Ms. Samantha DUCHSCHERER
Global Product Manager, Applied Materials Inc.
Samantha is the Global Product Manager at Applied Materials, overseeing SmartFactory AI Productivity, Simulation AutoSched®, and Simulation AutoMod®. Prior to joining Applied Materials, Samantha held the position of Manager of Industry I4.0 at Bosch. In this role, she focused on enabling productivity enhancements through activities such as establishing data pipelines and implementing AI-powered self-adjusting machines. In addition to her industry experience, Samantha also worked as a Research Associate at Oak Ridge National Laboratory's Geographic Information Science and Technology Group, further expanding her expertise in data science. She holds a Master of Science degree in Mathematics from the University of Tennessee, Knoxville, and a Bachelor of Science degree in Mathematics from the University of North Georgia, Dahlonega. With her diverse background in software, automotive, and research institutions, Samantha brings a well-rounded perspective for scaled implementation of I4.0 solutions.
Presentation Title
AI Productivity Foundation with APPLIED MATERIALS
Abstract
Currently, various dispatching rules and schedulers are employed to meet due date commitments, maximize throughput, and minimize queue violations. However, these methods typically require manual adjustments and involve multiple parameters, resulting in a time-consuming process for users. Considering the impact of various unexpected events in manufacturing, automating this process becomes crucial for achieving higher yields and lower costs. Therefore, Applied is dedicated to assisting customers in establishing a robust foundation for implementing scalable AI solutions that addresses this productivity challenge. Applied has created a comprehensive blueprint that will assist facilities in transitioning from the initial manual stage to achieving the desired automated outcome. This involves establishing a platform with the right pipelines and infrastructure, implementing a simulation optimization method for faster results, leveraging reinforcement learning to further enhance speed and efficiency, and ultimately creating an AI dispatching engine that autonomously controls area-specific dispatching rules based solely on a user-defined objective function.