公开(公告)号：US08868985B2

公开(公告)日：2014-10-21

申请号：US13394919

申请日：2010-09-13

申请人： Holger Hackstein ,  Claus Neubauer ,  Chao Yuan

发明人： Holger Hackstein ,  Claus Neubauer ,  Chao Yuan

IPC分类号： G06F11/00 ,  G05B23/02

CPC分类号： G05B23/0229 ,  G05B23/024 ,  G05B23/0283

摘要： A machine fault diagnosis system is provided. The system combines a rule-based predictive maintenance strategy with a machine learning system. A simple set of rules defined manually by human experts is used to generate artificial training feature vectors to portray machine fault conditions for which only a few real data points are available. Those artificial training feature vectors are combined with real training feature vectors and the combined set is used to train a supervised pattern recognition algorithm such as support vector machines. The resulting decision boundary closely approximates the underlying real separation boundary between the fault and normal conditions.

摘要翻译： 提供机器故障诊断系统。 该系统将基于规则的预测维护策略与机器学习系统相结合。 人类专家手动定义的一套简单的规则用于生成人工训练特征向量，以描绘只有少数实际数据点可用的机器故障条件。 将这些人工训练特征向量与真实训练特征向量相结合，组合集合用于训练支持向量机等监督模式识别算法。 所得到的决策边界与故障和正常条件之间的基本实际分离边界紧密相近。

公开(公告)号：US08744807B2

公开(公告)日：2014-06-03

申请号：US12781890

申请日：2010-05-18

申请人： Mathaeus Dejori ,  Ciprian Raileanu ,  Nazif Cihan Tas ,  Claus Neubauer

发明人： Mathaeus Dejori ,  Ciprian Raileanu ,  Nazif Cihan Tas ,  Claus Neubauer

IPC分类号： G06F17/40 ,  G06F11/34 ,  G06F9/445 ,  G01D9/00

CPC分类号： G06F11/3476 ,  G01D9/005 ,  G06F9/44526

摘要： In a framework for acquiring and analyzing data from a network of sensors, plug-in software interfaces are used to provide scalability and flexibility. Data collection set-up data is exchanged through one or more first plug-in software interfaces with data collection devices, to configure the processor to collect measurement data from the data collection devices. Analysis set-up data is exchanged through one or more second plug-in software interfaces with one or more data analysis software packages, to configure the processor to provide a predefined subset of the measurement data to the data analysis software packages and to accept analysis results from the data analysis software packages. Measurement data and analysis results are subsequently exchanged through the plug-in interfaces.

摘要翻译： 在用于从传感器网络获取和分析数据的框架中，使用插件软件接口来提供可扩展性和灵活性。 数据收集设置数据通过与数据采集设备的一个或多个第一插件软件接口进行交换，以配置处理器从数据采集设备收集测量数据。 分析设置数据通过一个或多个第二插件软件接口与一个或多个数据分析软件包交换，以配置处理器向数据分析软件包提供测量数据的预定义子集并接受分析结果 从数据分析软件包中。 随后通过插件接口交换测量数据和分析结果。

公开(公告)号：US08200592B2

公开(公告)日：2012-06-12

申请号：US11668676

申请日：2007-01-30

申请人： Klaus Brinker ,  Claus Neubauer

发明人： Klaus Brinker ,  Claus Neubauer

IPC分类号： G06N5/00

CPC分类号： G05B13/048 ,  G05B23/0245

摘要： The present invention provides methods and apparatus for determining and utilizing detection models, such as models for machine condition monitoring. Specifically, the present invention provides a method for identifying and prioritizing labeled data. The model allows a monitored system to be associated with a calibrated and ordered set of states. Further, in machine condition monitoring, the machine condition is associated with the entire set of states in a particular order with a relevance zero-point. That is, a ranked set of calibrated data describing machine conditions is augmented with an annotation indicating a cut-off between relevant and non-relevant data.

摘要翻译： 本发明提供了用于确定和利用检测模型的方法和装置，例如用于机器状态监测的模型。 具体地，本发明提供了一种用于识别和标记数据的优先级的方法。 该模型允许被监视的系统与校准的和有序的状态集相关联。 此外，在机器状态监视中，机器状态与具有相关性零点的特定顺序的整个状态集相关联。 也就是说，描述机器状况的一系列校准数据被增加，其中注释指示相关数据和非相关数据之间的截止。

公开(公告)号：US07949497B2

公开(公告)日：2011-05-24

申请号：US12077255

申请日：2008-03-18

申请人： Chao Yuan ,  Claus Neubauer

发明人： Chao Yuan ,  Claus Neubauer

IPC分类号： G06F11/30

CPC分类号： G05B23/0232

摘要： Condition signals of machines are observed and one or more discontinuities are detected in the condition signals. The discontinuities in the condition signals are compensated for (e.g., by applying a shifting factor to models of the signals) and trends of the compensated condition signals are determined. The trends are used to predict future fault conditions in machines. Kalman filters comprising observation models and evolution models are used to determine the trends. Discontinuity in observed signals is detected using hypothesis testing.

摘要翻译： 观察机器的状态信号，并在条件信号中检测到一个或多个不连续性。 条件信号中的不连续性被补偿（例如，通过将移位因子应用于信号的模型），并且确定补偿状态信号的趋势。 趋势用于预测机器中未来的故障状况。 包含观察模型和进化模型的卡尔曼滤波被用于确定趋势。 使用假设检验检测观察信号的不连续性。

公开(公告)号：US07797265B2

公开(公告)日：2010-09-14

申请号：US12072179

申请日：2008-02-25

申请人： Klaus Brinker ,  Fabian Moerchen ,  Bernhard Glomann ,  Claus Neubauer

发明人： Klaus Brinker ,  Fabian Moerchen ,  Bernhard Glomann ,  Claus Neubauer

IPC分类号： G06N5/00

CPC分类号： G06F17/30707

摘要： Documents from a data stream are clustered by first generating a feature vector for each document. A set of cluster centroids (e.g., feature vectors of their corresponding clusters) are retrieved from a memory based on the feature vector of the document using a locality sensitive hashing function. The centroids may be retrieved by retrieving a set of cluster identifiers from a cluster table, the cluster identifiers each indicative of a respective cluster centroid, and retrieving the cluster centroids corresponding to the retrieved cluster identifiers from a memory. Documents may then be clustered into one or more of the candidate clusters using distance measures from the feature vector of the document to the cluster centroids.

摘要翻译： 通过首先为每个文档生成特征向量来聚集来自数据流的文档。 基于使用位置敏感散列函数的文档的特征向量，从存储器检索集合中心集合（例如，其对应的集群的特征向量）。 可以通过从集群表中检索一组集群标识符来检索质心，每个集群标识符指示相应的集群质心，并且从存储器中检索与所检索的集群标识符相对应的集群质心。 然后可以使用从文档的特征向量到聚类中心的距离度量将文档聚类成一个或多个候选聚类。

公开(公告)号：US07567878B2

公开(公告)日：2009-07-28

申请号：US11563241

申请日：2006-11-27

申请人： Chao Yuan ,  Claus Neubauer

发明人： Chao Yuan ,  Claus Neubauer

IPC分类号： G01N37/00

CPC分类号： G05B19/4065 ,  G05B23/024 ,  G05B23/0281 ,  G05B2219/31357 ,  G05B2219/34477 ,  G06K9/6284 ,  Y02P90/14

摘要： A method for monitoring machine conditions provides additional information using a one-class classifier in which an evaluation function is learned. In the method, a distance is determined from an anomaly measurement x to a boundary of a region R1 containing all acceptable measurements. The distance is used as a measure of the extent of the anomaly. The distance is found by searching along a line from the anomaly to a closest acceptable measurement within the region R1.

摘要翻译： 用于监视机器状况的方法使用其中学习评估功能的一类分类器提供附加信息。 在该方法中，从异常测量x到包含所有可接受测量的区域R1的边界确定距离。 该距离用于测量异常的程度。 通过沿着从异常线到一个最接近的区域R1内可接受的测量的线来搜索距离。

公开(公告)号：US07457674B2

公开(公告)日：2008-11-25

申请号：US11210485

申请日：2005-08-24

申请人： Chao Yuan ,  Claus Neubauer ,  Zehra Cataltepe ,  Wesley McCorkle ,  Hans-Gerd Brummel ,  Ming Fang

发明人： Chao Yuan ,  Claus Neubauer ,  Zehra Cataltepe ,  Wesley McCorkle ,  Hans-Gerd Brummel ,  Ming Fang

IPC分类号： G05B13/02

CPC分类号： G05B17/02 ,  G05B23/0243

摘要： A system for updating a plurality of monitoring models is provided. The system includes a model association module that, for each of a plurality of monitored systems determines, an association between a particular monitored system and at least one of a plurality of estimation models. Each estimation model is based upon one of a plurality of distinct sets of estimation properties, and each set uniquely corresponds to a particular estimation model. The system also includes an updating module that updates at least one of the estimation properties and propagates the updated estimation properties to each estimation model that corresponds to a distinct set containing at least one estimation property that is updated. The system further includes a model modification module that modifies each estimation model that corresponds to a distinct set containing at least one estimation property that is updated.

摘要翻译： 提供了一种用于更新多个监视模型的系统。 该系统包括模型关联模块，对于多个被监视系统中的每一个确定特定监视系统与多个估计模型中的至少一个之间的关联。 每个估计模型基于多个不同的估计属性集合之一，并且每个估计模型唯一地对应于特定估计模型。 该系统还包括更新模块，其更新估计属性中的至少一个并且将更新的估计属性传播到对应于包含至少一个被更新的估计属性的不同集合的每个估计模型。 该系统还包括模型修改模块，其修改对应于包含至少一个被更新的估计属性的不同集合的每个估计模型。

公开(公告)号：US20080086283A1

公开(公告)日：2008-04-10

申请号：US11866535

申请日：2007-10-03

申请人： Chao Yuan ,  Claus Neubauer

发明人： Chao Yuan ,  Claus Neubauer

IPC分类号： G06F17/18

CPC分类号： G05B23/024

摘要： A method for monitoring a system includes receiving a set of training data. A Gaussian mixture model is defined to model a probability distribution for a particular sensor of the system from among a plurality of sensors of the system based on the received training data. The Gaussian mixture model includes a sum of k mixture components, where k is a positive integer. Sensor data is received from the plurality of sensors of the system. An expectation-maximization technique is performed to estimate an expected value for the particular sensor based on the defined Gaussian mixture model and the received sensor data from the plurality of sensors.

摘要翻译： 一种用于监视系统的方法包括接收一组训练数据。 高斯混合模型被定义为基于接收到的训练数据从系统的多个传感器中的系统的特定传感器的概率分布建模。 高斯混合模型包括k个混合分量的和，其中k是正整数。 从系统的多个传感器接收传感器数据。 执行期望最大化技术以基于所定义的高斯混合模型和来自多个传感器的接收的传感器数据来估计特定传感器的期望值。

公开(公告)号：US07305317B2

公开(公告)日：2007-12-04

申请号：US10932573

申请日：2004-09-02

申请人： Chao Yuan ,  Zehra Cataltepe ,  Claus Neubauer ,  Ming Fang

发明人： Chao Yuan ,  Zehra Cataltepe ,  Claus Neubauer ,  Ming Fang

IPC分类号： G01C25/00

CPC分类号： G05B23/0254 ,  G05B23/0235

摘要： A joint approach of out-of-range detection and fault detection for power plant monitoring. The method initially determines whether a sensor is an independent sensor or a dependent sensor. If the sensor is an independent sensor, then an operating range is established for each independent sensor. A reading from each independent sensor is then compared with the operating range that has been established. If the reading is out-of-range, an alarm may be activated. If the reading is not out-of-range, then this reading is used to determine an expected operating range for each dependent sensor. A reading from each dependent sensor is then compared with the predicted operating range. Again, if the reading from the dependent sensor is out of the expected range, an alarm may be sounded.

摘要翻译： 电站监控的超范围检测和故障检测的联合方法。 该方法最初确定传感器是独立传感器还是依赖传感器。 如果传感器是独立的传感器，则为每个独立的传感器建立一个工作范围。 然后将每个独立传感器的读数与已建立的操作范围进行比较。 如果读数超出范围，则可能会激活报警。 如果读数不超出范围，则该读数用于确定每个相关传感器的预期工作范围。 然后将每个从属传感器的读数与预测的工作范围进行比较。 再次，如果来自从属传感器的读数超出预期范围，则可能会发出警报。

公开(公告)号：US07183905B2

公开(公告)日：2007-02-27

申请号：US10932576

申请日：2004-09-02

申请人： Claus Neubauer ,  Zehra Cataltepe ,  Chao Yuan ,  Jie Cheng ,  Ming Fang ,  Wesley McCorkle

发明人： Claus Neubauer ,  Zehra Cataltepe ,  Chao Yuan ,  Jie Cheng ,  Ming Fang ,  Wesley McCorkle

IPC分类号： G08B29/00

CPC分类号： G05B23/0272 ,  Y04S10/522

摘要： A tool for sensor management and fault visualization in machine condition monitoring. The method and system are able to monitor a plurality of sensors at one time. The sensors may be used in a power plant system monitoring system. The method and system may display a fault status for each sensor in the plurality of sensors in a single display, wherein the fault status for each sensor is displayed over time. The method and system also provide a mechanism that permits a user to examine details of each sensor in the plurality of sensors at any given time. In addition, the method and system are capable of categorizing each fault in the fault status using one or more properties or categorizing criteria. The method and system also permit sensors to be tested such that different operating models may be examined by utilizing different sensors.

摘要翻译： 机器状态监测中的传感器管理和故障可视化工具。 该方法和系统能够一次监视多个传感器。 传感器可用于发电厂系统监控系统。 该方法和系统可以在单个显示器中的多个传感器中的每个传感器显示故障状态，其中每个传感器的故障状态随时间显示。 该方法和系统还提供了允许用户在任何给定时间检查多个传感器中的每个传感器的细节的机构。 此外，该方法和系统能够使用一个或多个属性或分类标准对故障状态中的每个故障进行分类。 该方法和系统还允许测试传感器，使得可以通过利用不同的传感器检查不同的操作模型。