No abstract

No abstract

This study aims to conduct abnormality detection by applying machine learning algorithms when drilling a carbon fiber reinforced plastic laminate. In-process signals including current, thrust force, and vibration were captured during the dry drilling experiments using a 6 mm physical vapor deposit diamond-coated drill at the consistent spindle speed of 6500 RPM and 0.05 mm/rev. Across measurements from out-of-process variables, including hole diameter, roundness, surface roughness, entry/exit delamination, and entry/exit uncut fiber area, in-process measurements were most able to find outliers with respect to diameter. Both Principal Component Analysis, an unsupervised dimensionality reduction technique, and Linear Discriminant Analysis, a supervised dimensionality reduction technique, could separate oversize or undersize holes from average-sized holes when using fast Fourier transformation data of in-process vibration. Predictive performance with k-Nearest Neighbors shows that our machine learning pipeline can predict oversized vs. non-oversized holes with over 85% accuracy in this dataset. Peak prediction performance is obtained when in-process measurement data is viewed from the frequency domain, and predictions are weighted based on the relative distances of the nearest neighbors.

No abstract

The material used is a commercial magnesium based alloy AZ31(Mg-3Al-1Zn) sheet with a thickness of 0.8 mm. Friction tests at various temperatures(R.T. to 200℃) and at various holding forces in the 4 type molds were carried out to investigate the coefficient of friction. A warm drawing process with a local heating and cooling technique was developed in the Mg alloy sheet forming to improve formability because it is very difficult for Mg alloy to deform at room temperature by the conventional method. So, the coefficient of friction at various mold surface treatment conditions in this study was needed to develop the Mg alloy sheet forming technology.