In order to estimate the remaining safe service life of the pipeline, the extreme gradient boosting algorithm model besed on grey correlating analysis was proposed. Grey Relational Analysis (GRA) was used to calculate and rank the correlation values between each influencing factor and the remaining life, and the data of the influencing factors with high correlation were preferably input into the eXtreme Gradient Boosting (XGBoost) algorithm for the prediction of the remaining life of corroded pipelines. Taking an oilfield water injection pipeline as an example, the results showed that the Root Mean Square Error (RMSE) was 0.012, the Mean Absolute Error (MAE) was 0.068, and the goodness of fit (R2) was 0.999, compared with the other three prediction models, the results showed that the prediction accuracy and generalization performance of the model constructed in this paper were better.