This study explores the application of interpretable machine learning in the analysis of corrosion in offshore wind power equipment. By using atmospheric corrosion monitoring data and various environmental factors, linear regression, random forest, and gradient boosting regression models were employed to predict corrosion current. The results show that the random forest model performed the best in predicting corrosion current. Feature importance analysis, SHAP analysis, and partial dependence plot analysis revealed the key roles of humidity, rainfall, and temperature in the corrosion process. This study demonstrates the effectiveness of interpretable machine learning methods in understanding complex corrosion behaviors and their influencing factors, providing scientific evidence for corrosion monitoring and protection of wind power equipment.