application to bridge structure are summarized This paper makes a systematic exposition.The learning ability and generalization ability of support vector machine are closely related to the selection of its own parameters.Blind selection among many parameters will cost a lot of time,and the results are not necessarily optimal.Therefore,this paper uses particle swarm optimization algorithm to optimize the model parameters of support vector machine.Particle swarm optimization algorithm has the advantages of simple operation and relatively high search efficiency.In addition,the particle swarm optimization algorithm does not require the continuous differentiability of the optimization function,and can deal with multivariable and nonlinear model problems.In this method,the particle swarm optimization algorithm is used to optimize the parameters of support vector machine,and the optimized model is used to complete the classification and prediction work.In the bridge damage location identification,the normalized curvature modal difference is used as the feature vector to input into the support vector machine for training through the comparison and trade-off of each damage fingerprint.Through literature research and corresponding trial calculation,it is known that RBF kernel function has higher accuracy than linear kernel function and polynomial kernel function sigmoid,so it is used as kernel function of support vector machine in this simulation.Then,the support vector machine is optimized by particle swarm optimization algorithm,and the optimal parameters are obtained.In this paper,luoqingjiang bridge is taken as an example to determine the location of the damage.The results show that the correct rate of the identification is 96.32%,and the judgment effect of the damage location is good.On the basis of bridge damage location identification,the curvature modal difference at the damage location is normalized and input into the optimized support vector machine,and its regression algorithm is used to identify the damage degree of the position.By comparing the simulation results before and after optimization,it is proved that the SVM optimized by PSO has higher accuracy At the same time,it has better generalization ability.