公开(公告)号：US10108513B2

公开(公告)日：2018-10-23

申请号：US15303243

申请日：2014-04-16

Applicant: Siemens Aktiengesellschaft

Inventor： Chao Yuan ,  Amit Chakraborty ,  Holger Hackstein ,  Hans Weber

IPC: G06F11/00 ,  G06F11/22 ,  G05B23/02 ,  G06N99/00

Abstract: A method for predicting failure modes in a machine includes learning (31) a multivariate Gaussian distribution for each of a source machine and a target machine from data samples from one or more independent sensors of the source machine and the target machine, learning (32) a multivariate Gaussian conditional distribution for each of the source machine and the target machine from data samples from one or more dependent sensors of the source machine and the target machine using the multivariate Gaussian distribution for the independent sensors, transforming (33) data samples for the independent sensors from the source machine to the target machine using the multivariate Gaussian distributions for the source machine and the target machine, and transforming (34) data samples for the dependent sensors from the source machine to the target machine using the transformed independent sensor data samples and the conditional Gaussian distributions for the source machine and the target machine.

公开(公告)号：US09958401B2

公开(公告)日：2018-05-01

申请号：US14780436

申请日：2014-03-24

Applicant: SIEMENS AKTIENGESELLSCHAFT

Inventor： Holger Hackstein ,  Christian Morhart ,  Dominikus Joachim Müller ,  Florian Poprawa ,  Andreas Ziroff

IPC: G01N22/00 ,  G01F1/74 ,  G01N15/06 ,  G01N15/00

CPC classification number: G01N22/00 ,  G01F1/74 ,  G01N15/06 ,  G01N2015/0046 ,  G01N2015/0693

Abstract: The present embodiments relate to a device and a method for determining at least one concentration of coal particles in a gas flow flowing through a channel, wherein at least part of the gas flow having coal particles contained therein is measured by at least one microwave sensor and at least one measurement signal characterizing the concentration of the coal particles is provided, wherein an autocorrelation function of the measurement signal is determined and at least one distance value characterizing a distance of a point of the gas flow belonging to the concentration from the microwave sensor is determined in dependence on the autocorrelation function.

公开(公告)号：US09791426B2

公开(公告)日：2017-10-17

申请号：US14749682

申请日：2015-06-25

Applicant: SIEMENS AKTIENGESELLSCHAFT

Inventor： Gerit Ebelsberger ,  Holger Hackstein ,  Erhard Magori

IPC: G01N33/00 ,  G01N1/22 ,  F23R3/00

CPC classification number: G01N33/004 ,  F23R3/002 ,  G01N1/2226 ,  G01N1/2247

Abstract: A sensor apparatus for analyzing a gas in a process chamber, having a housing, a gas sensor for analyzing at least a part of the gas, the gas sensor being arranged at a determined position in the housing, a gas feed for connecting the housing to the process chamber to feed the part of the gas from the process chamber into the housing and to the determined position, and a gas discharge for discharging the gas from the housing, wherein the gas feed and the gas discharge are configured as tubes lying inside one another, characterized by a closure cap at the combustion chamber-side end of the tubes lying inside one another, the closure cap including an even number of at least four openings with the same area, which are connected alternately as a gas inlet and a gas outlet to the tubes lying inside one another is provided.

公开(公告)号：US20170205537A1

公开(公告)日：2017-07-20

申请号：US15320899

申请日：2015-06-29

Applicant: Siemens Aktiengesellschaft

Inventor： Chao Yuan ,  Amit Chakraborty ,  Holger Hackstein

IPC: G01W1/10 ,  G06Q10/04 ,  G06N7/00 ,  G01W1/12

CPC classification number: G01W1/10 ,  G01W1/12 ,  G06F17/18 ,  G06N7/005 ,  G06Q10/04 ,  G06Q50/06

Abstract: A method for solar forecasting includes receiving a plurality of solar energy data as a function of time of day at a first time, forecasting (620) from the solar energy data a mode, where the mode is a sunny day, a cloudy day, or an overcast day, and the forecast predicts the mode for a next solar energy datum, receiving (622) the next solar energy datum, updating a probability distribution function (pdf) of the next solar energy datum given the mode, updating a pdf of the mode for the next solar energy datum from the updated pdf of the new solar energy datum given the mode, forecasting (624, 626) a plurality of future unobserved solar energy data from the updated pdf of the mode, where the plurality of future unobserved solar energy data and the plurality of solar energy data have a Gaussian distribution for a given mode determined from training data.

公开(公告)号：US09599557B2

公开(公告)日：2017-03-21

申请号：US14770663

申请日：2014-02-11

Applicant: SIEMENS AKTIENGESELLSCHAFT

Inventor： Alexander Michael Gigler ,  Holger Hackstein ,  Remigiusz Pastusiak ,  Kerstin Wiesner

IPC: G01N21/47 ,  G01N21/53 ,  G01N21/15 ,  G01N21/85 ,  G01N15/06 ,  G01N15/02 ,  G01N33/24 ,  G01N21/3554 ,  G01N21/3563 ,  G01N21/552 ,  G01N21/35 ,  G01N21/84 ,  G01N15/00

CPC classification number: G01N21/53 ,  G01N15/0205 ,  G01N15/0612 ,  G01N21/15 ,  G01N21/3554 ,  G01N21/3563 ,  G01N21/474 ,  G01N21/552 ,  G01N21/8507 ,  G01N33/24 ,  G01N2015/0096 ,  G01N2021/151 ,  G01N2021/3595 ,  G01N2021/536 ,  G01N2021/8411 ,  G01N2021/8528

Abstract: An optical sensor is arranged in an indentation of a dust line, the indentation being equipped with at least one gas inlet nozzle for removing the dust from the optical sensor. Dust is transported through the dust line. An optical property of the dust is measured using at least one optical sensor arranged in an indentation of the dust line, and the dust is then removed from the optical sensor by blowing in air using the at least one gas inlet nozzle arranged in the indentation.

公开(公告)号：US20160069822A1

公开(公告)日：2016-03-10

申请号：US14780436

申请日：2014-03-24

Applicant: SIEMENS AKTIENGESELLSCHAFT

Inventor： Holger Hackstein ,  Christian Morhart ,  Dominikus Joachim Müller ,  Florian Poprawa ,  Andreas Ziroff

IPC: G01N22/00

CPC classification number: G01N22/00 ,  G01F1/74 ,  G01N15/06 ,  G01N2015/0046 ,  G01N2015/0693

Abstract: The present embodiments relate to a device and a method for determining at least one concentration of coal particles in a gas flow flowing through a channel, wherein at least part of the gas flow having coal particles contained therein is measured by at least one microwave sensor and at least one measurement signal characterizing the concentration of the coal particles is provided, wherein an autocorrelation function of the measurement signal is determined and at least one distance value characterizing a distance of a point of the gas flow belonging to the concentration from the microwave sensor is determined in dependence on the autocorrelation function.

Abstract translation: 本实施例涉及一种用于确定流过通道的气流中的至少一种煤颗粒浓度的装置和方法，其中至少部分含有煤颗粒的气流通过至少一个微波传感器测量， 提供表征煤粒子浓度的至少一个测量信号，其中确定测量信号的自相关函数，并且表征属于来自微波传感器的浓度的气流的点的距离的至少一个距离值是 根据自相关函数确定。

公开(公告)号：US20150142384A1

公开(公告)日：2015-05-21

申请号：US14406606

申请日：2013-06-11

Applicant: Siemens Aktiengesellschaft

Inventor： Yuan Chao ,  Amit Chakraborty ,  Holger Hackstein ,  Leif Wiebking

IPC: G06F11/30 ,  G06F17/18

CPC classification number: G06F11/3089 ,  G06F11/008 ,  G06F17/18

Abstract: A method for monitoring a condition of a system or process includes acquiring sensor data from a plurality of sensors disposed within the system (S41 and S44). The acquired sensor data is streamed in real-time to a computer system (S42 and S44). A discriminative framework is applied to the streaming sensor data using the computer system (S43 and S45). The discriminative framework provides a probability value representing a probability that the sensor data is indicative of an anomaly within the system. The discriminative framework is an integration of a Kalman filter with a logistical function (S41).

Abstract translation: 一种用于监视系统或过程的状况的方法包括从设置在系统内的多个传感器获取传感器数据（S41和S44）。 所获取的传感器数据被实时流式传输到计算机系统（S42和S44）。 使用计算机系统将歧视性框架应用于流传感器数据（S43和S45）。 辨别框架提供概率值，该概率值表示传感器数据表示系统内的异常的概率。 歧视性框架是卡尔曼滤波器与后勤功能的集成（S41）。