University of Southern California
file
Various critical decision-making and control problems associated with engineering and socio-technical systems are subject to uncertainties. Large-scale data collected from the Internet-of-Things and cyber-physical systems can provide information about the probability distribution of these uncertainties, such as product demand in supermarkets. Such distributional information can be used to dramatically improve the performance of closed-loop systems if they adopt appropriate controllers, which reduce the conservativeness of classical techniques, such as robust control.
file
In this project we consider the development of a Cyber Physical Freight Transportation System for load balancing in multimodal transportation networks. We use on line simulation models to capture the nonlinear and complex dynamical characteristics of the transportation networks. The simulation models generate the states of the network that are used to solve an optimization problem which finds the optimum routes.
file
A significant challenge in dimensional accuracy control of cyber-physical additive manufacturing systems (CPAMS) is the specification of geometric shape deviation models. The current practice of constructing tailor-made deviation models for each combination of computer- aided design model, additive manufacturing (AM) process, and process setting is impractical and inefficient for general application in CPAMS. We present a new framework and class of Bayesian neural networks for automated and efficient deviation model building in CPAMS.
