The extreme value theory was used to analyze the statistical characteristics of maximum forced response of the mistuned bladed disks

and applied to a compressor disk. The mistuning bladed disk was reduced and modeled. The Monte Carlo method was used to simulate the response calculation

and the distribution characteristics for the amplification factor of the maximum response under different engine order excitations were studied. The extreme value theory was used to model the maximum response distribution

and the maximum likelihood estimation method was introduced to get the unknown parameters. The K-S(Kolmogorov-Smirnov) test was employed to test the goodness of fit of different distribution functions. The statistical characteristics of the response of a compressor disk were analyzed. The fitting results of seven kinds of distribution functions for the amplification factor of the maximum response were compared. Results showed that the fitting effects of the extreme value distribution

two-parameter Weibull distribution

normal distribution

lognormal distribution and Gamma distribution were all poor; the fitting effect of the commonly used three-parameter Weibull distribution was not as good as that of the generalized extreme value distribution. Therefore

the generalized extreme value distribution can more accurately describe the statistical characteristics of the dynamic response of mistuned bladed disks.