The forecast of typhoon intensity, especially the rapid intensification (RI) forecast, is still a very challenging problem in current typhoon forecasting. This article is based on the XGBoost model, using NCEP GFS analysis and forecast data from 2015 to 2020, as well as IBTrACS data, to construct RI forecast models (FM) and forecast correction models (FCM) for typhoons in the northwest Pacific for the next 24 hours. Through predictor contribution analysis of the FM model, it was found that the five factors that have the greatest impact on model forecasting are typhoon abundance, average temperature at 200hPa, intensity changes over the past 6 hours, potential intensity, and average divergence at 200hPa. The model was independently tested using data from 2021 to 2022, and the results showed that the FM model had high accuracy when tested using analytical data, with FNR, FPR, and TS of 0.25, 0.24, and 0.32, respectively. However, due to the influence of forecast errors caused by forecast factors, the performance of FM models in real-time forecasting decreases. FCM models constructed using forecast data can effectively correct forecast errors by learning them, thereby reducing the impact of forecast errors. The FNR, FPR, and TS of the FCM model in real-time forecasting tests were 0.28, 0.25, and 0.30, respectively. Compared with the FM model (FNR, FPR, and TS were 0.32, 0.26, and 0.27, respectively), the FNR and FPR decreased by 0.04 and 0.01, and the TS increased by 0.03. The FCM model is convenient and easy to use, providing reference for real-time forecasting of typhoon intensity and typhoon RI.