Abstract: A system and methods are disclosed for determining a model of a subterranean region. The method includes obtaining an observed dataset and a current model for the subterranean region, simulating a dataset from the current model, and determining a data penalty function based on a difference between the observed and simulated datasets. The method further includes training a machine learning (ML) network to predict a model from the observed dataset and determining the predicted model using the trained ML network. The method further includes determining a first model penalty function based on the current model, a second model penalty function based on a difference between the current and the predicted models, and a composite penalty function based on a weighted sum of the data penalty function, the first and the second model penalty functions. Finally, the method includes determining the model based on an extremum of a composite penalty function.

Abstract: Embodiments of the invention are directed to using a trained machine learning model to generate predicted circuit data for a circuit design, and computing an objective function using the predicted circuit data. Optimization of the objective function is performed to generate an optimal solution, and the optimal solution is mapped to the circuit design.

Abstract: Provided is a groove bottom curve design optimization method for an overflow brick, including: S1: obtaining a standard output of the overflow brick based on design parameters; S2: obtaining an initial groove bottom curve of the overflow brick based on the design parameters and the standard output; S3: obtaining a groove bottom curve of the overflow brick through straight line correction of the initial groove bottom curve based on a length of a splitting block; S4: obtaining an extreme thickness difference of a formed glass substrate through overflow simulation based on the groove bottom curve and the design parameters; and S5: when the extreme thickness difference is smaller than or equal to a preset threshold, processing the overflow brick using the groove bottom curve and the design parameters; and when the extreme thickness difference is greater than the preset threshold, adjusting the design parameters and repeating steps S1 to S4.

Abstract: A method can include receiving data for a geologic region; based at least in part on the data, selecting a model from a plurality of models using a trained machine learning model, and inverting the data using the selected model to determine parameters of the selected model.

Abstract: A computer-implemented method for updating a description of an automation system of a power network including at least: providing a preliminary description of the automation system, the preliminary description including components and relationships; providing at least one non-functional requirement; adapting the preliminary description to meet the non-functional requirement by modifying the components and relationships; instantiating a final description of the automation system based on the adapted preliminary description.

Abstract: Determining the location, size, and orientation of features within a subterranean formation can be determined by using more than one set of azimuthal data collected along at least two different angle ranges of seismic detection. The azimuthal data collected along one azimuthal range can be stacked and combined. A feature probability map can be generated for each azimuthal data collection using a machine learning system. Feature probability maps generated using azimuthal data collected along different azimuthal angle ranges can be used to optimize a machine learning estimator to generate ensemble azimuthal datasets. More than one estimator can be used thereby generating more than one ensemble azimuthal dataset. These results can be combined using a weighting algorithm applied using a machine learning model resulting in a combined feature probability map that can reduce the uncertainty of the characteristics of the feature of the subterranean formation.

Abstract: An integrated capacity modelling system for monitoring and controlling multiple oil and gas assets, the system comprising a data acquisition module, capable of acquiring upstream data, whereas upstream data may include information from the multiple oil and gas assets; a subsurface and surface processes simulation module, capable of simulating production and injection performance of multiple oil and gas assets from the reservoir to the sales delivery point; a data assimilation module, capable of extracting key features in the data for the purposes of calculating production capacity of multiple oil and gas assets from the acquired upstream data and from the simulation module and for building an asset capacity model thereof; a data presentation module, capable of presenting all the components of the asset capacity model of multiple oil and gas assets, wherein the presentation module is capable of presenting the asset capacity model of multiple oil and gas assets in nodes of a hierarchical structure of a pluralit

Abstract: An approach for reducing edge computing resources associated with autonomous vehicle infrastructure is disclosed. The approach utilizes digital twin computing to create a digital copy of the autonomous vehicle and edge computing demand. The approach can simulate the entire journey of the autonomous vehicle(s) on a travel path to determine the edge computing resources requirements. And based on the generated data set, the approach provides recommendations of proactive vehicle maintenance plan to improve edge computing capability of the vehicle based on the selected route. Other recommendation can include identifying whether road maintenance is to be performed for optimum usage of edge computing capability.

Abstract: In one embodiment, use of virtual thermal cameras in simulations systems can rapidly increase the deployment of vehicles with autonomous driving systems that include thermal cameras as a part of the sensor systems that detect people, other cars, etc. This use can be achieved by calibrating virtual thermal cameras using a virtual object or scenes with predetermined temperatures of objects (humans) in the scenes. The virtually calibrated thermal camera can then be used in virtual simulations of driving scenarios to generate learning data, such as virtual thermal images, to test autonomous driving systems and autonomous driving algorithms. The calibration can use a temperature conversion process, and the generation of the learning data can also use this temperature conversion process that includes the addition of noise, represented by temperature values.

Abstract: A global fluid identity repository is used to maintain and manage fluid characterization data for various fluids utilized in the oil & gas industry, e.g., reservoir fluids within subsurface formations. Tracking and notification services may be utilized to track changes made to a global fluid identity, e.g., changes in fluid sample and/or experiment data for a fluid, and automatically generate notifications when downstream data such as fluid models and/or simulation results become stale as a result of these changes.

Abstract: A well pattern optimization method based on CO2 incomplete miscible displacement characteristics is provided, including: obtaining fluid component data of formation crude oil, and establishing a fluid component model based on the fluid component data; establishing a three-dimensional reservoir model based on the fluid component model, and setting reservoir parameters for the three-dimensional reservoir model; performing simulation operation on the three-dimensional reservoir model with set reservoir parameters under different CO2 flooding well pattern modes, and obtaining simulation operation results; and performing analysis of fronts and production parameter comparison on the simulation operation results, and obtaining an optimal CO2 flooding well pattern mode.

Abstract: A method and system provide for multi-surface patterning. An input target multi-surface consisting of multiple target surfaces is obtained. A first guide curve is obtained. A pattern is obtained. One or more section planes are created based on the pattern and the first guide curve. The one or more section planes are intersected with each of the multiple target surfaces resulting in an intersection curve for each of the multiple target surfaces. A single continuous curve is created from the intersecting curves. Points are generated based on the continuous curve, the first guide curve, and the pattern. An object is generated and placed based on the points.

Abstract: Systems and methods for emulate or prototyping of hardware, such as memory, are disclosed. A memory compiler may receive information, such as system calls, indicative of one or more aspects of latency. Responsive to the information, the memory compiler may create infrastructure, such as pipelines and FIFOs, based on the aspects of latency, for emulation or prototyping of the hardware. Using the created infrastructure may improve emulation compile speed, such as by creating a pipeline-based cache structure, and may improve emulation runtime speed, such as by utilizing earlier unused model clocks to fetch data from host sooner.

Abstract: A model representing a physical object in a shape optimization according to a design objective, and a control point for altering a shape of the physical object are received. The shape is defined by a set of nodes in the model. Sibling models are generated from the model according to a perturbation scheme. The control point is perturbed with respective perturbed values for the sibling models. Each sibling model contains nodal location changes for the nodes. The nodal location changes are determined based on a respective shape function formulated according to a respective perturbed value at the control point and one or more simulated physical behaviors of the model. The model is updated to have an optimal value for the control point. The optimal value is identified from a relationship according to the design objective. The relationship correlates a physical characteristic of the sibling models to the respective perturbed values.

Abstract: Techniques are discussed herein for executing simulations with parameterized object controllers to control smart agents, to evaluate the agent realism of the smart agents and to validate the efficacy of the simulations. A simulation system may analyze log data captured by a vehicle operating in a physical environment, to determine observable and non-observable behavior characteristics of the agents in the environment. The simulation system may execute simulations using object controllers to control simulated objects (e.g., “smart agents”) based on parameters associated with scenarios, object types, and/or scenario locations. Log data associated with smart agent behaviors may be aggregated and compared to the behavior characteristics of agents in physical environments, to determine metrics for agent realism and simulation efficacy. Based on such metrics, simulation results may be validated and/or object controller parameters may be modified.

Abstract: A design method, for processes forming and assembling parts, begins by simulating a forming process (2) to generate a sprung back part simulation model (30) that corresponds to a reference geometry (10) of the formed part (3). Next, an assembly simulation (40) uses this sprung back model (30) to create an assembled sprung back part simulated model (50). If the geometry of this assembled model (50) does not match the reference geometry (10), a compensated sprung back part geometry (60) is iteratively adapted, and the assembly simulation (40) is repeated until the assembled model (50) aligns with the reference geometry (10). The final optimized geometry (60) can then be used to design and manufacture both the parts and the tools needed for forming them. The method avoids an iterative repetition of forming simulations, which allows a user interacting with the process to work in a more efficient manner.

Abstract: A subsurface representation may define subsurface configuration of a subsurface region. A grid connectivity graph for the subsurface representation may include (1) nodes that represent cells within the subsurface representation, and (2) edges between the nodes that represent connectivity between the cells within the subsurface representation. The grid connectivity graph may be filtered to remove edges that do not satisfy a connectivity criterion. The filtered grid connectivity graph may be used to compute a linear solver preconditioner that improves the performance of the subsurface simulation.

Abstract: A method of simulating an aircraft one-engine inoperative (“OEI”) event includes operating a supplemental power unit (“SPU”) at a first SPU power level less than an SPU contingency power rating, operating a primary engine at a first primary-engine power level, reducing the primary-engine power level to less than the first primary-engine power level, and maintaining a sum of the primary-engine power level and the SPU power level at a power level substantially equal to the SPU contingency power rating.

Abstract: Disclosed is a method for optimizing multi-cycle pressure-separated water injection in an oilfield based on an improved butterfly algorithm. The method includes: S1: obtaining basic data of a target water injection pipeline network; S2: constructing an objective function for a water injection scheme optimization model considering multi-cycle pressure-separated water injection; S3: establishing constraints to construct the water injection scheme optimization model considering multi-cycle pressure-separated water injection; and S4: solving the water injection scheme optimization model considering multi-cycle pressure-separated water injection using the improved butterfly algorithm to generate a multi-cycle pressure-separated water injection optimization scheme.

Abstract: A circuit simulation method includes the following operations: performing Monte Carlo simulations in parallel according to a first netlist file and process model data, in order to generate a performance simulation result, in which the first netlist file is configured to indicate a basic circuit in a circuitry; selecting component parameters lower than a predetermined yield rate according to the performance simulation result; and determining whether an estimated yield rate of the circuitry meets the predetermined yield rate according to the component parameters.