Bridge structure parameter correction model establishment and prediction method based on time domain data

The invention discloses a method for establishing and predicting a bridge structure parameter correction model based on time domain data. The method comprises the following steps: selecting at least one type of to-be-corrected parameters of a bridge structure; taking each type of to-be-corrected parameters as a training sample; obtaining a measuring point acceleration time history data series corresponding to each type of to-be-corrected parameters at each measuring point position, and taking the series as a sampling point; a measuring point acceleration time history data system is compressed and converted into an accumulated strength value, and data are input, so that a training sample set is constructed; establishing a blind Kriging model, inputting the training sample set into the blind Kriging model, determining important variables by adopting a Bayesian variable selection algorithm, carrying out iteration from 0 by setting a parameter k in the blind Kriging model, finally finding out an optimal value of