Machine-Driven Performance for the Digital Thread (Authentise Weekly News-In-Review – Week 32)

Machine-learning methods are transforming image recognition and problem-solving skills in computers with hardware and simulation algorithms that are capable of providing actionable insights. Businesses are already starting to employ these new tools to gain a more efficient and productive workflow, automating the digital thread beyond simple dematerialization, as well as stepping into smart decision-making.

Machine Learning “Surfnet” Creates 3D Models From 2D Images

The SurfNet process. Image via Purdue University Mechanical Engineering.


New research has developed AI technology that can transform 2D images into 3D content. The method, called SurfNet, has great potential in the field of robotics and autonomous vehicles, as well as creating digital 3D content. The research was led by Purdue University’s Donald W. Feddersen Professor of Mechanical Engineering, Karthik Ramani.

Karthik Ramani explains this process:

“If you show it hundreds of thousands of shapes of something such as a car, if you then show it a 2D image of a car, it can reconstruct that model in 3D”.

Read more about Surfnet here.

MIT’s Robotic Arm 3D Printers Take The Stress Out of Architecture

4 self-supporting gridshell test designs, 3D printed in plastic using a robotic arm. Image via 3D Printing and Additive Manufacturing journal.


Stress Line Additive Manufacturing (SLAM) is an architectural 3D printing concept out of MIT. It challenges the typical FDM approach to construction, accounting for structural stresses caused by the act of depositing material layer-by-layer. […] In further development, the researchers will apply further architectural theory to the designs and make solid filled objects. They also hope to be able to integrate sensors into the system so the robotic arm intelligently adapts the design as it prints.

Read more about it at 3D Printing Industry.

Geometric search engines – How useful are they?

Digitisation presents challenges as well as opportunities: On the one hand we’re surrounded by more data than ever before, yet on the other, we have more efficient tools to manage the onslaught. […] In the process of searching for similar designs, while we have traditional search methods like text based and keyword based, they do fall short at times. Geometric Search Engines (GSEs) can significantly improve speed and efficiency of the digital thread in additive manufacturing to help solve these challenges.

Read the full article at Develop3D.

Don’t forget to come back next week for another news’ roundup. In the mean time, our Twitter feed should keep you updated with the latest AM/IIoT news!

#PurdueUniversity #GeometricSearchEngines #KarthikRamani #Surfnet #SLAM #FDM #robotics #MIT #autonomousvehicles #simulation #DonaldWFeddersen #machinelearning

Follow us at:

  • LinkedIn
  • Twitter
  • YouTube
  • Facebook

MES for OEMs

MES for Service Bureaus

Extension Modules

About

Company Overview

Jobs

Support

Resources

Machine Integrations

Software Integrations

Contact Us

Philadelphia, PA, USA

Member of

Privacy Policy

Terms of Use

AUTHENTISE © COPYRIGHT 2020. ALL RIGHTS RESERVED.