2023 Industry 4.0 Session 3: Applications of Machine Learning and GenAI to further Industry 4.0

Tuesday, October 3 4:00PM-5:15PM CDT at the Hyatt Lodge Oak Brook

Explore the technology trends and organizational requirements needed for successful deployment of ML and AI, covering data management, quality, and integration. Generative AI is the next wave of productivity, taking materials-based and typically human-based creative industries by storm. Learn about how you can integrate these developments and empower your processes in this session featuring leaders in the field.

Read more about this session's speakers below:

4:00PM-5:15PM: Applications of Machine Learning and GenAI

4:00-4:30PM: "AI and machine learning deployment in refining: novel applications and learnings"

Marty Gonzalez, Innovation and Technology Principal, bp digital transformation & integration

There has been activity focused on combining large language models with other structure such as causal graphs that add explainability and a means to validate results. Hear about bp's work in machine learning and their best practices when it comes to generative AI in industrial data applications.

4:30-5:00PM:"How adding machine learning to simulation brings greater value for process industries"

Justin Hodges, Senior AI/ML Technical Specialist, Siemens Digital Industries Software

Machine learning (ML) had surges in popularity every decade before breaking the pattern to yield a permanent adoption of ML into numerous aspects of society.  Many factors, including but not limited to advances in parallel computing capabilities from GPUs to facilitate the inception of more sophisticated and capable ML algorithms, have supported this AI industrial revolution. Engineers today have the distinct opportunity to utilize these advancements in ML capabilities for our domain area of simulation and physical testing.

This talk will begin by providing a landscape for active and fruitful areas in which ML can help engineers, including faster insights, assisted workflows, leveraging physical and simulated data, efficient exploration, and tailored solutions. After providing concrete details to each theme, specific use cases will be reviewed within the scope of process industries. This will include various types of reduced order modeling problems/solutions, integrated solutions for standard industry toolchains, key ML pipeline considerations (e.g. pre-processing, sampling, etc.), and use cases concerning high quality and effective physical test measurement, among other things.

Connect with Justin through his LinkedIn here: https://www.linkedin.com/in/justin-hodges-phd-3432a58b