公开(公告)号：US20140110167A1

公开(公告)日：2014-04-24

申请号：US13883822

申请日：2012-10-26

申请人： Thomas Goebel ,  Roberto Valerio Molina ,  Ricardo Vilalta ,  Kinjal Dhar Gupta

发明人： Thomas Goebel ,  Roberto Valerio Molina ,  Ricardo Vilalta ,  Kinjal Dhar Gupta

IPC分类号： E21B41/00 ,  G06N99/00 ,  G06N3/08 ,  E21B44/00

CPC分类号： E21B41/0092 ,  E21B44/00 ,  G06K9/6292 ,  G06N3/08 ,  G06N99/005

摘要： Predicting a drill string stuck pipe event. At least some of the illustrative embodiments are methods including: receiving a plurality of drilling parameters from a drilling operation; applying the plurality of drilling parameters to an ensemble prediction model comprising at least three machine-learning algorithms operated in parallel, each machine-learning algorithm predicting a probability of occurrence of a future stuck pipe event based on at least one of the plurality of drilling parameters, the ensemble prediction model creates a combined probability based on the probability of occurrence of the future stuck pipe event of each machine-learning algorithm; and providing an indication of a likelihood of a future stuck pipe event to a drilling operator, the indication based on the combined probability.

摘要翻译： 预测钻柱卡住管道事件。 至少一些说明性实施例是一种方法，包括：从钻井操作接收多个钻孔参数; 将所述多个钻孔参数应用于包括并行操作的至少三个机器学习算法的整体预测模型，每个机器学习算法基于所述多个钻孔参数中的至少一个来预测未来卡箍管事件的发生概率 综合预测模型基于每个机器学习算法的未来卡通管道事件的发生概率创建组合概率; 并且向钻井操作者提供未来卡住管道事件的可能性的指示，基于组合概率的指示。

公开(公告)号：US08752648B2

公开(公告)日：2014-06-17

申请号：US13883822

申请日：2012-10-26

申请人： Thomas Goebel ,  Roberto Valerio Molina ,  Ricardo Vilalta ,  Kinjal Dhar Gupta

发明人： Thomas Goebel ,  Roberto Valerio Molina ,  Ricardo Vilalta ,  Kinjal Dhar Gupta

IPC分类号： E21B45/00 ,  E21B44/00 ,  G06N3/08 ,  E21B41/00 ,  G06N99/00

CPC分类号： E21B41/0092 ,  E21B44/00 ,  G06K9/6292 ,  G06N3/08 ,  G06N99/005

摘要： Predicting a drill string stuck pipe event. At least some of the illustrative embodiments are methods including: receiving a plurality of drilling parameters from a drilling operation; applying the plurality of drilling parameters to an ensemble prediction model comprising at least three machine-learning algorithms operated in parallel, each machine-learning algorithm predicting a probability of occurrence of a future stuck pipe event based on at least one of the plurality of drilling parameters, the ensemble prediction model creates a combined probability based on the probability of occurrence of the future stuck pipe event of each machine-learning algorithm; and providing an indication of a likelihood of a future stuck pipe event to a drilling operator, the indication based on the combined probability.

摘要翻译： 预测钻柱卡住管道事件。 至少一些说明性实施例是一种方法，包括：从钻井操作接收多个钻孔参数; 将所述多个钻孔参数应用于包括并行操作的至少三个机器学习算法的整体预测模型，每个机器学习算法基于所述多个钻孔参数中的至少一个来预测未来卡箍管事件的发生概率 综合预测模型基于每个机器学习算法的未来卡通管道事件的发生概率创建组合概率; 并且向钻井操作者提供未来卡住管道事件的可能性的指示，基于组合概率的指示。

公开(公告)号：US07987144B1

公开(公告)日：2011-07-26

申请号：US09713342

申请日：2000-11-14

申请人： Youssef Drissi ,  Ricardo Vilalta

发明人： Youssef Drissi ,  Ricardo Vilalta

IPC分类号： G06N5/00

CPC分类号： G06N99/005 ,  G06K9/6267

摘要： A data classification method and apparatus are disclosed for labeling unknown objects. The disclosed data classification system employs a learning algorithm that adapts through experience. The present invention classifies objects in domain datasets using data classification models having a corresponding bias and evaluates the performance of the data classification. The performance values for each domain dataset and corresponding model bias are processed to identify or modify one or more rules of experience. The rules of experience are subsequently used to generate a model for data classification. Each rule of experience specifies one or more characteristics for a domain dataset and a corresponding bias that should be utilized for a data classification model if the rule is satisfied. The present invention dynamically modifies the assumptions (bias) of the learning algorithm to improve the assumptions embodied in the generated models and thereby improve the quality of the data classification and regression systems that employ such models. The disclosed self-adaptive learning process will become increasingly more accurate as the rules of experience are accumulated over time.

摘要翻译： 公开了一种用于标记未知物体的数据分类方法和装置。 所公开的数据分类系统采用适应经验的学习算法。 本发明使用具有相应偏差的数据分类模型对领域数据集中的对象进行分类，并评估数据分类的性能。 处理每个域数据集的性能值和对应的模型偏差以识别或修改一个或多个经验规则。 随后，经验规则用于生成数据分类模型。 每个经验规则指定一个域数据集的一个或多个特征以及如果该规则得到满足，应该用于数据分类模型的相应偏倚。 本发明动态地修改学习算法的假设（偏差），以改进所产生模型中体现的假设，从而提高采用这种模型的数据分类和回归系统的质量。 随着时间的推移，随着经验规则的积累，公开的自适应学习过程将变得越来越准确。

公开(公告)号：US06728689B1

公开(公告)日：2004-04-27

申请号：US09713341

申请日：2000-11-14

申请人： Youssef Drissi ,  Ricardo Vilalta

发明人： Youssef Drissi ,  Ricardo Vilalta

IPC分类号： G06E100

CPC分类号： G06K9/6262 ,  G06K9/6253 ,  G06N99/005

摘要： A data classification method and apparatus are disclosed for labeling unknown objects. The disclosed data classification system employs a learning algorithm that adapts through experience. The present invention classifies objects in domain datasets using data classification models having a corresponding bias and evaluates the performance of the data classification. The performance values for each domain dataset and corresponding model bias are processed to identify or modify one or more rules of experience. The rules of experience are subsequently used to generate a model for data classification. Each rule of experience specifies one or more characteristics for a domain dataset and a corresponding bias that should be utilized for a data classification model if the rule is satisfied. The present invention dynamically modifies the assumptions (bias) of the learning algorithm to improve the assumptions embodied in the generated models and thereby improve the quality of the data classification and regression systems that employ such models. A dynamic bias may be employed in the meta-learning algorithm by utilizing two self-adaptive learning algorithms. In a first function, each self-adaptive learning algorithm generates models used for data classification. In a second function, each self-adaptive learning algorithm serves as an adaptive meta-learner for the other adaptive learning algorithm.

摘要翻译： 公开了一种用于标记未知物体的数据分类方法和装置。 所公开的数据分类系统采用适应经验的学习算法。 本发明使用具有相应偏差的数据分类模型对领域数据集中的对象进行分类，并评估数据分类的性能。 处理每个域数据集的性能值和对应的模型偏差以识别或修改一个或多个经验规则。 随后，经验规则用于生成数据分类模型。 每个经验规则指定一个域数据集的一个或多个特征以及如果该规则得到满足，应该用于数据分类模型的相应偏倚。 本发明动态地修改学习算法的假设（偏差），以改进所产生模型中体现的假设，从而提高采用这种模型的数据分类和回归系统的质量。 通过利用两种自适应学习算法，可以在元学习算法中采用动态偏差。 在第一个功能中，每个自适应学习算法生成用于数据分类的模型。 在第二个功能中，每个自适应学习算法作为另一种自适应学习算法的自适应元学习者。

公开(公告)号：US07143085B2

公开(公告)日：2006-11-28

申请号：US10209619

申请日：2002-07-31

申请人： Gregory T. Brown ,  Youssef Drissi ,  Moon Ju Kim ,  Lev Kozakov ,  Juan Leon-Rodriquez ,  Ricardo Vilalta

发明人： Gregory T. Brown ,  Youssef Drissi ,  Moon Ju Kim ,  Lev Kozakov ,  Juan Leon-Rodriquez ,  Ricardo Vilalta

IPC分类号： G06F7/00

CPC分类号： G06F17/30864 ,  G06F17/30657 ,  Y10S707/99931 ,  Y10S707/99932 ,  Y10S707/99933 ,  Y10S707/99936 ,  Y10S707/99937

摘要： Euclidean analysis is used to define queries in terms of a multi-axis query space where each of the keywords T1, T2, . . . Ti, . . . Tn is assigned an axis in that space. Sets of test queries St for each one from one of a plurality of server sources, are plotted in the query space. Clusters of the search terms are identified based on the proximity of the plotted query vectors to one another. Predominant servers are identified for each of the clusters. When a search query Ss is received, the location of its vector is determined and the servers accessed by the search query Ss are those that are predominant in the cluster which its vector may fall or is in closest proximity to.

摘要翻译： 欧几里德分析用于根据多轴查询空间来定义查询，其中每个关键字T 1，T 2，...。 。 。 。。。。。。。。。。。。 。 。 在该空间中分配了一个轴。 在多个服务器源中的一个服务器源中的每​​一个的测试查询集合被绘制在查询空间中。 基于绘制的查询向量彼此的邻近度来识别搜索项的群集。 为每个集群标识主要服务器。 当接收到搜索查询S 时，确定其向量的位置，并且由搜索查询S 访问的服务器是在群集中占主导地位的那些 矢量可能会下降或最接近。

公开(公告)号：US06842751B1

公开(公告)日：2005-01-11

申请号：US09629086

申请日：2000-07-31

申请人： Ricardo Vilalta ,  Irina Rish

发明人： Ricardo Vilalta ,  Irina Rish

IPC分类号： G06F17/30

CPC分类号： G06F2216/03 ,  Y10S707/99936 ,  Y10S707/99943 ,  Y10S707/99945

摘要： A data classification method and apparatus are disclosed for labeling unknown objects. The disclosed data classification system employs a model selection technique that characterizes domains and identifies the degree of match between the domain meta-features and the learning bias of the algorithm under analysis. An improved concept variation meta-feature or an average weighted distance meta-feature, or both, are used to fully discriminate learning performance, as well as conventional meta-features. The “concept variation” meta-feature measures the amount of concept variation or the degree of lack of structure of a concept. The present invention extends conventional notions of concept variation to allow for numeric and categorical features, and estimates the variation of the whole example population through a training sample. The “average weighted distance” meta-feature of the present invention measures the density of the distribution in the training set. While the concept variation meta-feature is high for a training set comprised of only two examples having different class labels, the average weighted distance can distinguish between examples that are too far apart or too close to one other.

摘要翻译： 公开了一种用于标记未知物体的数据分类方法和装置。 所公开的数据分类系统采用模型选择技术来表征域，并且识别域元特征与分析算法的学习偏差之间的匹配程度。 使用改进的概念变异元特征或平均加权距离元特征或两者来完全区分学习性能以及常规元特征。 “概念变化”元特征测量概念变化的数量或概念的结构缺乏程度。 本发明扩展了概念变化的常规概念以允许数字和分类特征，并且通过训练样本来估计整个示例群体的变化。 本发明的“平均加权距离”元特征测量训练集中分布的密度。 虽然对于由仅具有不同类别标签的两个示例组成的训练集，概念变体元特征是高的，但是平均加权距离可以区分彼此太远或太接近的示例。