Online tool wear prediction based on partial least square regression and Monte Carlo cross validation

摘要

Tool wear prediction is paramount for guaranteeing the quality of the workpiece and improving lifetime of the cutter. However, the multicollinearity between the extracted features deteriorates the prediction accuracy. To overcome this, a partial least square regression-based method is proposed. The main characteristic of partial least square regression is that the regression analysis is realized in the principle component space so that multicollinearity between the input variables can be avoided. To testify the correctness of the proposed method, the milling experiment is preceded and the dynamic cutting force is collected to depict the variation of the tool wear. Moreover, Monte Carlo cross validation is adopted to improve the robustness of partial least square regression. The analysis and comparison between the partial least square regression model and the multiple linear regression model shows that the presented method can get more accurate results.