English

Artificial intelligence accelerates the process design of 3D printing of metal alloys

91
2024-02-27 17:00:47
See translation

In order to successfully 3D print metal parts to meet the strict specifications required by many industries, it is necessary to optimize process parameters, including printing speed, laser power, and layer thickness of deposited materials.

However, in order to develop additive manufacturing process diagrams that ensure these optimal results, researchers have to rely on traditional methods, such as using off-site material characterization to test laboratory experiments on parts printed with various parameters. Testing so many parameter combinations to develop the best process may be time-consuming and expensive, especially considering the various metals and alloys available for additive manufacturing.

David Guirguis, Jack Beuth, and Conrad Tucker from the Department of Mechanical Engineering at Carnegie Mellon University have developed a system that utilizes ultra high speed in situ imaging and visual transformers. This system not only optimizes these process parameters, but also has scalability, making it applicable to various metal alloys.

Their research findings are published in the journal Nature Communications.
Visual converter is a form of machine learning that applies neural network architectures originally developed for natural language processing tasks to computer vision tasks, such as image classification. The video visual converter goes further by using video sequences instead of still images to capture spatial and temporal relationships, enabling the model to learn complex patterns and dependencies in video data.

The self attention mechanism allows natural language processing models to balance the importance of different words in a sequence, and allows models created by Guirguis to balance the importance of different parts of the input sequence to predict the occurrence of defects.

"We need to automate this process, but it cannot be achieved solely through computer programming," explained Guirguis, a postdoctoral researcher in mechanical engineering. To capture these patterns, we need to apply machine learning.

"We are pleased to have developed an artificial intelligence method that utilizes the temporal characteristics of additive manufacturing imaging data to detect different types of defects. This demonstrates the groundbreaking generalizability of AI methods using different AM metals and reveals that the same trained AI model can be used without the need for expensive retraining with additional data," commented Professor Tucker of Mechanical Engineering.

Guirguis said he is fortunate to have received such powerful machine learning training at Carnegie Mellon University because mechanical engineers know how to apply experimental and computational solutions to the problems they solve, which is more important than ever before.

In this case, Guirguis attempts to overcome the main limitations of in-situ imaging in laser powder bed melt additive manufacturing processes. This technology uses high-power laser as an energy source to melt and melt powder at specific locations to form certain shapes, then a new layer of powder is spread out by a recoating machine, and the process is repeated until a 3D object is formed.

However, during the printing process, the molten metal seen by the camera is saturated, so its physical characteristics cannot be seen, which can identify defects that may reduce mechanical performance and fatigue life of printed parts.

Source: Laser Net

Related Recommendations
  • Aerotech launches new micro hexapod sports platform

    Recently, Aerotech Inc., a global leader in precision motion control and automation, launched the HexGen HEX150-125HL miniature hexapod motion platform, a six degree of freedom (DOF) precision positioning system. This compact and cost-effective hexapod sports platform has a base diameter of 150 millimeters and a nominal height of 125 millimeters. It can achieve a minimum incremental movement of up...

    01-14
    See translation
  • More penetrating than X-rays μ Meson imaging is expected to be advanced with high-power lasers

    μ Mesons are naturally occurring subatomic particles that can penetrate much deeper dense matter than X-rays. Therefore, μ Meson imaging can enable scientists to capture images of nuclear reactors, volcanoes, tsunamis, and hurricanes. However, this process is slow, as it occurs naturally μ The low flux of mesons requires several months of exposure time for the image.It is understood that ...

    2023-11-01
    See translation
  • NASA plans to use lasers to measure the impact of exhaust gases on the lunar surface during landing, in order to plan lunar landings more effectively

    Recently, NASA's official website showed that a research team at the University of Central Florida has tested an instrument called Ejecta STORM, which aims to measure the size and velocity of surface particles generated by exhaust gases from rocket powered landers on the moon or Mars.According to NASA, when a spacecraft lands on the moon or Mars, rocket exhaust plumes can produce efflorescent ejec...

    2023-10-31
    See translation
  • Accurate measurement of neptunium ionization potential using new laser technology

    Neptunium is the main radioactive component of nuclear waste, with a complex atomic structure that can be explored through mass spectrometry. This analysis is crucial for understanding its inherent characteristics and determining the isotopic composition of neptunium waste. Magdalena Kaja and her team from Johannes Gutenberg University in Mainz, Germany have developed a novel laser spectroscopy te...

    2024-05-11
    See translation
  • 2Pi Optics has launched a new type of fisheye camera based on its so-called metasurface optics

    2Pi Optics has launched a new type of fisheye camera based on its so-called metasurface optics.The company plans to showcase this technology at the large-scale technology trade show CES 2024 in Las Vegas next week.This company, headquartered in Cambridge, Massachusetts, stated that it has created the world's leading high-resolution fisheye sensor based on optical superlens technology. This technol...

    2024-01-05
    See translation