公开(公告)号：US20080229754A1

公开(公告)日：2008-09-25

申请号：US11689874

申请日：2007-03-22

申请人： Kai Frank Goebel ,  Rajesh Venkat Subbu ,  Randal Thomas Rausch ,  Dean Kimball Frederick

发明人： Kai Frank Goebel ,  Rajesh Venkat Subbu ,  Randal Thomas Rausch ,  Dean Kimball Frederick

IPC分类号： F02C1/00

CPC分类号： F02C9/00 ,  F05D2270/44 ,  F05D2270/71 ,  Y02T50/671

摘要： A method for multi-objective fault accommodation using predictive modeling is disclosed. The method includes using a simulated machine that simulates a faulted actual machine, and using a simulated controller that simulates an actual controller. A multi-objective optimization process is performed, based on specified control settings for the simulated controller and specified operational scenarios for the simulated machine controlled by the simulated controller, to generate a Pareto frontier-based solution space relating performance of the simulated machine to settings of the simulated controller, including adjustment to the operational scenarios to represent a fault condition of the simulated machine. Control settings of the actual controller are adjusted, represented by the simulated controller, for controlling the actual machine, represented by the simulated machine, in response to a fault condition of the actual machine, based on the Pareto frontier-based solution space, to maximize desirable operational conditions and minimize undesirable operational conditions while operating the actual machine in a region of the solution space defined by the Pareto frontier.

摘要翻译： 公开了一种使用预测建模的多目标故障调节方法。 该方法包括使用模拟故障实际机器的仿真机，并使用模拟实际控制器的仿真控制器。 基于模拟控制器的指定控制设置和由模拟控制器控制的模拟机器的指定操作场景，执行多目标优化过程，生成与仿真机器的性能相关的基于Pareto前沿的解空间， 模拟控制器，包括对操作场景的调整，以表示模拟机器的故障状态。 实际控制器的控制设置由模拟控制器进行调整，用于根据基于Pareto前沿解决方案空间的实际机器的故障情况来控制由仿真机器表示的实际机器，以最大化 期望的操作条件，并且在由帕累托边界限定的解空间的区域中操作实际机器时最小化不期望的操作条件。

公开(公告)号：US07904282B2

公开(公告)日：2011-03-08

申请号：US11689874

申请日：2007-03-22

申请人： Kai Frank Goebel ,  Rajesh Venkat Subbu ,  Randal Thomas Rausch ,  Dean Kimball Frederick

发明人： Kai Frank Goebel ,  Rajesh Venkat Subbu ,  Randal Thomas Rausch ,  Dean Kimball Frederick

IPC分类号： G06F9/455

CPC分类号： F02C9/00 ,  F05D2270/44 ,  F05D2270/71 ,  Y02T50/671

摘要： A method for multi-objective fault accommodation using predictive modeling is disclosed. The method includes using a simulated machine that simulates a faulted actual machine, and using a simulated controller that simulates an actual controller. A multi-objective optimization process is performed, based on specified control settings for the simulated controller and specified operational scenarios for the simulated machine controlled by the simulated controller, to generate a Pareto frontier-based solution space relating performance of the simulated machine to settings of the simulated controller, including adjustment to the operational scenarios to represent a fault condition of the simulated machine. Control settings of the actual controller are adjusted, represented by the simulated controller, for controlling the actual machine, represented by the simulated machine, in response to a fault condition of the actual machine, based on the Pareto frontier-based solution space, to maximize desirable operational conditions and minimize undesirable operational conditions while operating the actual machine in a region of the solution space defined by the Pareto frontier.

摘要翻译： 公开了一种使用预测建模的多目标故障调节方法。 该方法包括使用模拟故障实际机器的仿真机，并使用模拟实际控制器的仿真控制器。 基于模拟控制器的指定控制设置和由模拟控制器控制的模拟机器的指定操作场景，执行多目标优化过程，生成与仿真机器的性能相关的基于Pareto前沿的解空间， 模拟控制器，包括对操作场景的调整，以表示模拟机器的故障状态。 实际控制器的控制设置由模拟控制器进行调整，用于根据基于Pareto前沿解决方案空间的实际机器的故障情况来控制由仿真机器表示的实际机器，以最大化 期望的操作条件，并且在由帕累托边界限定的解空间的区域中操作实际机器时最小化不期望的操作条件。

公开(公告)号：US20080234994A1

公开(公告)日：2008-09-25

申请号：US11689885

申请日：2007-03-22

申请人： Kai Frank Goebel ,  Rajesh Venkat Subbu ,  Dean Kimball Frederick

发明人： Kai Frank Goebel ,  Rajesh Venkat Subbu ,  Dean Kimball Frederick

IPC分类号： G06F17/00

CPC分类号： G06F17/5009 ,  G06F17/5095 ,  G06F2217/10

摘要： A method for multi-objective deterioration accommodation using predictive modeling is disclosed. The method uses a simulated machine that simulates a deteriorated actual machine, and a simulated controller that simulates an actual controller. A multi-objective process is performed, based on specified control settings for the simulated controller and specified operational scenarios for the simulated machine controlled by the simulated controller, to generate a Pareto frontier-based solution space relating performance of the simulated machine to settings of the simulated controller, including adjustment to the operational scenarios to represent a deteriorated condition of the simulated machine. Control settings of the actual controller are adjusted, represented by the simulated controller, for controlling the actual machine, represented by the simulated machine, in response to a deteriorated condition of the actual machine, based on the Pareto frontier-based solution space, to maximize desirable operational conditions and minimize undesirable operational conditions while operating the actual machine in a region of the solution space defined by the Pareto frontier.

摘要翻译： 公开了一种使用预测建模的多目标恶化调节方法。 该方法使用模拟恶化的实际机器的模拟机，以及模拟实际控制器的仿真控制器。 基于模拟控制器的指定控制设置和由模拟控制器控制的模拟机器的指定操作场景，执行多目标过程，以生成将仿真机器的性能与模拟机器的性能相关联的基于帕累托前沿的解空间 模拟控制器，包括对操作场景的调整，以表示模拟机器的劣化状况。 由模拟控制器表示的实际控制器的控制设置根据基于帕累托前沿的解决方案空间，根据实际机器的劣化情况，对模拟机器所代表的实际机器进行调整，以最大化 期望的操作条件，并且在由帕累托边界限定的解空间的区域中操作实际机器时最小化不期望的操作条件。

公开(公告)号：US20080208487A1

公开(公告)日：2008-08-28

申请号：US11678273

申请日：2007-02-23

申请人： Kai Frank Goebel ,  Piero Patrone Bonissone ,  Weizhong Yan ,  Neil Holger White Eklund ,  Feng Xue

发明人： Kai Frank Goebel ,  Piero Patrone Bonissone ,  Weizhong Yan ,  Neil Holger White Eklund ,  Feng Xue

IPC分类号： G06F19/00

CPC分类号： G06Q10/04 ,  G05B23/0283

摘要： A method to reduce uncertainty bounds of predicting a remaining life of a probe using a set of diverse models is disclosed. The method includes generating an estimated remaining life output by each model of the set of diverse models, aggregating each of the respective estimated remaining life outputs via a fusion model, and in response to the aggregating, predicting the remaining life, the predicting having reduced uncertainty bounds based on the aggregating. The method further includes generating a signal corresponding to the predicted remaining life of the probe.

摘要翻译： 公开了一种减少使用一组不同模型预测探测器的剩余寿命的不确定性界限的方法。 该方法包括通过不同模型集合的每个模型生成估计的剩余寿命输出，通过融合模型聚合各自的估计剩余寿命输出中的每一个，并且响应于聚合预测剩余寿命，预测具有降低的不确定性 基于聚合的边界。 该方法还包括产生与探测器的预测剩余寿命相对应的信号。

公开(公告)号：US06757668B1

公开(公告)日：2004-06-29

申请号：US09704476

申请日：2000-11-03

申请人： Kai Frank Goebel ,  Malcolm John Ashby ,  Vivek Venugopal Badami

发明人： Kai Frank Goebel ,  Malcolm John Ashby ,  Vivek Venugopal Badami

IPC分类号： G06F1700

CPC分类号： G06K9/6292 ,  G05B23/0221

摘要： The present invention provides methods and tools to aggregate information stemming from a plurality of different classification tools and supportive evidential information to arrive at a unified classification estimate. The information fusion system according to the present invention has a plurality of sensors associated with the system, where each sensor is related to at least one class of the system and is data-related to the at least one class. A plurality of classification tools are each designed to receive selected and pre-processed outputs from the sensors and to generate classification outputs representing a state of at least one class of the system. An information fusion tool is configured to receive the outputs of the classification tools as well as evidential information as inputs, and has an hierarchical architecture which manipulates the inputs to generate an output of aggregated fused information for a particular class of the system.

摘要翻译： 本发明提供了聚合来自多个不同分类工具的信息和支持性证据信息以获得统一分类估计的方法和工具。 根据本发明的信息融合系统具有与系统相关联的多个传感器，其中每个传感器与系统的至少一个类别相关，并且与至少一个类别是数据相关的。 多个分类工具被设计成从传感器接收所选择的和预处理的输出，并产生表示系统的至少一个类的状态的分类输出。 信息融合工具被配置为接收分类工具的输出以及作为输入的证据信息，并且具有操纵输入以生成用于系统的特定类别的聚合融合信息的输出的分层架构。

公开(公告)号：US20080140352A1

公开(公告)日：2008-06-12

申请号：US11608076

申请日：2006-12-07

申请人： Kai Frank Goebel ,  Piero Patrone Bonissone ,  Weizhong Yan ,  Neil Holger White Eklund ,  Feng Xue ,  Hai Qiu

发明人： Kai Frank Goebel ,  Piero Patrone Bonissone ,  Weizhong Yan ,  Neil Holger White Eklund ,  Feng Xue ,  Hai Qiu

IPC分类号： G06F15/00

CPC分类号： G05B19/4184 ,  G05B2219/32234 ,  G05B2219/32235 ,  G05B2219/32369 ,  Y02P90/14 ,  Y02P90/26

摘要： A method to predict equipment life is disclosed. The method includes making available a set of input parameters, and defining a model of a health of the equipment as a function of the set of input parameters. The method continues with receiving at least one signal representative of a respective one of an actual sensor output relating to an actual operation attribute margin of the equipment, predicting a remaining useful equipment life based upon a sequence of outputs of the model of the health of the equipment, and generating a signal corresponding to the remaining useful equipment life.

摘要翻译： 公开了一种预测设备寿命的方法。 该方法包括提供一组输入参数，以及根据输入参数集合定义设备健康的模型。 该方法继续接收表示与设备的实际操作属性边缘相关的实际传感器输出中的相应一个信号的至少一个信号，基于该设备的健康模型的输出序列来预测剩余的有用设备寿命 设备，并产生对应于剩余有用设备寿命的信号。

公开(公告)号：US07933754B2

公开(公告)日：2011-04-26

申请号：US11608036

申请日：2006-12-07

申请人： Kai Frank Goebel ,  Neil Holger White Eklund ,  Hai Qiu ,  Weizhong Yan

发明人： Kai Frank Goebel ,  Neil Holger White Eklund ,  Hai Qiu ,  Weizhong Yan

IPC分类号： G06G7/48

CPC分类号： G06F17/5009 ,  G05B17/02 ,  G05B23/0283 ,  G06F2217/16

摘要： A method to estimate damage propagation is disclosed. The method includes making available a set of input parameters to a computational model, executing the computational model with defined changes within a range of an input parameter of the set of input parameters to define a range of at least one modeled output, receiving at least one signal responsive to and representative of a respective one of an actual sensor output, and estimating damage propagation based upon a correlation of the received signal to the modeled output.

摘要翻译： 公开了一种估计损伤传播的方法。 该方法包括向计算模型提供一组输入参数，在输入参数集合的输入参数的范围内执行具有定义的改变的计算模型，以定义至少一个建模输出的范围，接收至少一个 响应并代表实际传感器输出中的相应一个的信号，以及基于接收信号与建模输出的相关性估计损伤传播。

公开(公告)号：US07548830B2

公开(公告)日：2009-06-16

申请号：US11678273

申请日：2007-02-23

申请人： Kai Frank Goebel ,  Piero Patrone Bonissone ,  Weizhong Yan ,  Neil Holger White Eklund ,  Feng Xue

发明人： Kai Frank Goebel ,  Piero Patrone Bonissone ,  Weizhong Yan ,  Neil Holger White Eklund ,  Feng Xue

IPC分类号： G06F17/18

CPC分类号： G06Q10/04 ,  G05B23/0283

摘要： A method to reduce uncertainty bounds of predicting a remaining life of a probe using a set of diverse models is disclosed. The method includes generating an estimated remaining life output by each model of the set of diverse models, aggregating each of the respective estimated remaining life outputs via a fusion model, and in response to the aggregating, predicting the remaining life, the predicting having reduced uncertainty bounds based on the aggregating. The method further includes generating a signal corresponding to the predicted remaining life of the probe.

摘要翻译： 公开了一种减少使用一组不同模型预测探测器的剩余寿命的不确定性界限的方法。 该方法包括通过不同模型集合的每个模型生成估计的剩余寿命输出，通过融合模型聚合各自的估计剩余寿命输出中的每一个，并且响应于聚合预测剩余寿命，预测具有降低的不确定性 基于聚合的边界。 该方法还包括产生与探测器的预测剩余寿命相对应的信号。

公开(公告)号：US20080140361A1

公开(公告)日：2008-06-12

申请号：US11608058

申请日：2006-12-07

申请人： Piero Patrone Bonissone ,  Feng Xue ,  Anil Varma ,  Kai Frank Goebel ,  Weizhong Yan ,  Neil Holger White Eklund

发明人： Piero Patrone Bonissone ,  Feng Xue ,  Anil Varma ,  Kai Frank Goebel ,  Weizhong Yan ,  Neil Holger White Eklund

IPC分类号： G06F17/10

CPC分类号： G06N5/04

摘要： A method to predict remaining life of a target is disclosed. The method includes receiving information regarding a behavior of the target, and identifying from a database at least one piece of equipment having similarities to the target. The method further includes retrieving from the database data prior to an end of the equipment useful life, the data having a relationship to the behavior, evaluating a similarity of the relationship, predicting the remaining life of the target based upon the similarity, and generating a signal corresponding to the predicted remaining equipment life.

摘要翻译： 公开了一种预测目标的剩余寿命的方法。 该方法包括接收关于目标的行为的信息，以及从数据库中识别具有与目标相似的至少一件设备。 该方法还包括在设备使用寿命结束之前从数据库中获取数据，数据与行为有关系，评估关系的相似性，基于相似度预测目标的剩余寿命，并且生成 信号对应于预计的剩余设备寿命。

公开(公告)号：US06216066B1

公开(公告)日：2001-04-10

申请号：US09108359

申请日：1998-07-01

申请人： Kai Frank Goebel ,  David Lacey Doel

发明人： Kai Frank Goebel ,  David Lacey Doel

IPC分类号： G06F700

CPC分类号： G05B23/0232 ,  G05B23/0262 ,  G06K9/6223 ,  G06K9/6284 ,  G07C3/00

摘要： This invention provides a system and method for generating alerts through multi-variate assessment. A normalizer normalizes data obtained from a process. A classifier classifies the correlated data in a multi-dimensional space defined for the variables in the process. The normalized data are classified into a normal cluster indicative of normal operating conditions and at least one alert cluster each indicative of alert conditions. An alert verifier verifies correlated data classified as an alert condition. In another embodiment of this invention, a tracker is used for addressing drifting data sets that arise in the process over time which allows the adaptation of classifiers to the shifted state. In a third embodiment, the multi-variate generator is used in parallel with a trend performance analysis tool to validate alerts generated therefrom.

摘要翻译： 本发明提供了一种通过多变量评估产生警报的系统和方法。 归一化器对从进程获得的数据进行归一化。 分类器将过程中的变量定义的多维空间中的相关数据进行分类。 标准化数据被分类为指示正常操作条件的正常集群和每个指示警报条件的至少一个警报集群。 警报验证者验证分类为警报条件的相关数据。 在本发明的另一个实施例中，跟踪器用于寻址随着时间的流逝出现的漂移数据集，其允许分类器适应移位状态。 在第三实施例中，多变量发生器与趋势性能分析工具并行使用以验证从其产生的警报。