专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2004063769A3 NEURAL NETWORK TRAINING DATA SELECTION USING MEMORY REDUCED CLUSTER ANALYSIS FOR FIELD MODEL DEVELOPMENT 审中-公开
标题翻译：神经网络训练数据选择使用存储器减少集群分析进行现场模型开发
公开(公告)号：WO2004063769A3
公开(公告)日：2005-02-17
申请号：PCT/US0341239
申请日：2003-12-23
申请人： HALLIBURTON ENERGY SERV INC
发明人： CHEN DINGDING , QUIREIN JOHN A , WIENER JACKY M , GRABLE JEFFERY L , HAMID SYED , SMITH JR HARRY D
IPC分类号： G01V20060101 , G06E1/00 , G06E3/00 , G06F15/18 , G06F17/00 , G06F17/50 , G06G7/00 , G06K9/62 , G06N3/08 , G06N5/00 , G06N5/02
CPC分类号： G06K9/6298 , G01V11/00 , G06N3/08
摘要： A system and method for selecting a training data set from a set of multidimensional geophysical input data samples for training a model to predict target data. The input data may be data sets produced by a pulsed neutron logging tool at multiple depth points in a cases well. Target data may be responses of an open hole logging tool. The input data is divided into clusters (16, 24). Actual target data from the training well is linked to the clusters. The linked clusters are analyzed for variance, etc. and fuzzy inference (34) is used to select a portion of each cluster (36) to include in a training set. The reduced set is used to train a model, such as an artificial neural network. The trained model may then be used to produce synthetic open hole logs in response to inputs of cased hole log data.
摘要翻译：一种用于从一组多维地球物理输入数据样本中选择训练数据集的系统和方法，用于训练模型以预测目标数据。输入数据可以是在情况良好的多个深度点上由脉冲中子测井工具产生的数据集。目标数据可能是露天测井工具的响应。输入数据被分成簇（16,24）。来自训练井的实际目标数据与集群有关。分析链接的聚类以进行方差等，并且使用模糊推理（34）来选择每个聚类（36）的一部分以包括在训练集中。缩减集用于训练模型，如人造神经网络。然后可以使用经过训练的模型来响应于套管孔日志数据的输入而产生合成开孔日志。

2. 发明申请

WO0250571A2 PROCESSING WELL LOGGING DATA WITH NEURAL NETWORK 审中-公开
标题翻译：用神经网络处理井记录数据
公开(公告)号：WO0250571A2
公开(公告)日：2002-06-27
申请号：PCT/US0149193
申请日：2001-12-19
申请人： HALLIBURTON ENERGY SERV INC , CHEN DINGDING , SAN MARTIN LUIS E , MERCHANT GULAMABBAS A , STRICKLAND ROBERT W , HAGAN MARTIN T
发明人： CHEN DINGDING , SAN MARTIN LUIS E , MERCHANT GULAMABBAS A , STRICKLAND ROBERT W , HAGAN MARTIN T
IPC分类号： E21B41/00 , G01V1/48 , G01V3/28 , G01V
CPC分类号： G01V3/28 , E21B2041/0028 , G01V1/48
摘要： An artificial neural network (ANN) (34) and method of training the ANN for inversion of logging tool signals into well logs of formation parameters is taught (Fig. 4). Properly selected synthetic models (32) of earth formations are used to train the ANN (34). The models include Oklahoma and chirp type formations.
摘要翻译：教授人工神经网络（ANN）（34）和训练用于将测井工具信号反演的ANN用于地层参数测井的方法（图4）。使用适当选择的地层合成模型（32）来训练ANN（34）。模型包括俄克拉何马州和唧唧类型组成。

3. 发明申请

WO2013016359A2 AUTOMATIC OPTIMIZING METHODS FOR RESERVOIR TESTING 审中-公开
标题翻译：水库试验的自动优化方法
公开(公告)号：WO2013016359A2
公开(公告)日：2013-01-31
申请号：PCT/US2012048010
申请日：2012-07-24
申请人： HALLIBURTON ENERGY SERV INC , PROETT MARK , CHEN DINGDING , HADIBEIK ABDOLHAMID , EYUBOGLU SAMMI ABBAS
发明人： PROETT MARK , CHEN DINGDING , HADIBEIK ABDOLHAMID , EYUBOGLU SAMMI ABBAS
IPC分类号： E21B47/04
CPC分类号： E21B47/06 , E21B49/087
摘要： A method of determining a reservoir parameter of a subterranean formation comprising: initiating an initial pressure pulse in the subterranean formation; initiating a series of subsequent pressure pulses in the subterranean formation until the reservoir parameter may be determined, wherein each subsequent pressure pulse is optimized utilizing analytical and/or numerical simulation models; and determining the reservoir parameter.
摘要翻译：一种确定地下地层的储层参数的方法，包括：在地下地层中启动初始压力脉冲; 在地层中开始一系列随后的压力脉冲，直到可以确定储层参数，其中使用分析和/或数值模拟模型优化每个后续压力脉冲; 并确定储层参数。

4. 发明申请

WO2007067824A3 METHOD OF RESERVOIR CHARACTERIZATION AND DELINEATION BASED ON OBSERVATIONS OF DISPLACEMENTS AT THE EARTH'S SURFACE 审中-公开
标题翻译：基于地球表面位移观测的储层特征和分类方法
公开(公告)号：WO2007067824A3
公开(公告)日：2009-04-02
申请号：PCT/US2006060015
申请日：2006-10-16
申请人： HALLIBURTON ENERGY SERV INC , MESE ALI , HAMID SYED , CHEN DINGDING , SMITH HARRY D , HOWARD JOHN , SKINNER NEAL
发明人： MESE ALI , HAMID SYED , CHEN DINGDING , SMITH HARRY D , HOWARD JOHN , SKINNER NEAL
IPC分类号： G01V9/00
CPC分类号： G01V11/00
摘要： Reservoir characterization based on observations of displacements at the earth's surface. One method of characterizing a reservoir includes the steps of: detecting a response of the reservoir to a stimulus, the stimulus causing a pressure change in the reservoir; and determining a characteristic of the reservoir from the response to the stimulus. The response may be the pressure change which varies periodically over time, or a set of displacements of a surface of the earth. In another example, a method includes the steps of: detecting a set of displacements of the earth's surface corresponding to a pressure change in the reservoir; and determining a characteristic of the reservoir from the surface displacements . In yet another example, a method includes the steps of: detecting a set of displacements of the earth's surface corresponding to a change in volume of the reservoir; and determining a characteristic of the reservoir from the surface displacements.
摘要翻译：基于地球表面位移观测的油藏特征。表征储层的一种方法包括以下步骤：检测储层对刺激的响应，所述刺激导致储层中的压力变化; 以及从所述刺激的响应确定所述储层的特性。响应可以是随时间周期性地变化的压力变化或地球表面的一组位移。在另一示例中，一种方法包括以下步骤：检测对应于储层中的压力变化的地球表面的一组位移; 以及从表面位移确定储层的特征。在又一示例中，一种方法包括以下步骤：检测对应于储层体积变化的地球表面的一组位移; 以及从表面位移确定储层的特征。

5. 发明申请

WO2005098647A3 GENETIC ALGORITHM BASED SELECTION OF NEURAL NETWORK ENSEMBLE FOR PROCESSING WELL LOGGING DATA 审中-公开
标题翻译：基于遗传算法的神经网络选择ENSEMBLE用于处理井记录数据
公开(公告)号：WO2005098647A3
公开(公告)日：2009-04-16
申请号：PCT/US2005009494
申请日：2005-03-22
申请人： HALLIBURTON ENERGY SERV INC , CHEN DINGDING , HAMID SYED , SMITH HARRY D JR
发明人： CHEN DINGDING , HAMID SYED , SMITH HARRY D JR
IPC分类号： G06F15/18 , G06N3/08
CPC分类号： G06N3/086
摘要： A system and method for generating a neural network ensemble. Conventional algorithms are used to train a number of neural networks having error diversity, for example by having a different number of hidden nodes in each network. A genetic algorithm having a multi-objective fitness function is used to select one or more ensembles. The fitness function includes a negative error correlation objective to insure diversity among the ensemble members. A genetic algorithm may be used to select weighting factors for the multi-objective function. In one application, a trained model may be used to produce synthetic open hole logs in response to inputs of cased hole log data.
摘要翻译：一种用于生成神经网络集合的系统和方法。常规算法用于训练具有错误分集的多个神经网络，例如通过在每个网络中具有不同数量的隐藏节点。使用具有多目标适应度函数的遗传算法来选择一个或多个合奏。适应度函数包括负误差相关目标，以确保集合成员之间的多样性。可以使用遗传算法来选择多目标函数的加权因子。在一个应用中，可以使用经过训练的模型来响应于套管孔日志数据的输入来产生合成的开孔日志。

6. 发明申请

WO2008016717A2 WELL CONTROL SYSTEMS AND ASSOCIATED METHODS 审中-公开
标题翻译：井控系统及相关方法
公开(公告)号：WO2008016717A2
公开(公告)日：2008-02-07
申请号：PCT/US2007060001
申请日：2007-01-01
申请人： HALLIBURTON ENERGY SERV INC , SHAYEGI SARA , GODFREY CRAIG , CHEN DINGDING , SCHULTZ ROGER L
发明人： SHAYEGI SARA , GODFREY CRAIG , CHEN DINGDING , SCHULTZ ROGER L
IPC分类号： G05B13/02
CPC分类号： G05B13/048 , E21B2041/0028
摘要： Well control systems and associated methods- A well control method includes the steps of drilling a wellbore and predicting a change in flow between the wellbore and a reservoir prior to the change occurring, the predicting step being performed, and the change in flow occurring while drilling. Another well control method includes the steps of : sensing at least one first drilling operation variable while drilling a wellbore, thereby generating first sensed variables; sensing at least one second drilling operation variable while drilling the wellbore, thereby generating second sensed variables; and training a predictive device, using the first and second sensed variables, to predict the second drilling operation variable at a selected time.
摘要翻译：井控制系统和相关方法 - 井控制方法包括以下步骤：在更换发生之前，钻井井眼和预测井筒与储层之间的流量变化，执行预测步骤以及钻井时发生的流量变化。另一井井控制方法包括以下步骤：在钻井井时检测至少一个第一钻井作业变量，从而产生第一感测变量; 在钻井时感测至少一个第二钻探操作变量，由此产生第二感测变量; 以及训练使用所述第一和第二感测变量的预测装置在选定的时间预测所述第二钻井操作变量。

7. 发明公开

EP2310880A4 SYSTEMS AND METHODS EMPLOYING COOPERATIVE OPTIMIZATION-BASED DIMENSIONALITY REDUCTION 有权
标题翻译：系统和方法协作优化基于维度
公开(公告)号：EP2310880A4
公开(公告)日：2014-12-17
申请号：EP09805505
申请日：2009-08-05
申请人： HALLIBURTON ENERGY SERV INC
发明人： CHEN DINGDING , HAMID SYED , DIX MICHAEL C
IPC分类号： G01V1/34 , G06N3/12
CPC分类号： G01V1/34 , G06N3/126 , G06T11/206

8. 发明申请

WO2007001731A3 ENSEMBLES OF NEURAL NETWORKS WITH DIFFERENT INPUT SETS 审中-公开
标题翻译：具有不同输入集的神经网络的识别
公开(公告)号：WO2007001731A3
公开(公告)日：2009-06-11
申请号：PCT/US2006021158
申请日：2006-06-01
申请人： HALLIBURTON ENERGY SERV INC , SMITH HARRY D , CHEN DINGDING , QUIREIN JOHN A , HAMID SYED , GRABLE JEFFERY L
发明人： SMITH HARRY D , CHEN DINGDING , QUIREIN JOHN A , HAMID SYED , GRABLE JEFFERY L
IPC分类号： G06F15/18 , G06E1/00
CPC分类号： G06N3/0454 , G06N3/086
摘要： Methods of creating and using robust neural network ensembles are disclosed. Some embodiments take the form of computer-based methods that comprise receiving a set of available inputs; receiving training data; training at least one neural network for each of at least two different subsets of the set of available inputs; and providing at least two trained neural networks having different subsets of the available inputs as components of a neural network ensemble configured to transform the available inputs into at least one output. The neural network ensemble may be applied as a log synthesis method that comprises: receiving a set of downhole logs; applying a first subset of downhole logs to a first neural network to obtain an estimated log; applying a second, different subset of the downhole logs to a second neural network to obtain an estimated log; and combining the estimated logs to obtain a synthetic log.
摘要翻译：公开了创建和使用鲁棒神经网络集合的方法。一些实施例采用基于计算机的方法的形式，其包括接收一组可用输入; 接收培训数据; 为所述一组可用输入中的至少两个不同子集中的每一个训练至少一个神经网络; 以及提供至少两个经训练的神经网络，其具有可用输入的不同子集，作为被配置为将可用输入转换成至少一个输出的神经网络集合的组件。神经网络集合可以作为对数合成方法应用，包括：接收一组井下测井; 将第一个井下日志子集应用于第一神经网络以获得估计的对数; 将第二个不同的井下日志子集应用于第二神经网络以获得估计的对数; 并组合估计的日志以获得合成日志。

9. 发明申请

WO2007002693A3 WELL LOGGING WITH REDUCED USAGE OF RADIOISOTOPIC SOURCES 审中-公开
标题翻译：以减少放射性同位素来源的使用进行测井
公开(公告)号：WO2007002693A3
公开(公告)日：2007-05-10
申请号：PCT/US2006025029
申请日：2006-06-26
申请人： HALLIBURTON ENERGY SERV INC , SMITH HARRY D JR , QUIREIN JOHN A , GRABLE JEFFERY L , CHEN DINGDING
发明人： SMITH HARRY D JR , QUIREIN JOHN A , GRABLE JEFFERY L , CHEN DINGDING
IPC分类号： G06N3/02 , G01V5/04
CPC分类号： G06N3/086 , G06N3/0454
摘要： Logging systems and methods are disclosed to reduce usage of radioisotopic sources. Some embodiments comprise collecting at least one output log of a training well bore from measurements with a radioisotopic source; collecting at least one input log of the training well bore from measurements by a non-radioisotopic logging tool; training a neural network to predict the output log from the at least one input log; collecting at least one input log of a development well bore from measurements by the non-radioisotopic logging tool; and processing the at least one input log of the development well bore to synthesize at least one output log of the development well bore. The output logs may include formation density and neutron porosity logs.
摘要翻译：记录系统和方法被公开以减少放射性同位素源的使用。一些实施例包括：利用放射性同位素源从测量结果收集训练井孔的至少一个输出记录; 通过非放射性同位素测井工具的测量收集训练井筒的至少一个输入日志; 训练神经网络以预测来自至少一个输入日志的输出日志; 从非放射性同位素测井工具的测量结果收集开发井孔的至少一个输入测井; 以及处理所述开发井筒的所述至少一个输入测井以合成所述开发井筒的至少一个输出测井。输出测井可能包括地层密度和中子孔隙度测井。

10. 发明申请

WO2007002693A8 WELL LOGGING WITH REDUCED USAGE OF RADIOISOTOPIC SOURCES 审中-公开
标题翻译：良好的记录，减少使用无线电源
公开(公告)号：WO2007002693A8
公开(公告)日：2007-03-22
申请号：PCT/US2006025029
申请日：2006-06-26
申请人： HALLIBURTON ENERGY SERV INC , SMITH HARRY D JR , QUIREIN JOHN A , GRABLE JEFFERY L , CHEN DINGDING
发明人： SMITH HARRY D JR , QUIREIN JOHN A , GRABLE JEFFERY L , CHEN DINGDING
IPC分类号： G06N3/02
CPC分类号： G06N3/086 , G06N3/0454
摘要： Logging systems and methods are disclosed to reduce usage of radioisotopic sources. Some embodiments comprise collecting at least one output log of a training well bore from measurements with a radioisotopic source; collecting at least one input log of the training well bore from measurements by a non-radioisotopic logging tool; training a neural network to predict the output log from the at least one input log; collecting at least one input log of a development well bore from measurements by the non-radioisotopic logging tool; and processing the at least one input log of the development well bore to synthesize at least one output log of the development well bore. The output logs may include formation density and neutron porosity logs.
摘要翻译：公开了记录系统和方法以减少放射性同位素源的使用。一些实施例包括从具有放射性同位素源的测量中收集训练井的至少一个输出日志; 从非放射性同位素测井工具的测量中收集训练井的至少一个输入日志; 训练神经网络以从至少一个输入日志预测输出日志; 从非放射性同位素测井工具的测量中收集开发井眼的至少一个输入日志; 以及处理所述开发井的所述至少一个输入对数以合成所述显影井的至少一个输出对数。输出原木可包括地层密度和中子孔隙度日志。

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