Abstract:

Aiming at the problem of structural damage identification, we proposed an intelligent algorithm for structural damage identification based on multiobjective optimization strategy. The algorithm used the extreme learning machine as the damage parameter index, and established the nonlinear function expression between damage parameters and every frequency. We first had the structure of the actual structural frequency  minus the function expression, and then took the formation of each expression as a optimization objective to obtain a highdimension multiobjective optimization model based on structural damage identification. In order to improve the solution accuracy of the model, we proposed a grey multi particle swarm coevolutionary algorithm for multi-objective optimization. The experimental results show that these methods can deal with the problem of structural damage identification.

Key words: multi-objective optimization, extreme learning machine, grey multi particle swarms co-evolutionary, structural damage identification