AI Transforms PLC Visual Inspection! - MATLAB
Video Player is loading.
Current Time 0:00
Duration 41:51
Loaded: 0.39%
Stream Type LIVE
Remaining Time 41:51
 
1x
  • Chapters
  • descriptions off, selected
  • captions off, selected
  • en (Main), selected
    Video length is 41:51

    AI Transforms PLC Visual Inspection!

    Overview

    This webinar provides an overview of the complete workflow for designing and deploying AI algorithms for image classification on PLCs. The focus is on developing an image classification algorithm for hexnuts to determine if they are damaged or in good quality. The main points covered in the workflow are as follows:

    1. Design and train the deep learning algorithm using the Deep Learning Toolbox, specifically utilizing the resnet18 architecture.
    2. Deploy the trained AI model onto a Beckhoff PLC using generic C code generation, ensuring library-free source code.
    3. Optimize the AI models using pruning, quantization to reduce size and increase the inference speed.
    4. Utilize the MATLAB App Designer to create a user-friendly graphical user interface (GUI) for interacting with the Beckhoff PLC in External Mode, enabling seamless communication and monitoring.

    This overview showcases the end-to-end process, from Deep Learning model design to deployment on hardware, providing insights of MATLAB in developing and deploying AI solutions for real-world applications.

    About the Presenters

    Sagar Hukkire, Application Engineering MathWorks

    Sagar Hukkire works as an Application Engineer, focusing on the usages of MATLAB in Data Analytics, Text Analytics, and Image Analytics applications. Before joining MathWorks in 2020, Sagar worked extensively in the field of Machine Learning and Deep Learning, specializing in developing cutting-edge solutions for Text Analytics and Image Analytics. His passion for cloud technologies has allowed him to further enhance his skill set and stay at the forefront of technological advancements.

    Sagar holds a Master of Science degree in Information Technology from the University of Stuttgart, Germany, further solidifying his technical foundation.

    Conrado Ramirez Garcia, Senior Application Engineer - Design Automation and Code Generation, MathWorks

    Conrado Ramirez Garcia is an application engineer at MathWorks Germany. He specialized in supporting customers of different areas including machine builders, industrial robotics, wind turbines, automation, and energy production. His focus area includes the code generation for embedded devices and industrial controllers.

    Before joining MathWorks, he worked for 5 years at GE Aviation and GE Power as a Controls Engineer. Conrado holds a master’s degree on Power Engineering from the Technische Universität München, where he specialized on Control Systems, Energy Systems and Power Electronics.

    Recorded: 7 Nov 2023

    View more related videos