专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明授权

US11200298B2 Reducing probability of glass breakage in drug delivery devices 有权
公开(公告)号：US11200298B2
公开(公告)日：2021-12-14
申请号：US16070224
申请日：2017-03-14
申请人： AMGEN INC.
发明人： Sean Fitzgibbon , Christopher R. Folk , Julian Jazayeri
IPC分类号： G06F17/18 , A61M5/20 , G06F30/17 , G06F30/20 , G16H20/17 , A61M5/315 , A61M5/32 , G06F111/08 , G06F111/10 , G06F17/13
摘要： A method for determining predicted failure rates of drug injection devices includes receiving a set of parameters that specify physical properties of (i) a syringe, and (ii) a liquid drug, and (iii) a drug injection device configured to deliver the liquid drug to a patient via the syringe. The method further includes receiving failure rate data that specifies a measured rate of failure of the drug injection device in response to various peak pressures within the syringe, applying the received set of parameters to a kinematic model of the drug injection device to determine a predicted peak pressure within the syringe, including determining the predicted peak pressure as a function of impact velocity of the liquid drug, determining a probability of failure of the drug injection device using (i) the received failure rate data and (ii) the predicted peak pressure, and providing an indication of the determined probability of failure to an output device.

42. 发明授权

US10928443B2 System and methods for analyzing and estimating susceptibility of circuits to radiation-induced single-event-effects 有权
公开(公告)号：US10928443B2
公开(公告)日：2021-02-23
申请号：US16445426
申请日：2019-06-19
申请人： LUCID CIRCUIT, INC.
发明人： Michel D Sika
IPC分类号： G01R31/28 , G06F30/39 , G06F30/367 , G06F111/08
摘要： Systems and methods for semiconductor design evaluation. IC layout information of a circuit design is received, and the circuit design is decomposed into smaller circuit pieces. Each circuit piece has IC layout information and a netlist. For each circuit piece, a set of strike models is selected based on the layout information and the net-list of the circuit piece and received radiation environment information. Each strike model has circuit components with voltage values corresponding to a respective particle strike. For each selected strike model of a circuit piece: a radiation susceptibility metric is determined by comparing functional results of simulation of the of the strike model with functional results of simulation of the circuit piece. For each circuit piece, a radiation susceptibility metric is determined based on the radiation susceptibility metrics generated for each selected strike model of the circuit piece.

43. 发明授权

US10902089B2 Method for predicting stochastic output performance or scaling stochastic inputs 有权
公开(公告)号：US10902089B2
公开(公告)日：2021-01-26
申请号：US15984755
申请日：2018-05-21
申请人： Government of the United States, as represented by the Secretary of the Air Force
发明人： Edwin E Forster
IPC分类号： G06F17/18 , G06F7/58 , G06F17/14 , G06N7/08 , G06N7/00 , G06F30/20 , G06F111/08
摘要： The invention provides a method for generating and analyzing random sample values. The method includes generating a random population array with a distribution and generating an array of random number coefficients by decomposing the random population array distribution using mean and variance. The array of random number coefficients is normalized and the normalized samples and antithetic samples may be mapped to the distribution of the random population array. The mapped, normalized samples and mapped normalized antithetic samples are arranged into a Walsh pattern.

44. 发明授权

US10824781B2 Reliability robust design method for multiple failure modes of ultra-deep well hoisting container 有权
公开(公告)号：US10824781B2
公开(公告)日：2020-11-03
申请号：US16333218
申请日：2017-12-07
申请人： CHINA UNIVERSITY OF MINING AND TECHNOLOGY
发明人： Hao Lu , Zhencai Zhu , Gongbo Zhou , Yuxing Peng , Guohua Cao , Wei Li , Gang Shen , Dagang Wang , Fan Jiang
IPC分类号： G06F30/23 , E21F13/00 , G06F30/17 , G06F111/04 , G06F111/08 , G06F111/10
摘要： A reliability robust design method for multiple failure modes of an ultra-deep well hoisting container, including: defining randomness of a structural parameter, a material property, and a dynamic load of a hoisting container, and solving a random response of a structural failure for a random parameter using a design of experiment method; establishing reliability performance functions of each failure modes in accordance with failure criterion of the hoisting container; establishing a joint probability model of correlated failures using a copula theory in consideration of probability correlation between the failure modes; establishing, a system reliability model with failure correlation of the hoister container; establishing a sensitivity model concerning each random parameter for system reliability of the hoisting container; and establishing, in conjunction with an optimization design model, a reliability robust optimization design model for the hoisting container using a joint failure probability and parameter sensitivity as constraints.

45. 发明授权

US10748077B2 Forecasting systems 有权
公开(公告)号：US10748077B2
公开(公告)日：2020-08-18
申请号：US14806563
申请日：2015-07-22
申请人： iRuiz Technologies Ltd
发明人： Ignacio Ruiz
IPC分类号： G06N7/08 , G06Q10/04 , G06F30/20 , G06F111/08
摘要： A computer-implemented method of determining an approximated value of a parameter in a first domain is described. The parameter is dependent on one or more variables which vary in a second domain, and the parameter is determined by a function which relates sets of values of the one or more variables in the second domain to corresponding values in the first domain. The method is implemented on a computer system including a processor, and the method comprises: determining a plurality of anchor points in the second domain, wherein each anchor point comprises a set of values of the one or more variables in the second domain; evaluating, at each anchor point, the function to generate corresponding values of the parameter in the first domain; generating an approximation function to the function by fitting a series of orthogonal functions or an approximation to a series of orthogonal functions to the corresponding values of the parameter in the first domain; and using the approximation function to generate the approximated value of the parameter in the first domain.

46. 发明授权

KR102464236B1 연속파 라이다 센서들을 시뮬레이션하는 방법 有权
公开(公告)号：KR102464236B1
公开(公告)日：2022-11-07
申请号：KR1020227004387
申请日：2019-07-09
IPC分类号： G01S7/48 , G06F30/367 , G01S17/00 , G06F111/08
摘要： 본발명은연속파(CW) 광검출및 거리측정(lidar) 센서의센서데이터를시뮬레이션하기위한방법에관한것이며, 이방법은 : CW 신호에기초하여, 적어도하나의광선을포함하는광선세트를생성하는단계, ―광선세트중의각각의광선은방출시작시간, t_0 및방출지속시간, T를가짐―; 광선세트중의각각의광선에대해, 적어도하나의객체를포함하는시뮬레이션된장면(6)을통해광선을전파하는단계; 광선세트중의각각의광선에대해, 시뮬레이션된장면(6)에서의검출위치에서전파된광선의신호기여분을계산하는단계; CW 신호와, 광선세트중의광선들의계산된신호기여분들의혼합에기초하여, 출력신호를생성하는단계; 및출력신호를저장하는단계와출력하는단계중 적어도하나를포함한다.

47. 发明申请

WO2022183143A2 SYSTEM AND METHODS FOR COVERAGE OPTIMIZATION OF TEST GENERATION PROGRAM FOR CPU RANDOM VERIFICATION USING REINFORCEMENT LEARNING 审中-公开
公开(公告)号：WO2022183143A2
公开(公告)日：2022-09-01
申请号：PCT/US2022/036338
申请日：2022-07-07
申请人： FUTUREWEI TECHNOLOGIES, INC.
发明人： YAN, Ning , MORTAZAVI, Masood Seyed , SHERRILL, Noah Lewis , CHU, Robert
IPC分类号： G06F30/27 , G06F30/33 , G06F111/08 , G06F115/10 , G06N3/08 , G06F11/261 , G06F11/263 , G06F2111/08 , G06F2115/10 , G06N3/045
摘要： According to various embodiments, a method for automated verification of a design under test (DUT) includes a computer device determining a plurality of test program sets in accordance with a set of configurable parameters. The method further includes the computer device determining a plurality of simulation results in accordance with the plurality of test program sets. The method further includes the computing device training an artificial intelligence system using the plurality of simulation results. The method further includes the computing device updating the set of configurable parameters in accordance with the trained artificial intelligence system. The method further includes the computing device repeating the determining the plurality of test program sets, the determining the plurality of simulation results, the training the artificial intelligence system, and the updating the set of configurable parameters until one or more predetermined criteria are satisfied.

48. 发明申请

WO2021178996A1 METHODS AND SYSTEMS AND SELECTING PARAMETERS TO APPROXIMATE DESIRED PROPERTIES OF STRUCTURAL COLOR 审中-公开
公开(公告)号：WO2021178996A1
公开(公告)日：2021-09-10
申请号：PCT/US2021/070213
申请日：2021-03-02
申请人： BASF SE , PRESIDENT AND FELLOWS OF HARVARD COLLEGE
发明人： TASK, Keith , DARJI, Rupa, Hiremath , MANOHARAN, Vinothan , STEPHENSON, Anna, B. , HWANG, Victoria , XIAO, Ming
IPC分类号： G06F30/25 , C09B67/08 , C09B69/00 , C09D5/00 , B01J13/00 , G06F111/08
摘要： Exemplary embodiments relate to techniques for determining structural color from parameters of an array of nanoparticles. The techniques include inputting structural and optical parameters and performing a probabilistic simulation to determine the structural color. An evolutionary optimization may be performed to determine parameters of the array of nanoparticles according to desired properties of structural color. The evolutionary optimization may employ the probabilistic simulation and further adjust one or more parameters of the array to approximate the desired properties of the structural color. Based on applying the probabilistic simulation, the technique may generate an output describing a value, or a range of values, for the one or more parameters of the array of nanoparticles that are selected to approximate the desired properties of the structural color.

49. 发明申请

WO2021178402A1 AUTOMATED DESIGN TOOL 审中-公开
公开(公告)号：WO2021178402A1
公开(公告)日：2021-09-10
申请号：PCT/US2021/020461
申请日：2021-03-02
申请人： SIEMENS ENERGY, INC.
发明人： RAMAMURTHY, Arun , XIA, Wei , BRYAN, Matthew , ABRAHAM, Santosh
IPC分类号： G06F30/27 , G06N3/04 , G06F119/08 , G06F111/08
摘要： A computer-implemented method of selecting design parameters for a system being designed includes developing, by a computing device an inverse model that includes a probabilistic representation of a simulation of a physical behavior of the system. The inverse model includes observable parameters and unobservable parameters. The method also includes specifying a desired value for a desired response characteristic for the system, specifying values for a portion of the observable parameters, and predicting, by an inverse model that includes a trained neural network, values of the observable parameters not specified and the unobservable parameters that result in the desired response characteristic equaling the desired value.

50. 发明申请

WO2021105714A1 MACHINE LEARNING 审中-公开
公开(公告)号：WO2021105714A1
公开(公告)日：2021-06-03
申请号：PCT/GB2020/053052
申请日：2020-11-27
申请人： INSTADEEP LTD
发明人： LATERRE, Alexandre
IPC分类号： G06F30/394 , G06F30/27 , G06F111/08
摘要： A computer-implemented method (200), a machine learning system (100), and non- transitory computer-readable storage medium (400) for training a neural network (102) are provided. The neural network (102) is used to instruct an agent (106) to select actions for interacting with an environment (108) to determine a solution to a specified problem. In the computer-implemented method (200) a state signal (116) representing a current state of the environment (108) is received. A Sequential Monte Carlo process is then used to perform a search to determine target action selection data (306) associated with the current state of the environment (108). This target action selection data (306) is stored in association with the state signal (116) and the current state of the environment (108) is updated by providing an action selection signal (114) based on the target action selection data (306). The Sequential Monte Carlo process involves generating a plurality of simulations using the neural network (102) to determine the target action selection data (306).

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式