Abstract: A computer-implemented method for detecting cyber-attacks affecting a computing device includes retrieving a plurality of sensor datasets from a plurality of sensors, each sensor dataset corresponding to involuntary emissions from the computing device in a particular modality and extracting a plurality of features from the plurality of sensor datasets. One or more statistical models are applied to the plurality of features to identify one or more events related to the computing device. Additionally, a domain-specific ontology is applied to designate each of the one or more events as benign, failure, or a cyber-attack.

Abstract: A system and method is provided that facilitates solving and enforcing associative constraints across heterogeneous models of the same system. The system may include a processor configured to: access an expression that specifies a relationship between at least one first constraint variable and at least one second constraint variable; access a first constraint map that maps at least one first model property of a first model to the at least one first constraint variable; and access a second constraint map that maps at least one second model property of a second model to the at least one second constraint variable.

Abstract: A method of managing a control system includes: executing a first iteration of a program in a first processor core of a multi-core computer system during a first period (S1501), executing a second iteration of the program in a second processor core of the multi-core system during a second period that overlaps the first period (S1502); and using outputs of the iterations to control the control system (S1503).

Abstract: A method for operating a machine-human interface in an automation environment includes receiving or automatically retrieving, by a machine-human interface computer, sensor data corresponding to a plurality of humans working the automation environment. The machine-human interface computer applies a human model to the sensor data to yield a plurality of human state records, each human state record corresponding to one of the humans working within the automation environment. The machine-human interface computer also identifies automation tasks using a factory state schedule. Based on the plurality of human state records, the machine-human interface computer assigns the automation tasks to the plurality of humans.

Abstract: A model-based human machine interface (HMI) system is provided. The HMI system includes a plurality of output devices each having output capabilities that include at least one unique output capability level and a semantics library that is configured to receive SUC component models each having an output format and data. The semantics library is configured to analyze the data relative to the SUC component models and to transmit each of the SUC component models to one or more of the plurality of output devices. The one or more of the plurality of output devices are selected based on a correlation between the output capabilities of the plurality of output devices and the output format of the SUC component models.

Abstract: A system is provided that facilitates design space exploration with quantitative pruning and ranking. The system may determine a collection of component model solutions corresponding to a functional model with functional model ports for a system to be produced. The component model solutions are comprised of simulated components selected from a component library based at least in part on correspondence between component ports of the simulated components and the functional model ports of the functional model. The system may select a subset of the component model solutions from the collection, which have behaviors determined for each component model solution that are consistent with behaviors determined for the functional model. The system may determine rankings for the component model solutions of the subset relative to each other based on a comparison of behaviors for each component model solution to each other and/or to the behaviors determined for the functional model.

Abstract: A computer-implemented method for learning structural relationships between nodes of a graph includes generating a knowledge graph comprising nodes representing a system and applying a graph-based convolutional neural network (GCNN) to the knowledge graph to generate feature vectors describing structural relationships between the nodes. The GCNN comprises: (i) a graph feature compression layer configured to learn subgraphs representing embeddings of the nodes of the knowledge graph into a vector space, (ii) a neighbor nodes aggregation layer configured to derive neighbor node feature vectors for each subgraph and aggregate the neighbor node feature vectors with their corresponding subgraphs to yield aggregated subgraphs, and (iii) a subgraph convolution layer configured to generate the feature vectors based on the aggregated subgraphs. Functional groups of components included in the system may then be identified based on the plurality of feature vectors.

Abstract: A method for providing adaptive resilience to a system defined by physical components includes generating an ontology comprising objects. Each object corresponds to (i) functions performed by a discrete physical component of the system; (ii) behaviors of the discrete physical component; (iii) physical structures included in the discrete physical component; and (iv) events that impact usage of the discrete physical component. Relationships are added to the ontology for each physical component including aggregation relationships, composition relationships, and dependencies between the physical components. Sensor data is received from sensors monitoring the physical components. Based on the data, an event is identified that is impacting physical components performing a system function. The ontology's attributes and relationships are used to generate an alternate system design comprising physical components that are functionally equivalent to the impacted components with respect to the system function.

Abstract: In an industrial automation environment, a three-tier architecture is used to offload human-machine-interaction (HMI) automation tasks to local mobile devices and then the cloud, to take advantage of distributed computing and processing resources and to add new features to the HMI panel system. A scheduling algorithm based on the characteristics of the HMI tasks distributes these tasks intelligently among the local HMI panel, mobile devices and the cloud, to best utilize the merits of each tier.

Abstract: A computer-implemented method for designing a system-of-systems for adaptation to unplanned scenarios includes receiving a plurality of sensor outputs and consolidating the plurality of sensor outputs into a current system status report. Next, in response to detection of a new unplanned need, currently available system resources are identified. An abstract description of a system-of-systems is updated based on the currently available system resources. Using the abstract description of the system-of-systems, feasible solutions are determined that could satisfy the new unplanned need. Each feasible solution comprises instructions for using resources included in the system-of-systems. A simulation network comprising a plurality of simulation models is generated based on the abstract description of the system-of-systems. Then, the simulation network is used to select one of the plurality of feasible solutions.

Abstract: A system and method is provided that facilitates cyber-physical security. The system may comprise a controller including at least one first processor; a monitor system including at least one second processor; and a plurality of sensors configured to capture a plurality of measurements associated with at least one hardware component. The sensors may include both: at least one controller sensor that communicates with the controller; and at least one side-channel sensor that communicates with the monitor system and not with the at least one controller. The first processor of the controller may be configured to cause the controller to control the hardware component based at least in part on measurements from the controller sensor.

Abstract: A system for threat detection in an industrial production environment comprises a programmable logic controller. This programmable logic controller includes a process image updated according to a scan cycle with process data associated with one or more field devices, a program configured to operate the one or more field devices using the process data, and one or more function blocks. These function blocks are configured to monitor the process data in the process image during each scan cycle, and identify a possible cyberattack based on the process data.

Abstract: Methods for synthesis of simulation models using functional operators. A method includes parsing a functional model, receiving a functional operator for a function within a simulation component of the functional model, receiving a structural template of the functional operator from a functional operator structural template library, mapping a plurality of functions according to the structural template of the functional operator to update the simulation component, and generating a simulation model with the updated simulation component.

Abstract: Methods for classifying and correlating simulation components to functional models. A method includes receiving a simulation component library comprising a plurality of simulation components into a memory of the data processing system, parsing the plurality of simulation components from the simulation component library, analyzing a plurality of extracted functions into a plurality of function graphs for each of the plurality of simulation components, composing an extracted functions graph with the plurality of extracted functions of the plurality of function graphs, and storing the extracted functions graph of the plurality of extracted functions in a components-to-function database.

Abstract: A system for threat detection in an industrial production environment comprises a programmable logic controller. This programmable logic controller includes a process image updated according to a scan cycle with process data associated with one or more field devices, a program configured to operate the one or more field devices using the process data, and one or more function blocks. These function blocks are configured to monitor the process data in the process image during each scan cycle, and identify a possible cyberattack based on the process data.

Abstract: A system and method is provided that facilitates solving and enforcing associative constraints across heterogeneous models of the same system. The system may include a processor configured to: access an expression that specifies a relationship between at least one first constraint variable and at least one second constraint variable; access a first constraint map that maps at least one first model property of a first model to the at least one first constraint variable; and access a second constraint map that maps at least one second model property of a second model to the at least one second constraint variable.

Abstract: A functional visualization of high-level system variables is based on information from a simulation environment. A functional model is imported from the simulation environment, including function nodes and connections. Each function node includes a function name, an associated component from the simulated system, and an associated physical variable. Each connection includes source and destination functions and a connection type. Values for the physical variables are obtained via a subscription with the simulation environment. The functional visualization is created and displayed based on the functional model and the values.

Abstract: A method for pipeline parallelizing a control program for multi-core execution includes using (12) data dependency analysis on a control program to identify tasks that can be performed in parallel, identifying (13) a largest task Tmax requiring the most execution time of the identified tasks, identifying (14) cut-points in the largest task Tmax where data dependency delays decouple the task, inserting (15) delayed data dependencies into cut-points of the largest task Tmax to create N pipeline sub-tasks, in which N is a number of cores available to a processor on which the control program will be executed, and scheduling (16) the tasks and pipeline sub-tasks to the available processor cores.

Abstract: Methods for product data management and corresponding systems and computer-readable mediums. A method includes receiving and parsing a functional model to produce a functional model graph, and receiving and parsing a three-dimensional (3D) model that corresponds to the functional model to produce a 3D model graph. The method includes identifying a plurality of one-dimensional (1D) candidate components corresponding to the functional model graph and the 3D model graph. The method includes creating a 1D graph corresponding to the 1D candidate components, parameterizing the 1D components in the 1D graph, and generating a 1D model from the parameterized 1D components.

Abstract: A method for translating domain-specific functional models to simulation models that provide simulation of physical domains. The method includes providing an overall domain of a behavior and subdividing the overall domain into a plurality of subdomains to define domain-specific behavior. The method also includes subdividing the subdomains into a plurality of single functional components to form domain-specific components and subdividing the single functional components into a plurality of atomic functional components to form atomic domain-specific components. In addition, the method includes providing transfer functions between the subdomains, single functional components and atomic functional components.