A Novel Tool (Single-Flute) Condition Monitoring Method for End Milling Process Based on Intelligent Processing of Milli
- PDF / 3,007,243 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 63 Downloads / 229 Views
International Journal of Precision Engineering and Manufacturing https://doi.org/10.1007/s12541-020-00388-8
REGULAR PAPER
A Novel Tool (Single‑Flute) Condition Monitoring Method for End Milling Process Based on Intelligent Processing of Milling Force Data by Machine Learning Algorithms Yinfei Yang1 · Bijun Hao1 · Xiuqing Hao1 · Liang Li1 · Ni Chen1 · Tao Xu1 · Khan M. Aqib1 · Ning He1 Received: 22 August 2018 / Revised: 6 July 2020 / Accepted: 16 July 2020 © Korean Society for Precision Engineering 2020
Abstract Tool condition monitoring is deemed as an essential technology of the intelligent manufacturing. Tool wear which directly affects the tool life makes a negative influence on the quality and dimensional accuracy of the machined surface, even leads to tool breakage, machine downtime, and other severe problems. Therefore, an available tool condition monitoring system is essential for the machining process to guarantee the processing quality and improve the machining efficiency. This paper proposes a new tool condition monitoring method based on the general judgment of cutting force. Milling force from a single-flute is predicted by deducing a theoretical formula based on un-deformed chip thickness. Based on the formula, cutting force samples used for machine learning paradigms are generated through time domain translation and Gaussian distribution. Nonlinear manifold learning methods are applied in the visualization of high dimensional data. Principal component analysis as a practical feature extraction method is used to reduce the large dimensionality of the sample set. The performance of respectively linear kernel, polynomial kernel, radial basis function and sigmoid kernel are self-compared to estimate the classification results via support vector machine. Experiments are carried out on an annealed Ti–6Al–4V alloy to measure the feasibility of this method. Keywords Cutting force simulation · Manifold learning · Polynomial kernel SVM · Principal component analysis (PCA) · Tool condition monitoring (TCM) List of Symbols h Un-deformed chip thickness fz Feed per tooth Φ Rotation angle Fc Main cutting force b Width of the un-deformed chip kc1.1 Specific cutting force for 1 mm2 chip cross section mc Increase in the kc curve ap Value of milling depth R Curvature radius
Yinfei Yang and Bijun Hao contributed equally to this work. * Liang Li [email protected] 1
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, Jiangsu, China
1 Introduction The modern manufacturing industry requires growing reliability from machine tools [1]. Conducting the machining process with a worn tool can increase the cutting force between tool and workpiece and the temperature in the cutting area, even produce tool vibrations, thus, directly causing undesirable downtime and scrapped components. Therefore, there is a growing demand for monitoring the tool wear state timely to improve machining efficiency and reduce production costs during the automatic man
Data Loading...
