Methods, systems, and computer program products for implementing condition monitoring activities
    1.
    发明公开
    Methods, systems, and computer program products for implementing condition monitoring activities 审中-公开
    方法,系统和进行状态监控计算机程序

    公开(公告)号:EP1686443A1

    公开(公告)日:2006-08-02

    申请号:EP06250485.7

    申请日:2006-01-30

    IPC分类号: G05B23/02

    CPC分类号: G05B23/0229

    摘要: Methods, systems, and computer program products are provided for implementing condition monitoring activities. Systems include a processor (204) in communication with a machine (202) being monitored. The processor (204) receives signals output by the machine (202) via a signal conversion element (210) associated with the machine (202). Systems also include a display device (205) in communication with the processor (204) for providing signatures of the signals received from the signal conversion element (210). Systems further include a means (204) for identifying, isolating, and capturing a signature (212) from the signatures presented on the display device (205). The systems also include a means (204) for digitizing and recording the signature (212) as an event kernel, normalizing the event kernel by performing a mean removal, and normalizing the energy to unity on results of the mean removal. Systems further include a storage device (206) for storing normalized event kernels.

    摘要翻译: 方法,系统和计算机程序产品提供了实施条件监测活动。 系统包括在通信的处理器(204)与被监控的机器(202)。 该处理器(204)经由与所述机器(202)相关联的信号转换元件(210)由所述机器(202)接收信号输出。 因此系统包括与所述处理器(204),用于提供从所述信号转换元件(210)接收的信号的签名通信的显示设备(205)。 进一步的系统包括:用于识别,分离和捕获从呈现在显示设备(205)上签名的签名(212)的装置(204)。 因此,该系统包括一个装置(204),用于数字化和记录签名(212)作为内核事件的,通过进行平均去除归一化的情况下的内核,并且在平均去除率的结果的能量归一化来统一。 另外的系统包括用于存储标准化事件内核的存储装置(206)。

    Systems and methods for remote monitoring of vibrations in machines
    2.
    发明公开
    Systems and methods for remote monitoring of vibrations in machines 审中-公开
    Systeme und Verfahren zurFernüberwachungvon Vibrationen in Maschinen

    公开(公告)号:EP1816453A2

    公开(公告)日:2007-08-08

    申请号:EP07101565.5

    申请日:2007-02-01

    IPC分类号: G01H9/00

    CPC分类号: G01H9/00

    摘要: A system and method for monitoring the vibrations of a machine (110) that includes a reflective patch (130) affixed to the machine and a vibration detection module (120) including an interrogator unit (160) and a demodulation unit. The interrogator unit may be positioned remotely from the machine such that the interrogator unit transmits an electromagnetic beam to the reflective patch and reflected from the reflective patch to the demodulation unit. The demodulation unit demodulates the electromagnetic beam to determine the vibration of the machine.

    摘要翻译: 一种用于监测机器(110)的振动的系统和方法,所述机器(110)包括固定到机器上的反射贴片(130)和包括询问器单元(160)和解调单元的振动检测模块(120)。 询问器单元可以远离机器定位,使得询问器单元将电磁波束发射到反射贴片并从反射贴片反射到解调单元。 解调单元解调电磁波束以确定机器的振动。

    System and method for generating alerts through multi-variate data assessment
    3.
    发明公开
    System and method for generating alerts through multi-variate data assessment 审中-公开
    系统和方法通过多变量数据审核生成警告

    公开(公告)号:EP0971321A3

    公开(公告)日:2003-11-05

    申请号:EP99305238.0

    申请日:1999-07-01

    IPC分类号: G07C3/00 G05B23/02

    摘要: This invention provides a system (28) and method for generating alerts through multi-variate assessment. A normalizer (30) normalizes data obtained from a process. A classifier (32) 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 (34) 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.

    System and method for generating alerts through multi-variate data assessment
    5.
    发明公开
    System and method for generating alerts through multi-variate data assessment 审中-公开
    系统与Verfahren zum Erzeugen von Warnungen durch multivariabler Datenbewertung

    公开(公告)号:EP0971321A2

    公开(公告)日:2000-01-12

    申请号:EP99305238.0

    申请日:1999-07-01

    IPC分类号: G07C3/00

    摘要: This invention provides a system (28) and method for generating alerts through multi-variate assessment. A normalizer (30) normalizes data obtained from a process. A classifier (32) 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 (34) 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(28)和方法。 规范化器(30)对从过程获得的数据进行归一化。 分类器(32)将相关数据分类到为进程中的变量定义的多维空间中。 归一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。 警报验证器(34)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,跟踪器被用于寻址在时间过程中出现的漂移数据集,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。

    Alert generation in trend performance analysis
    8.
    发明公开
    Alert generation in trend performance analysis 审中-公开
    报告人:Leistungstrendermitlung

    公开(公告)号:EP1122694A2

    公开(公告)日:2001-08-08

    申请号:EP01300861.0

    申请日:2001-01-31

    IPC分类号: G07C3/00

    摘要: This invention provides an improved alert generation system (20) and method for trend performance analysis. A multi-variate abnormal condition detector (28) normalizes data obtained from a process (16,17) and classifies the data in a multi-dimensional space defined for the variables in the process. The normalized data are classified into either a normal or abnormal class. An alert evaluator (29) evaluates the data classified in the abnormal class and determines whether the data are a true alert or a false alert. In another embodiment, the multi-variate abnormal condition detector (28) and alert evaluator (29) are used in parallel with a trend performance analysis tool to validate alerts generated therefrom.

    摘要翻译: 本发明提供了一种改进的警报生成系统(20)和用于趋势性能分析的方法。 多变量异常状态检测器(28)对从过程(16,17)获得的数据进行归一化,并且在该过程中为变量定义的多维空间中对数据进行分类。 归一化数据分为正常或异常类。 警报评估器(29)评估分类在异常类中的数据,并确定数据是真实警报还是虚假警报。 在另一个实施例中,多变量异常状况检测器(28)和警报评估器(29)与趋势性能分析工具并行使用,以验证从其产生的警报。