公开(公告)号：US09791351B2

公开(公告)日：2017-10-17

申请号：US14616105

申请日：2015-02-06

Applicant: General Electric Company

Inventor： Karen Warren Miller ,  Lijie Yu ,  Robert Iasillo

IPC: G01M15/14 ,  F02C9/00 ,  F02C3/04

CPC classification number: G01M15/14 ,  F02C3/04 ,  F02C9/00 ,  F05D2260/80 ,  F05D2260/83 ,  F05D2270/0831

Abstract: Systems and methods for gas turbine combustion profile monitoring are disclosed. In one embodiment, a method for detecting an anomaly in a combustion section of a gas turbine is disclosed. The method includes receiving, from a plurality of thermal sensors disposed around an exhaust section of a gas turbine, exhaust profile data of the gas turbine. The method further analyzes the exhaust profile data to calculate statistical features associated with a peak-trough pattern. The method further determines, using a machine learning algorithm, that the statistical features are abnormal. In response to the determination, the method processes the exhaust profile data for a predetermined period of time and reports an anomaly in a combustion section of the gas turbine if the statistical features remain abnormal for the predetermined period of time.

公开(公告)号：US10047679B2

公开(公告)日：2018-08-14

申请号：US15182381

申请日：2016-06-14

Applicant: General Electric Company

Inventor： Xiaomo Jiang ,  Ilan Leibu ,  Lijie Yu ,  Devang Jagdish Gandhi ,  Karen Warren Miller ,  Matthew Everett Moore ,  Ketan Kalele

IPC: G01M15/14 ,  F02C9/46 ,  F01D21/00

Abstract: A monitoring system for a gas turbine includes a processor configured to receive an operating signal indicating an operating parameter of the gas turbine. The processor is configured to predict an occurrence of a lean blowout (LBO) event based on the operating parameter and an entropy ratio of combustion dynamics associated with a combustor of the gas turbine, wherein the LBO event corresponds to when the combustor stops firing. The processor is configured to send an alarm signal indicating the predicted LBO event to an electronic device prior to the occurrence of the LBO event.

公开(公告)号：US09719366B2

公开(公告)日：2017-08-01

申请号：US13916179

申请日：2013-06-12

Applicant: General Electric Company

Inventor： Lijie Yu ,  Venkatesh Rajagopalan ,  Sachin Srivastava ,  Mayank Lalan

IPC: F01D11/14 ,  F01D11/20 ,  F01D17/02 ,  F01D21/00 ,  F01D21/04 ,  F01D21/10 ,  F01D21/14

CPC classification number: F01D11/14 ,  F01D11/20 ,  F01D17/02 ,  F01D21/003 ,  F01D21/04 ,  F01D21/045 ,  F01D21/10 ,  F01D21/14

Abstract: Systems and methods for blade health monitoring are provided. According to one embodiment of the disclosure, a system may include a feature extraction module and an anomaly detection module in communication with the extraction module. The feature extraction module may be configured to continuously receive blade passing signal data associated with clearance of a blade and pre-process the blade passing signal data. Blade clearance feature data may be extracted from the blade passing signal data prior to transmission to the anomaly detection module. The anomaly detection module may be configured to normalize the blade clearance feature data received from the extraction module, analyze the blade clearance feature data to detect a shift in the clearance of the blade, and determine an abnormality of the blade based on the shift exceeding a predetermined shift threshold.

公开(公告)号：US20140369833A1

公开(公告)日：2014-12-18

申请号：US13916179

申请日：2013-06-12

Applicant: General Electric Company

Inventor： Lijie Yu ,  Venkatesh Rajagopalan ,  Sachin Srivastava ,  Mayank Lalan

IPC: F01D5/12

CPC classification number: F01D11/14 ,  F01D11/20 ,  F01D17/02 ,  F01D21/003 ,  F01D21/04 ,  F01D21/045 ,  F01D21/10 ,  F01D21/14

Abstract: Systems and methods for blade health monitoring are provided. According to one embodiment of the disclosure, a system may include a feature extraction module and an anomaly detection module in communication with the extraction module. The feature extraction module may be configured to continuously receive blade passing signal data associated with clearance of a blade and pre-process the blade passing signal data. Blade clearance feature data may be extracted from the blade passing signal data prior to transmission to the anomaly detection module. The anomaly detection module may be configured to normalize the blade clearance feature data received from the extraction module, analyze the blade clearance feature data to detect a shift in the clearance of the blade, and determine an abnormality of the blade based on the shift exceeding a predetermined shift threshold.

Abstract translation: 提供了叶片健康监测的系统和方法。 根据本公开的一个实施例，系统可以包括与提取模块通信的特征提取模块和异常检测模块。 特征提取模块可以被配置为连续接收与叶片的间隙相关联的叶片通过信号数据，并且预处理叶片通过信号数据。 刀片间隙特征数据可以在传输到异常检测模块之前从刀片通过信号数据中提取。 异常检测模块可以被配置为对从提取模块接收到的叶片间隙特征数据进行归一化，分析叶片间隙特征数据以检测叶片的间隙中的移动，并且基于超过a的移位来确定叶片的异常 预定移位阈值。

公开(公告)号：US20170356349A1

公开(公告)日：2017-12-14

申请号：US15182381

申请日：2016-06-14

Applicant: General Electric Company

Inventor： Xiaomo Jiang ,  Ilan Leibu ,  Lijie Yu ,  Devang Jagdish Gandhi ,  Karen Warren Miller ,  Matthew Everett Moore ,  Ketan Kalele

IPC: F02C9/46 ,  G01M15/14 ,  F01D21/00

CPC classification number: F02C9/46 ,  F01D21/003 ,  F05D2270/051 ,  F05D2270/44 ,  G01M15/14

Abstract: A monitoring system for a gas turbine includes a processor configured to receive an operating signal indicating an operating parameter of the gas turbine. The processor is configured to predict an occurrence of a lean blowout (LBO) event based on the operating parameter and an entropy ratio of combustion dynamics associated with a combustor of the gas turbine, wherein the LBO event corresponds to when the combustor stops firing. The processor is configured to send an alarm signal indicating the predicted LBO event to an electronic device prior to the occurrence of the LBO event.

公开(公告)号：US20160231199A1

公开(公告)日：2016-08-11

申请号：US14616105

申请日：2015-02-06

Applicant: General Electric Company

Inventor： Karen Warren Miller ,  Lijie Yu ,  Robert Iasillo

IPC: G01M15/14 ,  F02C3/04

CPC classification number: G01M15/14 ,  F02C3/04 ,  F02C9/00 ,  F05D2260/80 ,  F05D2260/83 ,  F05D2270/0831

Abstract: Systems and methods for gas turbine combustion profile monitoring are disclosed. In one embodiment, a method for detecting an anomaly in a combustion section of a gas turbine is disclosed. The method includes receiving, from a plurality of thermal sensors disposed around an exhaust section of a gas turbine, exhaust profile data of the gas turbine. The method further analyzes the exhaust profile data to calculate statistical features associated with a peak-trough pattern. The method further determines, using a machine learning algorithm, that the statistical features are abnormal. In response to the determination, the method processes the exhaust profile data for a predetermined period of time and reports an anomaly in a combustion section of the gas turbine if the statistical features remain abnormal for the predetermined period of time.

Abstract translation: 公开了用于燃气轮机燃烧轮廓监测的系统和方法。 在一个实施例中，公开了一种用于检测燃气轮机的燃烧部分中的异常的方法。 该方法包括从设置在燃气轮机的排气部周围的多个热传感器接收燃气轮机的排气轮廓数据。 该方法进一步分析排气廓线数据以计算与峰谷图案相关联的统计特征。 该方法使用机器学习算法进一步确定统计特征是异常的。 响应于该确定，如果统计特征在预定时间段内保持异常，则该方法处理预定时间段的排气廓线数据并且报告燃气涡轮机的燃烧部分中的异常。

公开(公告)号：US20150081229A1

公开(公告)日：2015-03-19

申请号：US14027688

申请日：2013-09-16

Applicant: General Electric Company

Inventor： Lijie Yu ,  Adil Ansari ,  Vivek Venugopal Badami ,  John Thomas Bliss ,  Rahul Chadha ,  Rajan Gupta

IPC: F04D27/00

CPC classification number: F04D27/001 ,  F01D21/00 ,  F01D21/003 ,  F01D21/04 ,  F01D21/10 ,  F01D21/14 ,  F02C9/00 ,  F03D17/00 ,  F04D29/324 ,  F05D2260/80 ,  F05D2260/81 ,  G01B7/14 ,  G01B11/14 ,  G01B21/16 ,  G01D21/00 ,  G06F17/40 ,  G06F19/00

Abstract: A system including: at least one computing device configured to monitor a compressor blade in a turbomachine by: extracting time of arrival (TOA) data about the compressor blade at a defined interval; correlating turbomachine operating conditions with the TOA data; extracting resonance data about the compressor blade during startup or shutdown of the turbomachine, and extracting static deflection and tip clearance data about the compressor blade during steady state operation of the turbomachine; creating a baseline compressor blade comparison level based upon the extracted resonance data, extracted static deflection and tip clearance data, and correlation between the turbomachine operating conditions and the TOA data; and iteratively extracting updated TOA data and performing the correlating, the extracting of the resonance data, static deflection and tip clearance data using the updated TOA data at the defined interval to create an updated baseline compressor blade comparison level.

Abstract translation: 一种系统，包括：至少一个计算装置，被配置为通过以下定义的间隔提取关于压缩机叶片的到达时间（TOA）数据来监测涡轮机中的压缩机叶片; 将涡轮机操作条件与TOA数据相关联; 在涡轮机的启动或关闭期间提取关于压缩机叶片的共振数据，以及在涡轮机的稳态操作期间提取关于压缩机叶片的静态偏转和顶端间隙数据; 基于提取的共振数据，提取的静态偏转和叶尖间隙数据以及涡轮机操作条件和TOA数据之间的相关性来创建基准压缩机叶片比较水平; 并且迭代地提取更新的TOA数据并且以所定义的间隔执行关联，提取共振数据，静态偏转和提前间隙数据，以创建更新的基准压缩机叶片比较水平。