Abstract: The system and method described below allow for real-time control over positioning of a micro-object. A movement of at least one micro-object suspended in a medium can be induced by a generation of one or more forces by electrodes proximate to the micro-object. Prior to inducing the movement, a simulation is used to develop a model describing a parameter of an interaction between each of the electrodes and the micro-object. A function describing the forces generated by an electrode and an extent of the movement induced due to the forces is generated using the model. The function is used to design closed loop policy control scheme for moving the micro-object towards a desired position. The position of the micro-object is tracked and taken into account when generating control signals in the scheme.

Abstract: One embodiment can provide a method and a system for diagnosing faults in a physical system. During operation, the system obtains a time-domain model of the physical system and converts the time-domain model to the frequency domain to obtain a frequency-domain model of the physical system. The time-domain model can include one or more model parameters having known values. The system also obtains time-domain input and output signals and converts the time-domain input and output signals to the frequency domain to obtain frequency-domain input and output signals. The system identifies at least one model parameter having an expected value that is different from a known value of the at least one model parameter based on the frequency-domain model and the frequency-domain input and output signals, and generates a diagnostic output indicating at least one component within the physical system being faulty based on the identified at least one model parameter.

Abstract: Systems and methods described receive a set of experimental data of connection points of an unknown component of a partially known physical system. The systems and methods set feasibility constraints for an untrained model of the unknown component and simulate the partially known system using the untrained model of the unknown component to generate simulated data at the connection points of the unknown component. Systems and methods then optimize the untrained model based on the feasibility constraints and a comparison of the simulated data and the experimental data to generate a trained model of the unknown component.

Abstract: The following relates generally to defense mechanisms and security systems. Broadly, systems and methods are disclosed that detect an anomaly in an Embedded Mission Specific Device (EMSD). Disclosed approaches include a meta-material antenna configured to receive a radio frequency signal from the EMSD, and a central reader configured to receive a signal from the meta-material antenna. The central reader may be configured to: build a finite state machine model of the EMSD based on the signal received from the meta-material antenna; and detect if an anomaly exists in the EMSD based on the built finite state machine model.

Abstract: The following relates generally to system modeling. Some embodiments described herein learn a representation of the parameter feasibility space that make model parameter tuning easier by constraining the search space, thus enabling physical interpretation of the learned model. They also enable model-based system analytics (controls, diagnosis, prognostics) by providing a system model.

Abstract: Embodiments described herein provide a system for facilitating a training system for a device. During operation, the system determines a system model for the device that can be based on empirical data of the device. The empirical data is obtained based on experiments performed on the device. The system then generates, from the system model, synthetic data that represents behavior of the device under a failure. The system determines uncertainty associated with the synthetic data and, from the uncertainty, determines a set of prediction parameters using an uncertainty quantification model. The system generates training data from the synthetic data based on the set of prediction parameters and learns a set of learned parameters associated with the device by using a machine-learning-based classifier on the training data.

Abstract: Embodiments described herein provide a system for facilitating comprehensive control data for a device. During operation, the system determines one or more properties of the device that can be applied to empirical data of the device. The empirical data can be obtained based on experiments performed on the device. The system applies the one or more properties to the empirical data to obtain derived data and learns an efficient policy for the device based on both empirical and derived data. The efficient policy indicates one or more operations of the device that can reach a target state from an initial state of the device. The system then determines an operation for the device based on the efficient policy.

Abstract: The system and method described below allow for real-time control over positioning of a micro-object. A movement of at least one micro-object suspended in a medium can be induced by a generation of one or more forces by electrodes proximate to the micro-object. Prior to inducing the movement, a simulation is used to develop a model describing a parameter of an interaction between each of the electrodes and the micro-object. A function describing the forces generated by an electrode and an extent of the movement induced due to the forces is generated using the model. The function is used to design closed loop policy control scheme for moving the micro-object towards a desired position. The position of the micro-object is tracked and taken into account when generating control signals in the scheme.

Abstract: One embodiment of the present invention provides a system for providing assistance to a user of a product in diagnosing faults in the product. During operation, the system receives, at a help server, data associated with current and/or past operation of the product; performs an optimization to determine a sequence of diagnostic actions that is expected to maximize a net benefit to the user. The sequence of diagnostic actions includes one or more actions that require the user to perform at least one task, and performing the optimization involves accounting for costs to the user for performing the at least one task and savings to the user for correcting the faults. The system then interacts with the user, which involves presenting the sequence of diagnostic actions to the user.

Abstract: A new and/or improved method, apparatus and/or system is disclosed which aids in extending correct behavioral models to include fault modes and in fault mode analysis of components and/or systems in simulated model environments, including, e.g., FMEA and FMECA and diagnostic fault tree generation.

Abstract: One embodiment of the present invention provides a system for providing assistance to a user of a product in diagnosing faults in the product. During operation, the system receives, at a help server, data associated with current and/or past operation of the product; performs an optimization to determine a sequence of diagnostic actions that is expected to maximize a net benefit to the user. The sequence of diagnostic actions includes one or more actions that require the user to perform at least one task, and performing the optimization involves accounting for costs to the user for performing the at least one task and savings to the user for correcting the faults. The system then interacts with the user, which involves presenting the sequence of diagnostic actions to the user.