Abstract: Logged data from an autonomous vehicle is processed to generate augmented data. The augmented data describes an actor in an environment of the autonomous vehicle, the actor having an associated actor type and an actor motion behavior characteristic. The augmented data may be varied to create different sets of augmented data. The sets of augmented data can be used to create one or more simulation scenarios that in turn are used to produce machine learning models to control the operation of autonomous vehicles.

Abstract: A porous implant design method includes defining a design volume for a porous implant, a load to be borne by the design volume, and an objective function solution characteristic related to the design volume. Next, the load is divided into a plurality of sub-loads and an optimization procedure is performed: until all sub-loads have been applied, one of the plurality of sub-loads is applied to the material in the design volume, material from the design volume is removed such that remaining material within the design volume is capable of bearing one of the plurality of sub-loads while satisfying the objection function solution characteristic; the remaining material defines a void space without material, the void space is set as a new design volume for any remaining sub-loads, the new design volume is set as being full of material. Then, the remaining material from each cycle of the optimization is combined.

Abstract: A technique to stress test an integrated circuit design under test in a simulation environment may include running a simulation that includes providing bus interface transactions and idle cycles on a bus interface of an integrated circuit design. The technique may further include capturing bus interface activity on the bus interface during the simulation to generate a stimulus file and replaying the simulation by executing a test bench driver that reads the stimulus file and injects the bus interface transactions with modified idle cycles onto the bus interface of the integrated circuit design.

Abstract: A computer implemented method for drainage tile planning includes steps of presenting a first user interface to a user associated with a field in which drainage tile is to be installed and defining a set of drainage tile plan requirements by receiving through the first user interface and from the user associated with the field by: defining a boundary around the field by displaying a map including the field and receiving through the first user interface and from the user associated with the field a plurality of selections by the user associated with the field of edges of the field displayed on the map, and defining at least one desired drainage outlet position within the field by receiving through the user interface and from the user associated with the field a selection of the at least one desired drainage outlet position on the map.

Abstract: Systems and methods are disclosed for to determining a blood supply and blood demand. One method includes receiving a patient-specific model of vessel geometry of at least a portion of a coronary artery, wherein the model is based on patient-specific image data of at least a portion of a patient's heart having myocardium; determining a coronary blood supply based on the patient-specific model; determining at least a portion of the myocardium corresponding to the coronary artery; determining a myocardial blood demand based on either a mass or a volume of the portion of the myocardium, or based on perfusion imaging of the portion of the myocardium; and determining a relationship between the coronary blood supply and the myocardial blood demand.

Abstract: The present disclosure discloses a systematic method for generating a planar expandable structure by adding hinged points and hinged rods based on uniform tessellation, including: establishing a database of planar uniform tessellation graphs; selecting, inputting a graph of arbitrarily size range, naming it Graph A; drawing a dual tessellation graph of the Graph A, and extracting a basic unit b from it; determining whether the basic unit b has rotational symmetry, if not, then expanding the basic unit b to adjacent units, and denoting a final combined unit as Graph C; choosing to add hinged points or hinged rods, adjusting a length of each side of the Graph C, making Graph C?; adding original tessellation polygons in the Graph A to corresponding angular points of the Graph C?, rotating at a predetermined angle; hinging adjacent polygons by the hinged points or hinged rods together to obtain an expandable structural unit.

Abstract: A semi-elimination methodology for simulating high flow features in a reservoir and wells is disclosed. The reservoir and wells may be divided into a plurality of cells, including small cells in wells and the reservoir and bulk cells in the bulk of the reservoir, where the small cells are smaller (e.g., by pore volume) than the bulk cells. Processing of all of the cells, including all of the small cells, may be too computationally expensive, particularly when processing is iterative. In that regard, at least some of the small cells are partly processed in an iteration, such as for flow rates, compositions, or flow derivatives. After which, some or all of the small cells are eliminated from further processing in the iteration. In that way, high flow features in a reservoir and wells may be simulated effectively.

Abstract: A DOA-based pumping station-LID joint multi-objective optimization method, mainly including following steps: Step 1: collecting and sorting basic data of a research region; Step 2: fitting drainage parameter relationship expressions; Step 3: establishing an objective function and constraint conditions; Step 4: determining optimal solutions of a single objective function; Step 5: performing multi-objective function optimization calculation; Step 6: selecting an optimal solution. The multi-objective optimization method comprehensively considering economic and environmental benefits is particularly suitable for optimal design of installed flow capacity of a drainage pumping station at a watershed scale and layout rate of different LID measures.

Abstract: Methods and systems are provided characterizing a formation traversed by a wellbore, wherein the formation includes at least a flushed zone and an uninvaded zone, which involve obtaining well log data based on plurality of different well log measurements of the formation at multiple depths in the wellbore. The well log data is used by a computational model that solves for a set of petrophysical parameters that characterize a portion of the formation corresponding to the multiple depths in the wellbore, wherein the set of petrophysical parameters include a cementation exponent, a saturation exponent, and a flushed zone water resistivity. The solved-for set of petrophysical parameters can be used to determine a value of water saturation of the uninvaded zone for the portion of the formation corresponding to the multiple depths in the wellbore.

Abstract: The present disclosure provides a method for predicting a water invasion frontier for a complex well in a bottom-water gas reservoir. The technical solution is as follows: with consideration of forms of different well types and a gravitational pressure drop in production, a coupled permeability of a corresponding well type acting on a gas-water interface under the action of a baffle plate is expressed by using an equivalent percolation resistance method; a productivity of each infinitesimal section of the corresponding well type is calculated; a position of the gas-water interface is calculated with an equivalent permeability and a pseudo-productivity as characteristic parameters; water breakthrough is determined when there is a point over a water avoidance height, and a change in water invasion frontier form may be expressed with water quality point position data at this time.

Abstract: Apparatus and methods are provided for improving thermal control, including collecting data of a plurality of systems, each of the plurality of systems including at least one first cooling element and at least one first heat-generating element; conducting a first simulation using a simulation model based on the collected data to generate a first set of simulation results; conducting a first training on a control system using the first set of simulation results to obtain a first trained control system; and using the first trained control system to monitor a field system with a space having at least one second cooling element and at least one second heat-generating element and to control the at least one second cooling element and the at least one second heat-generating element.

Abstract: In some embodiments, techniques for creating a design for a physical device are provided. A computing system receives an initial design of the physical device. Performance of the physical device is simulated using the initial design. A performance loss value is determined for the physical device based on the simulated performance at a target wavelength and one or more delta wavelengths. The performance loss value is backpropagated to determine a gradient corresponding to an influence of changes in the initial design on the total performance loss value. The initial design of the physical device is revised based at least in part on the gradient.

Abstract: A machine learning-based method for designing a high-strength high-toughness steel, including: (S1) obtaining data and filling in missing parts to form a data set; (S2) selecting feature data in the data set to form a standard data set; (S3) constructing two machine learning models of the high-strength high-toughness steel; (S4) completing training after the two models are evaluated to be qualified; (S5) finding frontier points, drawing a Pareto front, and distinguishing a known region and a feature space; (S6) in the feature space, setting a step for the feature data, drawing a grid space, and performing multiple training predictions on each grid point by using the models, to obtain predicted Gaussian distributions of two objectives; and (S7) searching for an expected improvement point through an efficient global optimization algorithm, and obtaining design parameter values of corresponding features.

Abstract: A method for preoperatively characterizing an individual patients biomechanic function in preparation of implanting a prosthesis is provided. The method includes subjecting a patient to various activities, recording relative positions of anatomy during said various activities, measuring force environments responsive to said patient's anatomy and affected area during said various activities, characterizing the patient's biomechanic function from said relative positions and corresponding force environments, inputting the measured force environments, relative positions of knee anatomy, and patient's biomechanic function characterization into one or more computer simulation models, inputting a computer model of the prosthesis into said one or more computer simulation models, and manipulating the placement of the prosthesis in the computer simulation using said patient's biomechanic function characterization and said computer model of the prosthesis to approximate a preferred biomechanical fit of the prosthesis.

Abstract: Improved surgical planning systems and methods are provided for planning orthopaedic procedures, including pre-operatively, intra-operatively, and/or post-operatively to create, edit, execute, and/or review surgical plans. The surgical planning systems and methods may be utilized for planning and implementing orthopaedic procedures to restore functionality to a joint. In some embodiments, the systems and methods provide preoperative surgical planning based on anatomical makeup classifications that characterize anatomical differences within a representative patient population.

Abstract: The invention discloses a method for determining dynamic wetland boundary based on hydrology, organism and soil elements, including the following steps: step 1: extracting dynamic wetland hydrology boundary; step 2: obtaining data on wetland vegetation; step 3: obtaining data on wetland soil; step 4: simulating dynamic wetland vegetation boundary and dynamic wetland soil boundary according to the data from step 1 to step 3; step 5: determining dynamic wetland boundary; the invention can reflect the dynamic wetland boundary in multiple dimensions comprehensively and accurately.

Abstract: The present disclosure discloses a performance evaluation method of a LNG ambient air vaporizer, comprising: step 1, performing a site test on an actually-operating LNG AAV and obtaining its parameters, performing a fluid-thermal coupling calculation and simulation of the LNG AAV by use of FEA software, then performing model modification based on the test results; step 2, performing fluid-thermal-structure coupling calculation of an AAV for validation in the FEA software, adding a submodel module for optimization and validation tests; step 3, performing fluid-thermal-structure coupling calculation on the LNG AAV to be evaluated under a design operation condition and an operation condition of the AAV to be put into service in a certain region, and evaluating the LNG AAV according to the results. The present disclosure can evaluate vaporization performance and fatigue life of the AAV simultaneously and has good operability and economical efficiency.

Abstract: Systems, computer-implemented methods, and computer program products for planning of a cutting boundary for removal of a diseased region of an anatomy, such as a bone tumor. A cutting surface is placed relative to the diseased region in a virtual model. An optimization algorithm specifies an optimization criterion that minimizes an amount of healthy region to be removed by the cutting surface and initializes candidate solutions to influence characteristics of the cutting surface. The optimization algorithm identifies a candidate solution that satisfies the optimization criterion and modifies characteristics of the cutting surface based on the identified candidate solution. The cutting boundary is defined relative to diseased region in the virtual model based on the modified cutting surface. The cutting boundary can be registered to the anatomy for constraining operation of a surgical tool in response to interaction of the surgical tool with the registered cutting boundary.

Abstract: A method for fabricating a component of an abatement apparatus is disclosed. The method comprises: meshing a 3D model representation of a component defining a reaction chamber of an abatement apparatus based on specified component characteristics to define an optimised finite element representation of the component; and fabricating the optimised finite element representation. In this way, a 3D model of a component of an abatement apparatus can be generated from which its performance can be modelled. Particular characteristics of the component may be defined which affect the operation of the abatement apparatus. Those characteristics may then be used to generate the optimized finite element representation of the component which has those characteristics using meshing (it will be appreciated that meshing is the operation of representing a geometric object as a set of finite elements).

Abstract: A fingerboard management system that can determine via a rig controller, a selection of a location in the fingerboard for one or more tubulars and placement of the one or more tubulars in the fingerboard based on available locations in the fingerboard and historical information of each of the one or more tubulars and a method that can include importing a 3D model into a rig controller, collecting images of at least a portion of the rig, comparing the images to the 3D model or a visible marker, calibrating the vision system by determining a position, an orientation, and a field of view for each of the sensors based on the comparing, collecting additional images of the fingerboard, and determining an available total tubular storage space of the fingerboard based on the additional images of the fingerboard and the calibrated vision system.