Abstract
Aiming to monitor wear condition of milling cutters in time and provide tool change decisions to ensure manufacturing safety and product quality, a tool wear monitoring model based on Bagging-Gradient Boosting Decision Tree (Bagging-GBDT) is proposed. In order to avoid incomplete tool state information contained in a single domain feature parameter, a multi-domain combination method is used to extract candidate characteristic parameter sets from time domain, frequency domain, and time–frequency domain. Then top 21 significant features are screened by eXtreme Gradient Boosting selection method. Synthetic Minority Oversampling Technique technology is integrated during feature selection to overly sample feature vectors, so that wear condition categories can be well balanced. Bagging idea is then introduced for parallel calculation of the gradient boosting decision tree and to improve its generalization ability. A Bagging-GBDT milling cutter wear condition prediction model is constructed and verified by public ball-end milling data set. Experiments show that random features and training samples selection can effectively improve prediction performance and generalization ability of prediction model. Our Bagging-GBDT model gains F1 score of 0.99350, which is 0.2% and 13.2% higher than the random forest algorithm and basic GBDT model, respectively.
Highlights
High-speed milling technology is an important branch of advanced manufacturing industry
In order to improve generalization ability and computing efficiency of basic Gradient Boosting Decision Tree (GBDT), we introduce the Bagging idea to form one Bagging-GBDT milling cutter wear prediction model
In order to improve generalization performance of GBDT model, a Bagging algorithm is introduced for milling cutter wear condition prediction
Summary
High-speed milling technology is an important branch of advanced manufacturing industry. With the development of new-generation information technologies such as sensors and artificial intelligence, realization of intelligent monitoring of tool wear has become one of research hotspots [1,2,3]. In Yu [4], prognostic features are selected with a penalization method, and prediction model formed via manifold regularization. Liu [5] proposes a novel unsupervised CNN-transformer neural network (CTNN) model for wear estimation. The transformer model and convolutional neural networks (CNN) are parallely used to process condition monitoring (CM) data. Zhang [6] establishes a Least Square Support Vector Machine (LS-SVM) based wear model, which manifests that the LS-SVM model is capable of tool wear prediction at specified cutting conditions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
