This webinar will introduce participants to a number of computational methods that collectively enable a machine learning-empowered adaptive control system that can learn from experienced managers and operators in coordinating modular building manufacturing lines. The presenter will introduce computer vision and process data analytics methods that can automatically discover similar sequences of events and control actions from the logs of control systems, sensor records, and videos. These process data analytics techniques can support data-driven simulations of manufacturing processes and simulation-based optimization of process control and anomaly recovery strategies.
Presenter: Pingbo Tang, Ph.D., P.E.
Tang is an Associate Professor of Civil and Environmental Engineering at Carnegie Mellon University. His teaching and research interests lie in remote sensing, human systems engineering, and information modeling technology in support of the spatiotemporal analyses needed for the effective management of construction sites, constructed facilities, and civil infrastructure systems.