(133a) Learn Data-Driven Engineering with Interactive Modules

Data engineering with acquisition, transport, curation, and storage of data has emerged as a key role in Industry 4.0. This tutorial session shares new resources for hands-on data-driven engineering to teach important data engineering skills in collection, cleansing, pipelines, storage, and quality assessments. The sequence of learning modules covers introduction to data science in Python & MATLAB, data engineering, machine learning, process automation, optimization, and advanced control. Approximately 5,000 students per day access the freely available learning modules as self-paced tutorials on APMonitor.com or for Professional Development Credit on AIChE Academy. The 11 courses contain Python Jupyter Notebooks or MathWorks Live Scripts to provide interactive learning environments. Solution videos for each exercise guide students through potential solution strategies. One of the courses, Machine Learning for Engineers (https://apmonitor.com/pds), has 36 learning modules and 18 case studies that are specific to engineering practice with classification and regression in computer vision, energy, manufacturing, cybersecurity, and engineering design. This tutorial session gives an overview of the learning modules with a few interactive case studies during the session.

Dr. John Hedengren is a Professor at Brigham Young University in the Chemical Engineering Department. He leads the BYU Process Research and Intelligent Systems Modeling (PRISM) group with a current focus on structured machine learning for optimization of energy systems, unmanned aircraft, and drilling. Prior to BYU he worked in industry for 7 years on nonlinear estimation and predictive control for polymers. His work includes the APMonitor Optimization Suite with extension to Python GEKKO. He led the development of the Arduino-based Temperature Control Lab that is currently used by 70 universities for data science and process control education. His 85 publications span topics of data science, machine learning, smart grid optimization, unmanned aerial systems, and predictive control. He is the Chair of the Education Committee for the IEEE Control Systems Society, Distinguished Lecturer for the Society of Petroleum Engineers (2018-2019), recipient of the 2014 AIChE CAST Division David Himmelblau Award for Innovations in Computer-Based Chemical Engineering, and the 2018 AIChE CAST Division Computing Practice Award. He will share an overview of the BYU PRISM group research in hybrid machine learning methods with Transformer Neural Networks, Transfer learning, and applications in computer vision for worker safety and physics-informed neural networks applied to thermophysical property prediction.