Skip to content

Machine Learning and Advanced Digital Gauging for Subtractive and Additive Manufacturing Processes

  • today
  • access_time 10:00 - 10:25 AM EDT
  • location_onRoom 140C
  • blur_circularConference
  • monetization_onPaid Upgrade
  • schoolOptimization

Quality management in metal 3D printing is one of the biggest challenges manufacturers are facing today on their way to mass production — requiring extensive process monitoring and extensive testing of every single part. In an effort to improve process monitoring and reduce the non-destructive testing efforts like 100% CT scanning-based qualification processes, Renishaw and Altair set out to explore new possibilities using artificial intelligence (AI). The focus of the work is a methodology to analyze the incredibly large quantities of the acquired manufacturing data. They put up AI to a test and arguably found a new way to improve quality control and accelerate the qualification process, paving the way toward AI-powered real-time melt-pool analytics. AI and machine learning are of increasing interest and applicability to industrial manufacturing enterprises. The potential to accelerate the transition to automated workflows via incorporation of sophisticated computational algorithms has already been leveraged in the field of design engineering for some time. In this presentation, we will be considering how the combination of simulation, in-situ measurement and machine learning can pay real-time dividends to both well understood subtractive manufacturing processes and nascent additive manufacturing technologies. In the course of the work presented, Altair (Troy, MI) a world-leading software and cloud solution provider for simulation, IoT, high-performance computing (HPC), data analytics and AI teamed up with Renishaw (Gloucestershire, UK), a global leader in industrial metrology, healthcare and additive manufacturing. 

Learning Objectives:

  • Implementing data-driven decision making from the ground up allows design and manufacturing teams to holistically analyze processes to improve an organization’s smart factory practices.
  • Have endless possibilities for machine improvement, such as identifying the best sensor type and location for an application, shared learning to improve processes within an enterprise with hybrid cloud approach.