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

US20070011114A1 Ensembles of neural networks with different input sets 有权
标题翻译：具有不同输入集的神经网络的集合
公开(公告)号：US20070011114A1
公开(公告)日：2007-01-11
申请号：US11165892
申请日：2005-06-24
申请人： Dingding Chen , John Quirein , Harry Smith , Syed Hamid , Jeffery Grable
发明人： Dingding Chen , John Quirein , Harry Smith , Syed Hamid , Jeffery Grable
IPC分类号： G06N3/02
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日志; 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。

2. 发明申请

US20070011115A1 Well logging with reduced usage of radioisotopic sources 有权
标题翻译：测井记录减少放射性同位素来源的使用
公开(公告)号：US20070011115A1
公开(公告)日：2007-01-11
申请号：US11270284
申请日：2005-11-09
申请人： Harry Smith , John Quirein , Jeffery Grable , Dingding Chen
发明人： Harry Smith , John Quirein , Jeffery Grable , Dingding Chen
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。

3. 发明申请

US20070124079A1 Method of reservoir characterization and delineation based on observations of displacements at the earth's surface 有权
标题翻译：基于地球表面位移观测的储层表征和描绘方法
公开(公告)号：US20070124079A1
公开(公告)日：2007-05-31
申请号：US11288826
申请日：2005-11-29
申请人： Ali Mese , Syed Hamid , Dingding Chen , Harry Smith , John Howard , Neal Skinner
发明人： Ali Mese , Syed Hamid , Dingding Chen , Harry Smith , John Howard , Neal Skinner
IPC分类号： G01N15/08 , G01V1/40
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。

4. 发明申请

US20050246297A1 Genetic algorithm based selection of neural network ensemble for processing well logging data 有权
标题翻译：基于遗传算法的神经网络集合选择，用于处理测井数据
公开(公告)号：US20050246297A1
公开(公告)日：2005-11-03
申请号：US10811403
申请日：2004-03-26
申请人： Dingding Chen , Syed Hamid , Harry Smith
发明人： Dingding Chen , Syed Hamid , Harry Smith
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。

5. 发明授权

US08355873B2 Method of reservoir characterization and delineation based on observations of displacements at the earth's surface 有权
标题翻译：基于地球表面位移观测的储层表征和描绘方法
公开(公告)号：US08355873B2
公开(公告)日：2013-01-15
申请号：US11288826
申请日：2005-11-29
申请人： Ali Mese , Syed Hamid , Dingding Chen , Harry D. Smith, Jr. , John Howard , Neal Skinner
发明人： Ali Mese , Syed Hamid , Dingding Chen , Harry D. Smith, Jr. , John Howard , Neal Skinner
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。

6. 发明授权

US08374974B2 Neural network training data selection using memory reduced cluster analysis for field model development 失效
标题翻译：使用内存的神经网络训练数据选择降低了现场模型开发的聚类分析
公开(公告)号：US08374974B2
公开(公告)日：2013-02-12
申请号：US10393641
申请日：2003-03-21
申请人： Dingding Chen , John A. Quirein , Jacky M. Wiener , Jeffery L. Grable , Syed Hamid , Harry D. Smith, Jr.
发明人： Dingding Chen , John A. Quirein , Jacky M. Wiener , Jeffery L. Grable , Syed Hamid , Harry D. Smith, Jr.
IPC分类号： G06F15/18 , G06G7/00
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. Actual target data from the training well is linked to the clusters. The linked clusters are analyzed for variance, etc. and fuzzy inference is used to select a portion of each cluster 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。来自训练井的实际目标数据与集群有关。对链接的聚类进行方差分析等，并使用模糊推理来选择每个聚类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。

7. 发明申请

US20120109604A1 Estimating Mineral Content Using Geochemical Data 审中-公开
标题翻译：使用地球化学数据估算矿物含量
公开(公告)号：US20120109604A1
公开(公告)日：2012-05-03
申请号：US13381555
申请日：2009-08-27
申请人： Dingding Chen , Syed Hamid , Michael Charles Dix
发明人： Dingding Chen , Syed Hamid , Michael Charles Dix
IPC分类号： G06F7/60
CPC分类号： G01V11/00
摘要： A model is disclosed that includes an intelligent ligent linear programming (“ILP”) member to produce a ILP result, a member selected from the group consisting of a feed-forward neural network (“FNN”) to produce a FNN result and a geochemical normative analysis (“GNA”) model to produce a GNA result. The model also includes a result generator to combine the ILP result with the result from the other member to produce the estimates of the mineral content of the sample.
摘要翻译：公开了一种包括智能连线性规划（“ILP”）构件以产生ILP结果的模型，选自前馈神经网络（“FNN”）的成员以产生FNN结果和地球化学规范分析（“GNA”）模型来产生GNA结果。该模型还包括结果发生器，将ILP结果与其他成员的结果相结合，以产生样品的矿物质含量的估计值。

8. 发明授权

US07280987B2 Genetic algorithm based selection of neural network ensemble for processing well logging data 有权
标题翻译：基于遗传算法的神经网络集合选择，用于处理测井数据
公开(公告)号：US07280987B2
公开(公告)日：2007-10-09
申请号：US10811403
申请日：2004-03-26
申请人： Dingding Chen , Syed Hamid , Harry D. Smith, Jr.
发明人： Dingding Chen , Syed Hamid , Harry D. Smith, Jr.
IPC分类号： G06E1/00
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。

9. 发明申请

US20080228680A1 Neural-Network Based Surrogate Model Construction Methods and Applications Thereof 有权
标题翻译：基于神经网络的代理模型构建方法及应用
公开(公告)号：US20080228680A1
公开(公告)日：2008-09-18
申请号：US12048045
申请日：2008-03-13
申请人： Dingding Chen , Allan Zhong , Syed Hamid , Stanley Stephenson
发明人： Dingding Chen , Allan Zhong , Syed Hamid , Stanley Stephenson
IPC分类号： G06F15/18
CPC分类号： G06N3/0454 , B33Y80/00
摘要： Various neural-network based surrogate model construction methods are disclosed herein, along with various applications of such models. Designed for use when only a sparse amount of data is available (a “sparse data condition”), some embodiments of the disclosed systems and methods: create a pool of neural networks trained on a first portion of a sparse data set; generate for each of various multi-objective functions a set of neural network ensembles that minimize the multi-objective function; select a local ensemble from each set of ensembles based on data not included in said first portion of said sparse data set; and combine a subset of the local ensembles to form a global ensemble. This approach enables usage of larger candidate pools, multi-stage validation, and a comprehensive performance measure that provides more robust predictions in the voids of parameter space.
摘要翻译：本文公开了各种基于神经网络的替代模型构建方法，以及这些模型的各种应用。设计为仅在少量数据可用时使用（“稀疏数据条件”），所公开的系统和方法的一些实施例：创建在稀疏数据集的第一部分上训练的神经网络池; 为各种多目标函数中的每一个生成一组最小化多目标函数的神经网络集合; 基于不包括在所述稀疏数据集的所述第一部分中的数据，从每组集合中选择本地集合; 并组合一个本地组合的子集以形成全局集合。这种方法使得可以使用更大的候选池，多级验证以及综合性能测量，从而在参数空间的空白中提供更强大的预测。

10. 发明授权

US09514388B2 Systems and methods employing cooperative optimization-based dimensionality reduction 有权
标题翻译：采用基于协同优化的维数降低的系统和方法
公开(公告)号：US09514388B2
公开(公告)日：2016-12-06
申请号：US12190418
申请日：2008-08-12
申请人： Dingding Chen , Syed Hamid , Michael C. Dix
发明人： Dingding Chen , Syed Hamid , Michael C. Dix
IPC分类号： G06K9/62 , G06N3/08
CPC分类号： E21B47/12 , E21B49/08 , E21B2049/085 , G06K9/6229 , G06K9/6248 , G06N3/08 , G06N3/086
摘要： Dimensionality reduction systems and methods facilitate visualization, understanding, and interpretation of high-dimensionality data sets, so long as the essential information of the data set is preserved during the dimensionality reduction process. In some of the disclosed embodiments, dimensionality reduction is accomplished using clustering, evolutionary computation of low-dimensionality coordinates for cluster kernels, particle swarm optimization of kernel positions, and training of neural networks based on the kernel mapping. The fitness function chosen for the evolutionary computation and particle swarm optimization is designed to preserve kernel distances and any other information deemed useful to the current application of the disclosed techniques, such as linear correlation with a variable that is to be predicted from future measurements. Various error measures are suitable and can be used.
摘要翻译：只要在维度降低过程中保留数据集的基本信息，尺寸减小系统和方法便于高维数据集的可视化，理解和解释。在一些所公开的实施例中，使用聚类，集群内核的低维度坐标的进化计算，核心位置的粒子群优化以及基于内核映射的神经网络的训练来实现维数降低。为进化计算和粒子群优化选择的适应度函数被设计为保留核心距离以及被认为对所公开技术的当前应用有用的任何其它信息，例如与将来的测量将要预测的变量的线性相关。各种错误措施是合适的，可以使用。

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