Tool wear is a major contributor to machining errors of a workpiece. Tool wear prediction is an effective way to estimate the wear loss in precision machining. In this study, all kinds of machining conditions are treated as the input variables, the wear loss of the tool is treated as the output variable, and Projection Pursuit Regression (PPR) algorithm is proposed to mapping the tool wear loss. Finally, a real-time prediction device is presented based on the proposed PPR algorithm, and the prediction and measurement results are found to be in satisfied agreement with average error lower than 5%.