Abstract: A method includes simulating a process, with computer-based software, to produce virtual data about the process; identifying process parameters for a real-world version of the process; providing a real-world sensor to sense a parameter associated with the real-world version of the process; receiving sensor readings from the real-world sensor while the real-world version is being performed; and training a machine-learning software model to predict a behavior of the real-world sensor based on the virtual data about the process, the process parameters, and the sensor readings.

Abstract: Embodiments provide methods and systems for performing computer-based simulations of real-world objects. In one such embodiment, a mesh-based model representing a real-world object and composed of a plurality of mesh elements each having geometric properties is obtained. In turn, a simulation of physical behavior of the real-world object is performed using the mesh-based model. According to an embodiment, performing the simulation includes, for at least one mesh element, modifying as a function of the geometric properties, measurement values, amounts, or levels of material properties used to determine the physical behavior.

Abstract: Unlike existing methods that rely on a manual procedure for setting conditions for performing computer-based simulations, embodiments automatically set conditions for a simulation of a real-world object represented by a computer aided design (CAD) model. In one such embodiment, the morphology of a CAD mode is analyzed to identify a function of an element of the CAD model. In turn, conditions for a simulation are defined based upon one or more rules corresponding to the identified function of the element of the CAD model, where said defining includes automatically setting conditions in a simulation of the real-world physical object.

Abstract: Unlike existing methods that rely on manual procedures for repairing finite element meshes in computer-based simulations, embodiments automatically repair finite element meshes for use in simulations of real-world objects. One such embodiment begins by identifying a non-compliant mesh element in a finite element mesh and extracting a mesh patch from the finite element mesh that includes the identified non-compliant mesh element. To continue, an invariant patch description for the extracted mesh patch is generated and a repair solution corresponding to the generated invariant patch description is obtained from a database storing pre-determined repair solutions. In turn, the mesh patch in the finite element mesh is repaired using the obtained repair solution.

Abstract: Embodiments provide methods and systems for performing computer-based simulations of real-world objects. In one such embodiment, a mesh-based model representing a real-world object and composed of a plurality of mesh elements each having geometric properties is obtained. In turn, a simulation of physical behavior of the real-world object is performed using the mesh-based model. According to an embodiment, performing the simulation includes, for at least one mesh element, modifying as a function of the geometric properties, measurement values, amounts, or levels of material properties used to determine the physical behavior.

Abstract: A method includes simulating a process, with computer-based software, to produce virtual data about the process; identifying process parameters for a real-world version of the process; providing a real-world sensor to sense a parameter associated with the real-world version of the process; receiving sensor readings from the real-world sensor while the real-world version is being performed; and training a machine-learning software model to predict a behavior of the real-world sensor based on the virtual data about the process, the process parameters, and the sensor readings.

Abstract: Embodiments of the present invention provide an augmented reality by defining a model representing a real-world system. After defining the model, a plurality of model simulations are performed using the defined model which produce predicted field data that is stored in memory. In turn, data from one or more sensors in the real-world system is received and the defined model is calibrated using the received field data relative to the stored predicted field data. Then, an augmented reality of the real-world system is provided using the calibrated model.

Abstract: Embodiments of the present invention provide an augmented reality by defining a model representing a real-world system. After defining the model, a plurality of model simulations are performed using the defined model which produce predicted field data that is stored in memory. In turn, data from one or more sensors in the real-world system is received and the defined model is calibrated using the received field data relative to the stored predicted field data. Then, an augmented reality of the real-world system is provided using the calibrated model.

Abstract: Embodiments of the present invention provide an augmented reality by defining a model representing a real-world system. After defining the model, a plurality of model simulations are performed using the defined model which produce predicted field data that is stored in memory. In turn, data from one or more sensors in the real-world system is received and the defined model is calibrated using the received field data relative to the stored predicted field data. Then, an augmented reality of the real-world system is provided using the calibrated model.

Abstract: A computer-implemented method for simulating behavior of a modeled object includes storing a tolerance attribute value in a memory area for a specified parameter of the modeled object, defining a set of rules representative of a plurality of assumptions of a model simulation, executing the model simulation based on the tolerance attribute, verifying an output of the model simulation with respect to a set of rules that are dependent on input and output values for which the tolerance attribute as verified, and validating the output behavior against requirements for every stage of the product lifecycle, from preliminary design to end of life.

Abstract: Unlike existing methods that rely on a manual procedure for setting conditions for performing computer-based simulations, embodiments automatically set conditions for a simulation of a real-world object represented by a computer aided design (CAD) model. In one such embodiment, the morphology of a CAD mode is analyzed to identify a function of an element of the CAD model. In turn, conditions for a simulation are defined based upon one or more rules corresponding to the identified function of the element of the CAD model, where said defining includes automatically setting conditions in a simulation of the real-world physical object.

Abstract: Unlike existing methods that rely on manual procedures for repairing finite element meshes in computer-based simulations, embodiments automatically repair finite element meshes for use in simulations of real-world objects. One such embodiment begins by identifying a non-compliant mesh element in a finite element mesh and extracting a mesh patch from the finite element mesh that includes the identified non-compliant mesh element. To continue, an invariant patch description for the extracted mesh patch is generated and a repair solution corresponding to the generated invariant patch description is obtained from a database storing pre-determined repair solutions. In turn, the mesh patch in the finite element mesh is repaired using the obtained repair solution.

Abstract: In the proposed approach cluster elements (bins) are made available as a keypad in the form of a cluster map. The user directly selects the cluster element (bin) with a mouse, touch or actual keypad. For each of the associated attributes, a cluster map is available that orders the attributes from high-to-low by color or shade intensity. When a cluster element is selected in one cluster map, that same cluster element is also highlighted in other cluster maps. For each of the cluster maps, a value axis is available which shows the value of the parameter for the selected cluster element. In the case of numerical values, the high/low attribute pattern across the cluster maps is easily visible. The selected data objects in the cluster map are displayed in a separate widget.

Abstract: An embodiment provides a virtual reality experience by defining a model representing an object that includes experimental parameters. After defining the model, a model simulation is performed, using variations of the experimental parameters, that produces results for each of the one or more variations. The results include a value for a behavior of interest of the model for each of the variations. Next, the results are compressed to an interpolant comprising discrete polytope bins with continuous surrogates of the behavior of interest. Responsive to user provided values of the experimental parameters, a value of the behavior of interest is predicted using the interpolant. In turn, a virtual reality experience is provided by displaying to the user an effect on the model for the user-provided values of the one or more experimental parameters where the displayed effect on the model reflects the predicted value for the behavior of interest.

Abstract: Embodiments of the present invention provide an augmented reality by defining a model representing a real-world system. After defining the model, a plurality of model simulations are performed using the defined model which produce predicted field data that is stored in memory. In turn, data from one or more sensors in the real-world system is received and the defined model is calibrated using the received field data relative to the stored predicted field data. Then, an augmented reality of the real-world system is provided using the calibrated model.

Abstract: An embodiment provides a virtual reality experience by defining a model representing an object that includes experimental parameters. After defining the model, a model simulation is performed, using variations of the experimental parameters, that produces results for each of the one or more variations. The results include a value for a behavior of interest of the model for each of the variations. Next, the results are compressed to an interpolant comprising discrete polytope bins with continuous surrogates of the behavior of interest. Responsive to user provided values of the experimental parameters, a value of the behavior of interest is predicted using the interpolant. In turn, a virtual reality experience is provided by displaying to the user an effect on the model for the user-provided values of the one or more experimental parameters where the displayed effect on the model reflects the predicted value for the behavior of interest.

Abstract: A computer-implemented method for touch input via a multi-touch surface includes displaying an input widget via the multi-touch surface, wherein the input widget includes at least one control field and at least one element bar. A finger contact is detected along the multi-touch surface and substantially within the control field or the element bar. In response to detecting the finger contact, the contents of the element bar are adjusted.

Abstract: In the proposed approach cluster elements (bins) are made available as a keypad in the form of a cluster map. The user directly selects the cluster element (bin) with a mouse, touch or actual keypad. For each of the associated attributes, a cluster map is available that orders the attributes from high-to-low by color or shade intensity. When a cluster element is selected in one cluster map, that same cluster element is also highlighted in other cluster maps. For each of the cluster maps, a value axis is available which shows the value of the parameter for the selected cluster element. In the case of numerical values, the high/low attribute pattern across the cluster maps is easily visible. The selected data objects in the cluster map are displayed in a separate widget.

Abstract: In the proposed approach cluster elements (bins) are made available as a keypad in the form of a cluster map. The user directly selects the cluster element (bin) with a mouse, touch or actual keypad. For each of the associated attributes, a cluster map is available that orders the attributes from high-to-low by color or shade intensity. When a cluster element is selected in one cluster map, that same cluster element is also highlighted in other cluster maps. For each of the cluster maps, a value axis is available which shows the value of the parameter for the selected cluster element. In the case of numerical values, the high/low attribute pattern across the cluster maps is easily visible. The selected data objects in the cluster map are displayed in a separate widget.

Abstract: Embodiments provide methods and systems for constructing surrogate models for use in interactive experiences. One such embodiment begins by defining a model that includes a parametric state vector and a design variable vector and represents a real world system. Next, a first and second experiment are performed to determine a response over time of the parametric state vector and to produce a dataset of the parametric state vector and the design variable vector as a function of time. The dataset is then modified with one or more derivatives of the parametric state vector and a set of surrogate differential equations is constructed that approximates a higher derivative of the parametric state vector relative to that in the dataset and the set of surrogate differential equations is stored as a surrogate model. The surrogate model is in turn provided from memory in a manner accelerating simulated behavior in response to user-interaction with the model.