Patents Examined by Steven W Crabb
  • Patent number: 11958500
    Abstract: Autonomous vehicle model training and validation using low-discrepancy sequences may include: generating a low-discrepancy sequence in a multidimensional space comprising a plurality of multidimensional points; mapping each sample of a plurality of samples of a data corpus to a corresponding entry in the low-discrepancy sequence, wherein each sample of the plurality of samples comprises one or more environmental descriptors for an environment relative to a vehicle and one or more state descriptors describing a state of the vehicle; selecting, from the data corpus, a training data set by selecting, for each multidimensional point of the low-discrepancy sequence having one or more mapped samples, a mapped sample for inclusion in the training data set; and training one or more models used to generate autonomous driving decisions of an autonomous vehicle based on the selected training data set.
    Type: Grant
    Filed: March 24, 2023
    Date of Patent: April 16, 2024
    Assignee: GHOST AUTONOMY INC.
    Inventors: Volkmar Uhlig, Par Botes
  • Patent number: 11960804
    Abstract: A peridynamic method having an added mirroring node according to embodiments of the present invention includes: a first step of calculating a shape tensor of a first node; a second step of calculating force state vectors of the first node and each of a plurality of second nodes by using the shape tensor; and a third step of calculating a peridynamic motion equation of the first node by using the force state vectors. The first node is a node located on a boundary of a structure and has a predetermined size horizon region, the plurality of second nodes is nodes in the horizon region, the plurality of second nodes includes one or more third nodes, and the third node is a second node having no node at a point which is origin-symmetrical based on the first node among the plurality of second nodes. In the first step, the shape tensor is calculated by using a position value in which the third node is origin-symmetrical based on the first node.
    Type: Grant
    Filed: January 19, 2018
    Date of Patent: April 16, 2024
    Assignee: Korea Advanced Institute of Science And Technology
    Inventors: Jung-Wuk Hong, Seong Eun Oh, Sang Eon Lee, Suyeong Jin
  • Patent number: 11954417
    Abstract: Disclosed a method for predicting permeability of a multi-mineral phase digital core based on deep learning. In the present disclosure, a three-dimensional digital core is constructed and a pore structure is randomly generated; after a plurality of multi-mineral digital core images is acquired by performing image segmentation on the three-dimensional digital core, permeability corresponding to each of the multi-mineral digital core images is acquired by simulation using multi-physics field simulation software and a multi-mineral digital core data set is constructed based on the plurality of multi-mineral digital core images and the permeability corresponding to each of the multi-mineral digital core images; an SE-ResNet18 convolutional neural network is constructed and trained with the multi-mineral digital core data set; and an image of a multi-mineral core to be predicted is input into the trained SE-ResNet18 convolutional neural network to determine the permeability of the multi-mineral core.
    Type: Grant
    Filed: November 8, 2023
    Date of Patent: April 9, 2024
    Assignee: CHINA UNIVERSITY OF PETROLEUM (EAST CHINA)
    Inventors: Hai Sun, Liang Zhou, Dongyan Fan, Lei Zhang, Jun Yao, Yongfei Yang, Kai Zhang, Qian Sang, Xia Yan, Lei Liu, Fei Luo, Yuda Kan
  • Patent number: 11954300
    Abstract: In various example embodiments, a comparative modeling system is configured to receive selections of a data set, a transform scheme, and one or more machine-learning algorithms. In response to a selection of the one or more machine-learning algorithms, the comparative modeling system determines parameters within the one or more machine-learning algorithms. The comparative modeling system generates a plurality of models for the one or more machine-learning algorithms, determines comparison metric values for the plurality of models, and causes presentation of the comparison metric values for the plurality of models.
    Type: Grant
    Filed: January 29, 2021
    Date of Patent: April 9, 2024
    Assignee: Palantir Technologies Inc.
    Inventors: Matthew Maclean, Benjamin Duffield, Mark Elliot
  • Patent number: 11939864
    Abstract: Aspects of the subject technology relate to systems and methods for controlling a hydraulic fracturing job.
    Type: Grant
    Filed: October 6, 2020
    Date of Patent: March 26, 2024
    Assignee: HALLIBURTON ENERGY SERVICES, INC.
    Inventors: William Owen Alexander Ruhle, Ronald Glen Dusterhoft, Ajish Potty, Joshua Lane Camp
  • Patent number: 11922104
    Abstract: Systems and methods include a computer-implemented method for displaying incremental values of average rate variations over a cumulative time window. A subset of independent variables corresponding to production variables of the oil well are selected using statistical analysis from a set of independent variables corresponding to production features of an oil well. The production parameters include performance variables for production of the oil well, design variables of the design of the oil well, and modeled independent variables of the oil well. Using the subset of independent variables and machine learning, predicted values of dependent variables are determined including an oil gain (?Qo) and a water reduction (?Qw) associated with production of the oil well. A display specifying incremental values of average rate variations over a cumulative time window is generated in a graphical user interface. The display is based at least in part on the predicted values of dependent variables.
    Type: Grant
    Filed: January 15, 2021
    Date of Patent: March 5, 2024
    Assignee: Saudi Arabian Oil Company
    Inventor: Jose Andino Saint Antonin
  • Patent number: 11914927
    Abstract: Systems, methods, and software for filtering components, such as hardware components, compatible with computer-modeled structures are presented. A compatible components system provides selection methods that present components compatible with computer-aided design (CAD) models designed in computer modeling software. The system executes methods designed to filter components made available to designers using attribute information of the features and attribute information of the components. Designers may interact with the compatibility methods numerous times, narrowing components through a series or number of filtering steps until a desired compatible component is easily selected. The computer modeling software may include graphical user interfaces for selecting component source locations, filtering types of components presented by the system, and adding components to CAD models.
    Type: Grant
    Filed: July 13, 2020
    Date of Patent: February 27, 2024
    Inventors: James L. Jacobs, II, John E. Cronin, Justin R. Kunz, Steven M. Lynch
  • Patent number: 11907625
    Abstract: Disclosed are computer implemented techniques for conducting a fluid simulation of a porous medium. These techniques involve retrieving a representation of a three dimensional porous medium, the representation including pore space corresponding to the porous medium, with the representation including at least one portion of under-resolved pore structure in the porous medium, defining a representative flow model that includes the under-resolved pore structure in the representation, and constructing by the computer system fluid force curves that correspond to fluid forces in the under-resolved pore structure in the representation.
    Type: Grant
    Filed: December 29, 2020
    Date of Patent: February 20, 2024
    Assignee: Dassault Systemes Americas Corp.
    Inventors: Hiroshi Otomo, Rafael Salazar Tio, Hudong Chen, Raoyang Zhang, Andrew Fager, Ganapathi Raman Balasubramanian, Bernd Crouse, Hongli Fan, Jingjing Yang
  • Patent number: 11899739
    Abstract: This disclosure describes a method to verify the design of an article of manufacture that includes a software program executing on a workstation that executes the following steps: providing the shape of a first component and providing the shape of a second component; providing a boundary distance constraint; constructing a shape spectrum of the exterior boundary surface of closest approach associated with the shape of the first component, the shape of the second component, and the boundary distance constraint; verifying that the arrangement of the shape of the first component and the shape of the second component satisfy the boundary distance constraint; evaluating a subderivative of the shape spectrum of the exterior boundary surface of closest approach associated with the shape of the first component, the shape of the second component; where verifying that the boundary distance constraint is satisfied between the shape of the first component and the shape of the second component and when satisfied, the desi
    Type: Grant
    Filed: May 7, 2019
    Date of Patent: February 13, 2024
    Assignee: Monarch Intellectual Property LLC
    Inventor: Paul B. Morton
  • Patent number: 11898094
    Abstract: The present invention relates generally to systems and processes for improved drag reduction estimation and measurement and more specifically to portable drag reduction analyzers and processes for upscaling drag reduction data for a variety of field applications. A drag reduction parameter ?B for the fluid mixture is used for determining drag reduction for a fluid mixture in an oil field or pipeline operation.
    Type: Grant
    Filed: November 25, 2020
    Date of Patent: February 13, 2024
    Inventors: Nabijan Nizamidin, Harold C. Linnemeyer, Timothy P. Theriot, Gojko Matovic, Seung Han, Do Hoon Kim, Kerry K. Spilker
  • Patent number: 11893329
    Abstract: Computer implemented methods include providing a numerical simulation solid mesh comprising a plurality of solid nodes and a numerical simulation fluid mesh comprising a plurality of fluid nodes, and performing a numerical simulation with the solid mesh and fluid mesh including: determining a fluid-solid interaction between the fluid mesh and the solid mesh at a time step by (i) immersing boundaries of the solid and fluid meshes, (ii) computing current corrected fluid and solid velocities using an interaction parameter applied to an intermediate fluid-solid relative velocity, and (iii) computing a fluid-solid interaction force based on the current corrected fluid and solid velocities.
    Type: Grant
    Filed: December 23, 2020
    Date of Patent: February 6, 2024
    Assignee: Triad National Security, LLC
    Inventors: Esteban Rougier, Earl E. Knight, Zhou Lei, Antonio Munjiza
  • Patent number: 11886782
    Abstract: A system and computer-implemented method are provided for training a dynamics model to learn the dynamics of a physical system. The dynamics model may be learned to be able to infer a future state of the physical system and/or its environment based on a current state of the physical system and/or its environment. The learned dynamics model is inherently globally stable. Instead of learning a dynamics model and attempting to separately verify its stability, the learnable dynamics model comprises a learnable Lyapunov function which is jointly learned together with the nominal dynamics of the physical system. The learned dynamics model is highly suitable for real-life applications in which a physical system may assume a state which was unseen during training as the learned dynamics model is inherently globally stable.
    Type: Grant
    Filed: July 20, 2020
    Date of Patent: January 30, 2024
    Assignee: ROBERT BOSCH GMBH
    Inventors: Gaurav Manek, Jeremy Zieg Kolter, Julia Vinogradska
  • Patent number: 11880638
    Abstract: A simulation method predicts a behavior of a curable composition in a process of bringing droplets of the curable composition arranged on first and second members into contact with each other, and forming a film of the curable composition on the first member. The method includes inputting a physical property value of a gas between the first and second members, inputting a movement profile of the second member with respect to the first member when bringing the droplets of the curable composition on the first and second members into contact with each other, obtaining a pressure of the gas between the first and second members based on the physical property value and the input movement profile, and predicting, based on the pressure, an amount of a residual gas confined among the droplets by the contact between the droplets and the second member.
    Type: Grant
    Filed: November 30, 2020
    Date of Patent: January 23, 2024
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Shintaro Narioka, Yuichiro Oguchi
  • Patent number: 11880639
    Abstract: An apparatus for multi-stage fracking, wherein the apparatus includes a pump configured to pump a fracking fluid into a rock region comprises a plurality of rock zones, and a computing device communicatively connected to the pump, wherein the computing device includes at least a processor, and a memory communicatively connected to the at least a processor containing instructions configuring the at least a processor to receive reservoir data, determine an optimal fracking stimulation parameter as a function of the reservoir data, identify a fracking stage as a function of the optimal fracking stimulation parameter, and adjust a pump configuration of the pump as a function of the fracking stage.
    Type: Grant
    Filed: November 14, 2022
    Date of Patent: January 23, 2024
    Inventor: David Cook
  • Patent number: 11875093
    Abstract: Techniques and systems for creating and performing analysis on three-dimensional computer models are described. The model creation and analysis may be specified using an un-compiled script that includes a set of instructions. The set of instructions may implement a computer-aided design (CAD) kernel using a bridge layer that includes compiled bridge code. The instructions may be used to create a job set having a group of tasks. Using the job set, a processing queue may be constructed, the processing queue having a subset of common tasks prioritized within the processing queue. Subsets or groups of tasks or instructions may also be executed in parallel using multiple distinct processors or a multi-threaded processor.
    Type: Grant
    Filed: February 9, 2022
    Date of Patent: January 16, 2024
    Assignee: Boeing Ace Collateral Agent, LLC
    Inventors: Raymond P. D'Antuono, Bharath Mukundakrishnan, Sushrut S. Pavanaskar, Dev G. Rajnarayan
  • Patent number: 11852778
    Abstract: Implementations described and claimed herein provide systems and methods for developing a reservoir. In one implementation, observed data points in a volume along a well trajectory and well logs corresponding to observed data points are received at a neural network. Feature vectors are generated using the neural network. The feature vectors are defined based on a distance between each of the observed data points and randomly generated points in the volume. A 3D populated log is generated by propagating well log values of the feature vectors across the volume. Uncertainty is quantified by generating a plurality of realizations including the 3D populated log. Each of the realizations is different and equally probable. core values are generated from the realizations, and a static model of the reservoir is generated by clustering the volume into one or more clusters of rock types based on the core values.
    Type: Grant
    Filed: October 8, 2021
    Date of Patent: December 26, 2023
    Assignee: BEYOND LIMITS, INC.
    Inventors: Azarang Golmohammadizangabad, Shahram Farhadi Nia
  • Patent number: 11853663
    Abstract: The disclosure provides an efficient Monte Carlo molecular simulation method for calculating the liquid phase interfacial tension between benzene and water by improving Ewald sum, including the following steps: Step A: Initialize the simulation: two simulation boxes were prepared, both with the size (30×30×45 ?)-(35×35×55 ?), and 1200-2000 water molecules and 230-380 benzene molecules were respectively put on the grid point of the two boxes; Step B: Select the force field used for simulation; Step C: Perform Monte Carlo simulations on the two boxes separately under the canonical ensemble; Step D: Join the water box and the benzene box along the z direction to form a large box of (30×30×90 ?)-(35×35×110 ?), and run 50000-80000 Monte Carlo cycles to make the system reach equilibrium; Step E: After the system reaches equilibrium, the data was collected during the production period.
    Type: Grant
    Filed: October 17, 2019
    Date of Patent: December 26, 2023
    Assignee: SHENZHEN JINGTAI TECHNOLOGY CO., LTD.
    Inventors: Bai Xue, Jian Ma, Lipeng Lai, Shuhao Wen, Peiyu Zhang
  • Patent number: 11847391
    Abstract: Described are computer implemented techniques for simulating elements of a fluid flow. These techniques include storing in a memory state vectors for a plurality of voxels, the state vectors comprising a plurality of entries that correspond to particular momentum states of a plurality of possible momentum states at a voxel, storing in a memory a representation of at least one surface that is sized and oriented independently of the size and orientation of the voxels, perform interaction operations on the state vectors, the interaction operations modelling interactions between elements of different momentum states, perform surface interaction operations on the representation of the surface, the surface interaction operations modelling interactions between the surface and substantially all elements of voxels, and performing move operations on the state vectors to reflect movement of elements to new voxels.
    Type: Grant
    Filed: June 29, 2020
    Date of Patent: December 19, 2023
    Assignee: Dassault Systemes Simulia Corp.
    Inventors: Pradeep Gopalakrishnan, Raoyang Zhang, Hudong Chen, Junye Wang, Avinash Jammalamadaka
  • Patent number: 11835054
    Abstract: Described are computer-related techniques for determining rotation direction of an axial fan for use in fluid flow simulations. The techniques involve receiving by a computer processing system digital data of a three dimensional representation of an axial fan having plural fan blade, determining by the computer processing system from the data of three dimensional representation of the axial fan, at least a single centerline of a single blade of the axial fan from a two dimensional projection of the axial fan, and calculating by the computer processing system based on the initial valve of fan rotation, an actual value of fan rotational direction.
    Type: Grant
    Filed: March 25, 2020
    Date of Patent: December 5, 2023
    Assignee: Dassault Systemes Simulia Corp.
    Inventors: Huhu Wang, Edward Dean Tate, Jr., Karthik Mahadevan Muthuraman, Satheesh Kandasamy
  • Patent number: 11809793
    Abstract: The present invention relates to a system and method for modelling flow conditions in a well system, the well system being represented by a number of branches (1,1a) conducting hydrocarbons from at least one branch entry point (3,3a) to a branch exit point (2), at least one of said branches constituting a global well system exit point, wherein each branch has a branch entry point (3,3a) being provided with a least one flow inlet (4) and being related to known boundary conditions and with a input flow control unit (7) being related to adjustable flow characteristics for controlling the flow through said input, said boundary conditions including predetermined data concerning at least one of pressure, temperature and flow at said input flow control unit, and said branch conduit includes an branch flow control unit (6), having adjustable flow characteristics for controlling the flow through the branch.
    Type: Grant
    Filed: January 3, 2019
    Date of Patent: November 7, 2023
    Assignee: ROXAR SOFTWARE SOLUTIONS AS
    Inventor: Gudbrand Nerby