One problem in the injection molding industry is the lack of processing parameters provided to molders and engineers. Materials routinely lack the necessary data required to confidently set a first pass of processing parameters. Consequently, these parameters have to be inferred or guessed from similar materials or experience.
This webinar discusses the development of a new technology to predict missing processing parameters by using Machine Learning. Users will be introduced to Machine Learning, and how it applies to the Plastics industry. We will outline approaches and capabilities to use data and computers to reliably predict processing parameters and provide these to the engineer via web and mobile experiences.
Primary Topics:
What is Machine Learning
How Machine Learning applies to the Plastics Industry
Predicting undocumented processing parameters using ML
Availability of the technology
Speakers:
Jeff Selden, Director of Machine Learning, MobileSpecs
Jeff Selden is the Director of Machine Learning at MobileSpecs. Jeff has a PhD in Mathematics from the University of Arizona. Jeff has spent over 20 years as a collegiate instructor and researcher in mathematics.
Doug Kenik, Managing Director, MobileSpecs
Doug Kenik is the Managing Director of MobileSpecs. Doug has a MS in Mechanical Engineering, and has spent 10+ years in the composites and plastics industry as a developer and Product Manager for structural and process simulation software technologies.
Predicting Processing Parameters Using Machine Learning
April 02, 2019 |
All content on this page is provided by the presenting company.