Structural Damage Identification Based On Artificial Fish Swarm Algorithm

After the bridge has been put into use,structural damage often occurs with the increase of service life.And the accumulation of damage development makes the bridge a big security risk.In recent years,bridges and housing accidents have occurred frequently,causing casualties and huge economic losses.The main reason is that the damage of the structure in service can not be found as early as possible with scientific and reasonable maintenance.Therefore,it has important practical significance for the damage identification of structure in service.This paper first expounds the damage identification method based on vibration experiment and the development of intelligent algorithm based on fish swarm.Then,the artificial fish swarm algorithm is improved by dual foraging strategy and fmincon nonlinear solution.The damage identification results of the improved algorithm are compared with those of the traditional fish swarm algorithm to verify the effectiveness of the improved algorithm.Then,through the vibration experiment to identify structural modal parameters,the results of finite element software are compared and studied.Finally,the improved artificial fish swarm algorithm is used to identify the damage under different damage conditions to verify the feasibility of fish swarm algorithm in damage identification and the actual structure.The main research work and conclusions are as follows:(1)The artificial fish swarm algorithm is improved.The dual foraging strategy and Fmincon nonlinear solution were improved respectively.Using standard Sphere function and a two span continuous beam Matlab simulation program,the algorithm test results show that the convergence speed and convergence precision of the improved fish swarm algorithm have been greatly improved.(2)The method of structural modal parameter identification based on vibration test is compared.Using three kinds of test methods for a 2.5m simply supported steel beam experiments to identify the frequencies and modes of the steel girders.The experimentalresults are compared with the results of Sap2000 simulation.By the experiment method of Multi-point vibration pickup with single point excitation and the accuracy of the data extracted PolyLSCF method is proved to be the highest,and lay a foundation for further accurate identification of damage identification data.(3)The comparative analysis of the artificial fish swarm algorithm and improved algorithm accuracy of damage identification.Vibration modes and frequencies of steel beam structures based on experimental identification.In contrast,artificial fish swarm algorithm and improved algorithm are used to identify the effectiveness and accuracy of structural damage.The recognition results and the theory results were compared.The comparison results show that fish swarm algorithm can identify damage accurately in the actual structural damage identification,and the improved artificial fish swarm algorithm can identify the damage more accurately,greatly improve the accuracy of damage detection.