Bagging-gradient boosting decision tree based milling cutter wear status prediction modelling

Abstract

Article Highlights Candidate parameter sets are extracted from multi-domain (time, frequency, and time–frequency). Topmost significant features are screened by XGBoost selection, and balanced via SMOTE technology. Bagging idea is introduced for parallel calculation of the gradient boosting decision tree and to improve generalization ability of the prediction model.

Keywords

• Wear condition prediction
• XGBoost feature selection
• SMOTE
• Bagging-GBDT