Battelle Memorial Institute

Raytheon Technologies Corporation

United Technologies Corporation

Draguna Vrabie

Ozgur Erdinc

Mei Chen

Thomas A Frewen

Hala Mostafa

Thomas W Edgar

William J Hofer

Kathleen E Nowak

Karanjit Kalsi

Jianming Lian

Soumya Kundu

Methods are described for protecting a cyber-physical system against a potential attacker of the system. The methods include a method of generating a plurality of examples for a training data set and training a system model using the training data set to generate a decoy configured to generate a synthetic output that mimics historical outputs generated by the system for a given historical system context. Also described is a method including receiving a system context of a cyber-physical system; receiving an inquiry into the system by a potential attacker; applying a system model to the system context and the inquiry; obtaining from the system model a synthetic output that mimics how a component of the system would respond to the inquiry given the system context; and providing the synthetic output to the potential attacker.

High-fidelity model-driven deception platform for cyber-physical systems

A method and system of providing customizable service for an asset. The method including generating a predictive model for each asset of a fleet, each predictive model based on an operational profile for the asset and including a probability density function associated with the operational durability of the asset, establishing a maintenance strategy associated with the asset, and combining each of the predictive models to generate a compound fleet performance model, the fleet performance model including a combined probability density function. The method also includes collecting actual asset performance and maintenance data to generate actual asset metrics, determining a fleet performance profile based on the actual asset metrics indicative of a health assessment of the fleet, comparing the predicted fleet performance with the actual fleet performance, and ascertaining actionable choices for managing the assets based on a deviation of the predicted and actual fleet performance.

Method for online service policy tracking using optimal asset controller

A system is described for protecting a cyber-physical system against a potential attacker of the cyber-physical system. The system includes at least one processor configured to: collect historical information about the cyber-physical system, and train, based on the historical information, a machine-learned model to predict future conditions of at least a portion of the cyber-physical system. Responsive to detecting an input signal to the cyber-physical system, the system is configured to output an alert to the cyber-physical system indicative of a potential attacker, and respond to the input signal by simulating, based on the future conditions predicted by the machine-learned model, functionality and communications of the at least a portion of the cyber-physical system.

Methods and apparatus are disclosed for extracting maximal frequency response potential in controllable loads. In one example, a method includes assigning a fitness metric to at least one electrical device coupled to a power grid, assigning a frequency threshold based on the fitness metric, and transmitting the assigned frequency threshold to the at least one electrical device. The fitness metric can be based at least in part on an availability component and a quality component associated with the at least one device and the frequency threshold can cause the at least one electrical device to activate autonomously based on a frequency of the power grid.

Extracting maximal frequency response potential in controllable loads

Systems and methods for the configuration of service policies for aircraft fleets and gas turbine engines are disclosed. One or more engine performance profiles may be generated based on historical engine performance data. The historical engine performance data may be retrieved based on one or more engine service parameters. A fleet performance profile may be generated based on the engine performance profiles. The engine service parameters may be varied to generate a configured engine performance profile. A configured fleet performance profile may be generated based on the configured engine performance profile.

Growing community of inventors

West Richland, WA, United States of America

Draguna Vrabie