• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.5
• /
• pp.1061-1068
• /
• 2024

In this paper, anomaly detection methods for a collaborative robot during the chemical drum assembly process in the semiconductor industry are presented. The manual assembly of chemical drums has been automated using robots to prevent industrial accidents. However, the automation may increase downtime due to anomalies or failures in the robot manipulator tasks. To prevent this issue in advance, the methods to diagnose anomalous behaviors and conditions in the robotic automation workflow and subsequently resume tasks are proposed. To detect and diagnose anomalies in the tasks, the Random Forest classification method was utilized. Using this Random Forest classification, the collaborative robot anomaly detection model achieved an accuracy of 98.91%, successfully detecting all anomalies in the assembly process.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.4_1
• /
• pp.545-551
• /
• 2023

In this paper, a robot automation methodology for chemical drum assembly in semiconductor industries are presented. Robot automation is essential to resolve safety issues in which operators are directly or indirectly exposed to chemicals or fumes in assembling dispense heads on chemical drums. However, the chemical drum assembling process involves complex and difficult tasks, such as mating male/female keycodes and fastening screws with large-diameter, which may be very difficult to be performed by a single-arm robot with a commercial rigid F/T sensor. In order to solve the problems, a method for assembling a chemical drum using dual-arm collaborative robot system, compliance F/T sensor, robot vision and gripper is presented.

• Archives of Metallurgy and Materials
• /
• v.63 no.3
• /
• pp.1497-1502
• /
• 2018

Macroporous silica fibers having spherical cavities were fabricated by electrospinning using the spinning solution prepared from the mixed dispersion of tetraethylorthosilicate (TEOS) and polystyrene nanospheres as precursor and sacrificial templates, respectively, by injection through metallic nozzle. By applying electric field, the electro-spun fibers obtained by evaporation-driven self-assembly were collected on flat substrate or rotating drum, followed by the removal of the templates by calcination. The sound absorption coefficient of the porous fibers was measured by impedance tube, and the measured value was larger than 0.9 at high frequency region of incident waves. The surface of the resulting fibers was modified using fluorine-containing silane coupling agent to produce superhydrophobic fibrous materials to prevent the infiltration of humidity.