Machine Learning for Tool Wear Classification in Milling Based on Force and Current Sensors

2019 4th International Conference on Mechanical, Manufacturing, Modeling and Mechatronics;2019 4th International Conference on Design Engineering and Science

工业技术（总论）;机械制造

Schwenzer, M.^1 ; Miura, K.^1 ; Bergs, T.^1

Laboratory for Machine Tools and Production Engineering (WZL), RWTH Aachen University, Campus-Boulevard 30, Aachen

52074, Germany^1

关键词: Current sensors;    Current signal;    Flank wear;    Orthogonal cutting;    Random forests;    Tool coordinate system;    Validation data;    Wear state;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/520/1/012009/pdf
DOI  :  10.1088/1757-899X/520/1/012009

学科分类：工业工程学

来源: IOP

【 摘 要 】

This paper presents how to classify the wear state of an end-mill based on force and current signals of the linear axes. The data is divided in binary classes based on the maximum flank wear. A support vector machine and a random forest are trained on orthogonal cutting experiments, but the validation is performed on arbitrary tool paths. To achieve this unique level of generality the signals are transformed into the rotation tool coordinate system. The features are extracted over five cutter revolutions. Support vector machines outperform random forests achieving 99,8% and 97% accuracy in the two classes on the test data and 98% and 61% accuracy on the validation data.