Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

A universal convolutional neural network for the pixel-level detection and monitoring of weld beads

Wang Zhuo, Kayitmazbatir Metin, Banu Mihaela

Computer Methods in Materials Science

2024

Vol. 24, No. 2

27--38

In weld-based manufacturing processes such as welding and metal deposition additive manufacturing (AM), the weld bead is a direct indicator of manufacturing quality. For example, the geometry of the weld bead was optimized to a net shape which outperformed conventional geometries. Automatic monitoring of weld bead is thus of prime importance for welding process control and quality assurance. This paper develops a general-purpose convolutional neural network (CNN) for pixel-level detection and monitoring of beads, regardless of welding materials, machine, manufacturing conditions, etc. To achieve the generality, we collected a great variety of welding images containing 2677 single-line beads from 231 research articles, followed by pixel-wise hand-annotation. Consequently, the trained CNN can recognize different beads from various backgrounds at a pixel level. Case studies show that compared to the image-level classification in prior research, its pixel-level labeling permits real-time, complete characterization of weld beads (e.g., detailed morphology, discontinuity, spatter, and uniformity) for more informed process control. This research represents a significant step towards developing a truly human-like monitoring system with low-level scene understanding ability and general applicability.

Analysis and experiments of embedded gripping mechanism used in large-scale tools holding up pile foundation in ocean

Wang Zhuo, Zhang Bo, Wang Tao

Polish Maritime Research

2019

nr 3

15--21

With the rapid development of the marine economy and continuous improvement of the industry, the scale of the offshore engineering is increasing. This raises interest in studying, theoretically and experimentally, gripping and bearing mechanisms for large-scale holding and lifting tools used in foundation pile installations. In this paper, the embedded gripping mechanism is studied based on the theory of elastic-plastic mechanics. The embedded and bearing performance of the tooth is simulated and the influence factors are studied. In addition, the device used in the simplified embedded experiment on the tooth of the embedded block is designed. The relationship between embedded depth, load, and tooth profile angle is identified and validated. Meanwhile, the embedded performance of linear and ring type teeth is compared experimentally in order to select the suitable type of tooth for various situations. This comparison makes the basis for designing an upending gripper for the marine pile foundation, which can realize the operation of holding the pile to prevent its falling.