http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Nguyen, Cong Hong Phong,Choi, Young Elsevier 2018 AUTOMATION IN CONSTRUCTION - Vol.91 No.-
<P><B>Abstract</B></P> <P>Inspection is vital in industrial plant construction and management. However, traditional inspection methods that rely on human involvement and paper documentation are becoming untenable as modern industrial plants are becoming larger and more complex than legacy facilities. Hence, an efficient and robust method is required to support the inspection of modern industrial plants. In this paper, an improved technique relying on terrestrial laser scanning (TLS) for data acquisition and normal-based region growing and efficient random sample consensus (RANSAC) for point cloud data processing is proposed for the on-site dimensional inspection of the piping systems of an industrial plant. Consequently, the as-built condition of the plant is assessed via a distance-based deviation analysis and a comparison of geometric parameters between the as-designed and as-built models. The method is validated using a dataset acquired from a compartment of a ship has verified the robustness and reliability of the proposed approach.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Point cloud data and 3D CAD data comparison for on-site dimensional inspection. </LI> <LI> Normal-based region growing and efficient RANSAC for point cloud processing. </LI> <LI> As-built dimensional condition verification with distance-based deviation analysis and geometric parameter comparison. </LI> </UL> </P>
Daisuke Iba,Hiroki Inoue,Hidekatsu Noda,김명수,Ichiro Moriwaki 대한기계학회 2019 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.33 No.12
The purpose of this study was to try to clarify relative relationships among deviations on each tooth of gears by using the graph theory. Our previous study proposed a method to derive correlation coefficients among the tooth helix deviations and applied it to a ground helical gear. In addition, the coefficients were used as edges, and a network image of the relative helix deviations was generated. In this paper, this method was applied to the analysis of super-finished helical gears, and the phase relationship among the helix deviations was derived. Furthermore, this paper proposed a method, which enables us to derive the magnitude of helix deviation as a norm of signal, which disappeared from the phase network. Then, the derived magnitude was added to the network as the intensity of the vertices. As a result of the application of the proposed method to an analysis of the ground and super-finished helical gears, it was found that the newly created network images were able to show the different characteristics between the gear-finishing processes.
CNN 기반의 상자 표면 편차 이미지 분석을 통한 상자 포장공정에서의 실시간 진공 그리퍼 파지 작업 모니터링
백수정(Sujeong Baek),전승호(Seung Ho Jeon),송의찬(Eui Chan Song) 대한산업공학회 2020 대한산업공학회지 Vol.46 No.2
Due to smart factories that can produce various types of products quickly, the ability to pick up various objects within a single manufacturing process has become important. Accordingly, many general-purpose vacuum grippers have been used, however, the performance of the pick-up operation depends on the degree of uniformness in a contact surface of a target object. Therefore, we aim to prevent abnormal conditions in the manufacturing process by real-time inspecting a surface of a target product before a pick-up/gripping process is performed. In particular, in order not to increase the manufacturing cost, the surface deviation data of a product was collected using an ultrasonic sensor, and a quality inspection was performed in real time by applying a convolution neural network to the collected data. The performance of the proposed method is verified through pick-up operation using the 6-axis robot with a vacuum gripper in the box packaging process.