Tool condition monitoring is one of the key issues in mechanical machining for efficient manufacturing of the parts in several industries. In this study, a tool condition monitoring system for milling was developed using a tri-axial accelerometer, a data acquisition, and signal processing module, and an alexnet as deep learning. Milling experiments were conducted on an aluminum 6061 workpiece. A three-axis accelerometer was installed on a spindle to collect vibration signals in three directions during milling. The image using time-domain, CWT, STFT represented the change in tool wear of X, Y axis directions. Alexnet was modified to learn images of the two directional vibration signals, to predict the tool condition. From an analysis of the results of learning based on the experimental data, the performance of the monitoring system could be significantly improved by the suitable selection of the data image method.

The mechanical drilling of micro holes is considered a difficult endeavor, due to the high hardness and brittleness of alumina plates found during the drilling process. In this work, an alumina plate with a 4mm thickness is drilled with the use of a continuous-wave Nd:YAG fiber laser. As can be seen, there is minimum required power density to ablate the alumina plate. As shown in this study, the hole diameter and straightness are not constant with the hole depth recorded, which is presumably due to the recondensation of vaporized alumina, and the characteristics of irregular laser radiation. The oxygen pressure, power density, focal position, and laser on time (duration) are chosen as the control parameters. To understand the influence of control parameters, the orthogonal arrays table in Taguchi method is applied, and the micro holes are evaluated based on the use of geometrical factors. Through the review of a sensitivity and interaction analysis, the appropriate duration and oxygen pressure are identified as the major parameters governing the geometrical quality of drilled holes in this study.