NEURO-PARITY PATTERN RECOGNITION SYSTEM AND METHOD
    1.
    发明申请
    NEURO-PARITY PATTERN RECOGNITION SYSTEM AND METHOD 审中-公开
    神经元特征模式识别系统及方法

    公开(公告)号:WO9964962A9

    公开(公告)日:2000-03-23

    申请号:PCT/US9913054

    申请日:1999-06-09

    Applicant: ARCH DEV CORP

    CPC classification number: G21D3/04 Y02E30/40

    Abstract: A method and system for monitoring a process and determining its condition. Initial data is sensed, a first set of virtual data is produced by applying a system state (20) analyzation to the initial data, a second set of virtual data is produced by applying a neural network (40) analyzation to the initial data and a parity space (50) analyzation is applied to the first and second set of virtual data and also to the initial data to provide a parity space (50) decision about the condition of the process. A logic test (60) can further be applied to produce a further system decision about the state of the process.

    Abstract translation: 一种用于监控过程并确定其状况的方法和系统。 感测初始数据,通过对初始数据应用系统状态(20)分析来产生第一组虚拟数据,通过对初始数据应用神经网络(40)分析产生第二组虚拟数据,并且 将奇偶校验空间(50)分析应用于第一和第二组虚拟数据以及初始数据,以提供关于处理条件的奇偶校验空间(50)决定。 可以进一步应用逻辑测试(60)来产生关于过程状态的进一步的系统决策。

    SELF-TUNING SYSTEM FOR INDUSTRIAL SURVEILLANCE
    2.
    发明申请
    SELF-TUNING SYSTEM FOR INDUSTRIAL SURVEILLANCE 审中-公开
    自动调谐系统用于工业监控

    公开(公告)号:WO9905685A8

    公开(公告)日:1999-03-25

    申请号:PCT/US9815280

    申请日:1998-07-23

    Applicant: ARCH DEV CORP

    CPC classification number: G05B23/0221 G05B23/0254

    Abstract: A method and system for automatically establishing operational parameters of a statistical surveillance system. The method and system performs a frequency domain transition (20) on time dependent data, first Fourier composite (30) is formed, serial correlation (35) is removed, a series of Gaussian whiteness tests (50) are performed along with an autocorrelation (35) test, Fourier coefficients (80) are stored and a second Fourier composite is formed. Pseudorandom noise is added, a Monte Carlo simulation is performed to establish SPRT missed alarm probabilities and tested with a synthesized signal. A false alarm test is then empirically evaluated and if less than a desired target value, then SPRT probabilities are used for performing surveillance.

    Abstract translation: 自动建立统计监视系统运行参数的方法和系统。 该方法和系统对时间相关数据执行频域转换(20),形成第一傅里叶复合(30),去除串行相关(35),执行一系列高斯白度测试(50)以及自相关 35)测试,存储傅里叶系数(80)并形成第二傅里叶复合物。 添加伪随机噪声,执行蒙特卡洛模拟以建立SPRT漏检概率并用合成信号进行测试。 然后通过实验评估虚警测试,如果测试结果低于预期目标值,则使用SPRT概率进行监测。

    ULTRASENSITIVE SURVEILLANCE OF SENSORS AND PROCESSES
    3.
    发明公开
    ULTRASENSITIVE SURVEILLANCE OF SENSORS AND PROCESSES 有权
    超灵敏监测传感器和进程

    公开(公告)号:EP1055239A4

    公开(公告)日:2002-06-19

    申请号:EP99903131

    申请日:1999-01-14

    Applicant: ARCH DEV CORP

    CPC classification number: G21D3/001 G21C17/00 Y02E30/40

    Abstract: A method and apparatus for monitoring a source of data for determining an operating state of a working system. The method includes determining a sensor (or source of data) arrangement associated with monitoring the source of data for a system, activating a method for performing a sequential probability ratio test if the data source includes a single data (sensor) source, activating a second method for performing a regression sequential possibility ratio testing procedure if the arrangement includes a pair of sensors (data sources) with signals which are linearly of non-linearly related; activating a third method for performing a bounded angle ratio test procedure if the sensor arrangement includes multiple sensors and utilizing at least one of the first, second and third methods to accumulate sensor signals and determining the operating state of the system.

    Ultrasensitive surveillance of sensors and processes

    公开(公告)号:AU748987B2

    公开(公告)日:2002-06-13

    申请号:AU2322599

    申请日:1999-01-14

    Applicant: ARCH DEV CORP

    Abstract: A method and apparatus for monitoring a source of data for determining an operating state of a working system. The method includes determining a sensor (or source of data) arrangement associated with monitoring the source of data for a system, activating a method for performing a sequential probability ratio test if the data source includes a single data (sensor) source, activating a second method for performing a regression sequential possibility ratio testing procedure if the arrangement includes a pair of sensors (data sources) with signals which are linearly or non-linearly related; activating a third method for performing a bounded angle ratio test procedure if the sensor arrangement includes multiple sensors and utilizing at least one of the first, second and third methods to accumulate sensor signals and determining the operating state of the system.

    Neuro-parity pattern recognition system and method

    公开(公告)号:AU4431999A

    公开(公告)日:1999-12-30

    申请号:AU4431999

    申请日:1999-06-09

    Applicant: ARCH DEV CORP

    Abstract: A method and system for monitoring a process and determining its condition. Initial data is sensed, a first set of virtual data is produced by applying a system state analyzation to the initial data, a second set of virtual data is produced by applying a neural network analyzation to the initial data and a parity space analyzation is applied to the first and second set of virtual data and also to the initial data to provide a parity space decision about the condition of the process. A logic test can further be applied to produce a further system decision about the state of the process.

    Ultrasensitive surveillance of sensors and processes

    公开(公告)号:AU2322599A

    公开(公告)日:1999-08-02

    申请号:AU2322599

    申请日:1999-01-14

    Applicant: ARCH DEV CORP

    Abstract: A method and apparatus for monitoring a source of data for determining an operating state of a working system. The method includes determining a sensor (or source of data) arrangement associated with monitoring the source of data for a system, activating a method for performing a sequential probability ratio test if the data source includes a single data (sensor) source, activating a second method for performing a regression sequential possibility ratio testing procedure if the arrangement includes a pair of sensors (data sources) with signals which are linearly or non-linearly related; activating a third method for performing a bounded angle ratio test procedure if the sensor arrangement includes multiple sensors and utilizing at least one of the first, second and third methods to accumulate sensor signals and determining the operating state of the system.

    ULTRASENSITIVE SURVEILLANCE OF SENSORS AND PROCESSES

    公开(公告)号:CA2318093A1

    公开(公告)日:1999-07-22

    申请号:CA2318093

    申请日:1999-01-14

    Applicant: ARCH DEV CORP

    Abstract: A method and apparatus for monitoring a source of data for determining an operating state of a working system. The method includes determining a sensor (or source of data) arrangement associated with monitoring the source of data for a system, activating a method for performing a sequential probability ratio test if the data source includes a single data (sensor) source, activating a second method for performing a regression sequential possibility ratio testing procedure if the arrangement includes a pair of sensors (data sources) with signals which are linearly of non-linearly related; activating a third method for performing a bounded angle ratio test procedure if the sensor arrangement includes multiple sensors and utilizing at least one of the first, second and third methods to accumulate sensor signals and determining the operating state of the system.

    A neural network based system for equipment surveillance

    公开(公告)号:AU7011596A

    公开(公告)日:1997-03-19

    申请号:AU7011596

    申请日:1996-08-30

    Applicant: ARCH DEV CORP

    Abstract: A method and system for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process.

    MONITORIZACION ULTRASENSIBLE DE SENSORES Y PROCESOS.

    公开(公告)号:ES2257849T3

    公开(公告)日:2006-08-01

    申请号:ES99903131

    申请日:1999-01-14

    Applicant: ARCH DEV CORP

    Abstract: Un procedimiento para monitorizar una fuente de datos de sensores para determinar una condición operativa de un sistema monitorizado seleccionado, que incluye las etapas siguientes: realizar una fase de aprendizaje aportando datos de referencia característicos de una condición de operación normal de un sistema de referencia y recoger datos seleccionados de dicha fuente de datos de sensores y que es característica de una condición operativa de un sistema seleccionado, el procedimiento está caracterizado por las etapas de realizar un procedimiento de prueba de relación de ángulos acotados (BART) sobre dichos datos de referencia y dichos datos seleccionados en el que el procedimiento BART comprende la fase de aprendizaje y una fase de monitorización y en que la fase de aprendizaje incluye (a) adquirir una matriz de datos que contiene muestras de datos de una fuente de datos de sensores monitorizada en la que la matriz de datos es representativa de la operación normal del sistema y los parámetros BART se seleccionan para la fuente de datos de sensores, (b) determinar la altura del dominio de similitud para cada una de las fuentes de datos de sensores usando parámetros BART y (c) seleccionar un subconjunto de la matriz de datos para crear una matriz modelo H usada en los cálculos de estimación BART, y la fase de monitorización incluye (1) adquirir un vector de muestra en cada etapa temporal que contiene una lectura de sensor de la fuente de datos de sensores. (2) calcular un ángulo de similitud entre el vector de muestra y cada vector de muestra de la fase de aprendizaje almacenada en la matriz H, (3) calcular una estimación del vector de muestra de entrada Y usando los cálculos de la estimación BART, (4) determinar una diferencia entre la estimación y valores de datos reales de sensores y (5) introducir la diferencia en una prueba secuencial de relación de probabilidades para el análisis de alarmas de fallos; y (6) generar una indicación al determinar que existe una desviación dedichos datos seleccionados para dicho sistema monitorizado seleccionado con respecto a dichos datos de referencia.

    10.
    发明专利
    未知

    公开(公告)号:AT321340T

    公开(公告)日:2006-04-15

    申请号:AT99903131

    申请日:1999-01-14

    Applicant: ARCH DEV CORP

    Abstract: A method and apparatus for monitoring a source of data for determining an operating state of a working system. The method includes determining a sensor (or source of data) arrangement associated with monitoring the source of data for a system, activating a method for performing a sequential probability ratio test if the data source includes a single data (sensor) source, activating a second method for performing a regression sequential possibility ratio testing procedure if the arrangement includes a pair of sensors (data sources) with signals which are linearly or non-linearly related; activating a third method for performing a bounded angle ratio test procedure if the sensor arrangement includes multiple sensors and utilizing at least one of the first, second and third methods to accumulate sensor signals and determining the operating state of the system.

Patent Agency Ranking