In this paper, we propose a method to generate the trajectory of a robotic shoe sole spray system by extracting target points from a 3-D model of a mold sole. Point cloud transformation based on the mold 3-D file format, Z-Axis uppermost point extraction, elimination of unnecessary points, and final target point selection are sequentially performed. The Catmull- Rom algorithm is then applied to plan spline trajectory that allows the robot end effector to spray at a constant speed by following the extracted target points. The proposed algorithm is validated on the test bed of a shoe sole spray system. Through the proposed method, the adhesive can be uniformly dispensed to the sole of the shoe in an atypical shape without the process of extracting the work point using the vision system.

A smart factory with Big Data analytics is getting attention because of its ability to automate and make the manufacturing environment more intelligent. At the same time, higher reliability is required with a drastic increase in complexity and uncertainty within the current system of manufacturing fields. The pump is considered as one of the most crucial equipment as it can affect the overall manufacturing performance of the manufacturing processes and it needs to be timely diagnosed of its mechanical condition as a top priority. In this research, we propose an operation system of centrifugal pumps and a data-driven fault diagnostic model that is developed by collecting relevant multivariate data from several natures. Proposed machine learning models can be used for detecting and diagnosing pump faults via analytical processes containing signal preprocessing and feature engineering procedures. Simulation and case studies from rotating machinery have demonstrated the effectiveness of the proposed analytical framework not only for attaining quantitative reliability but practical usages in actual manufacturing fields as well.