-
1.发明申请Use of Sequential Clustering for Instance Selection in Machine Condition Monitoring 失效在机器状态监测中使用顺序聚类实例选择公开(公告)号：US20090043536A1
公开(公告)日：2009-02-12
申请号：US12048381
申请日：2008-03-14
申请人： Christian Balderer , Claus Neubauer , Chao Yuan
发明人： Christian Balderer , Claus Neubauer , Chao Yuan
CPC分类号： G05B17/02 , G05B23/0248 , G06K9/622 , G06K9/6256
摘要： A method is provided for selecting a representative set of training data for training a statistical model in a machine condition monitoring system. The method reduces the time required to choose representative samples from a large data set by using a nearest-neighbor sequential clustering technique in combination with a kd-tree. A distance threshold is used to limit the geometric size the clusters. Each node of the kd-tree is assigned a representative sample from the training data, and similar samples are subsequently discarded.
摘要翻译： 提供了一种用于在机器状态监视系统中选择用于训练统计模型的代表性训练数据集合的方法。 该方法通过使用最近邻序列聚类技术与kd-tree结合来减少从大数据集中选择代表性样本所需的时间。 距离阈值用于限制集群的几何尺寸。 从训练数据中分配kd-tree的每个节点代表性样本，随后丢弃类似的样本。
-
公开(公告)号：US07769561B2
公开(公告)日：2010-08-03
申请号：US11563396
申请日：2006-11-27
申请人： Chao Yuan , Christian Balderer , Tzu-Kuo Huang , Claus Neubauer
发明人： Chao Yuan , Christian Balderer , Tzu-Kuo Huang , Claus Neubauer
IPC分类号： G06F17/18
CPC分类号： G05B19/4065 , G05B23/024 , G05B2219/37508
摘要： A method for monitoring machine conditions is based on machine learning through the use of a statistical model. A correlation coefficient is calculated using weights assigned to each sample that indicate the likelihood that that sample is an outlier. The resulting correlation coefficient is more robust against outliers. The calculation of the weight is based on the Mahalanobis distance from the sample to the sample mean. Additionally, hierarchical clustering is applied to intuitively reveal group information among sensors. By specifying a similarity threshold, the user can easily obtain desired clustering results.
摘要翻译： 用于监测机器状况的方法是基于通过使用统计模型的机器学习。 使用分配给每个样本的权重来计算相关系数，指示该样本是异常值的可能性。 所得到的相关系数对异常值更强。 重量的计算基于从样品到样品平均值的马氏距离。 另外，应用层次聚类来直观地显示传感器之间的组信息。 通过指定相似性阈值，用户可以容易地获得所需的聚类结果。
-
3.发明授权Use of sequential nearest neighbor clustering for instance selection in machine condition monitoring 失效在机器状态监测中使用顺序最近邻群集实例选择公开(公告)号：US07716152B2
公开(公告)日：2010-05-11
申请号：US12048381
申请日：2008-03-14
申请人： Christian Balderer , Claus Neubauer , Chao Yuan
发明人： Christian Balderer , Claus Neubauer , Chao Yuan
IPC分类号： G06N5/00
CPC分类号： G05B17/02 , G05B23/0248 , G06K9/622 , G06K9/6256
摘要： A method is provided for selecting a representative set of training data for training a statistical model in a machine condition monitoring system. The method reduces the time required to choose representative samples from a large data set by using a nearest-neighbor sequential clustering technique in combination with a kd-tree. A distance threshold is used to limit the geometric size the clusters. Each node of the kd-tree is assigned a representative sample from the training data, and similar samples are subsequently discarded.
摘要翻译： 提供了一种用于在机器状态监视系统中选择用于训练统计模型的代表性训练数据集合的方法。 该方法通过使用最近邻序列聚类技术与kd-tree结合来减少从大数据集中选择代表性样本所需的时间。 距离阈值用于限制集群的几何尺寸。 从训练数据中分配kd-tree的每个节点代表性样本，随后丢弃类似的样本。
-
公开(公告)号：US20070162241A1
公开(公告)日：2007-07-12
申请号：US11563396
申请日：2006-11-27
申请人： Chao Yuan , Christian Balderer , Tzu-Kuo Huang , Claus Neubauer
发明人： Chao Yuan , Christian Balderer , Tzu-Kuo Huang , Claus Neubauer
IPC分类号： G01N37/00
CPC分类号： G05B19/4065 , G05B23/024 , G05B2219/37508
摘要： A method for monitoring machine conditions is based on machine learning through the use of a statistical model. A correlation coefficient is calculated using weights assigned to each sample that indicate the likelihood that that sample is an outlier. The resulting correlation coefficient is more robust against outliers. The calculation of the weight is based on the Mahalanobis distance from the sample to the sample mean. Additionally, hierarchical clustering is applied to intuitively reveal group information among sensors. By specifying a similarity threshold, the user can easily obtain desired clustering results.
摘要翻译： 用于监测机器状况的方法是基于通过使用统计模型的机器学习。 使用分配给每个样本的权重来计算相关系数，指示该样本是异常值的可能性。 所得到的相关系数对异常值更强。 重量的计算基于从样品到样品平均值的马氏距离。 另外，应用层次聚类来直观地显示传感器之间的组信息。 通过指定相似性阈值，用户可以容易地获得所需的聚类结果。
-
-
-
搜索结果
4 条记录 (耗时 0.014 秒)
