Although the grey forecasting model has been successfully adopted in various fields and has been demonstrated prospected aspect. The paper makes the original data multiply the time interval to get the accumulated sequence and uses the difference quotient method to establish the unequal interval GM(1,1) model. In order to reduce the error the paper adopts the weighted coefficient to revise the background values. By fitting and predicting the fatigue strength data it proves the method in the paper is effective which improves the accuracy of the model. It provides an effective way for the grey system application.