General Electric Company

Devang Jagdish Gandhi

Xiaomo Jiang

Christopher Schreiner

Vivek Shah

Sanjeev Shyam Heda

Bradley Wile

Matthew Everett Moore

Shaddy Abado

Lijie Yu

Karen Warren Miller

Ilan Leibu

Xiaohui Hu

Kevin Clement Metz

James John D'Amato

Donald Scott Doan

Ketan Kalele

This disclosure relates to modeling and visualization of vibration mechanics in residual space, and includes systems and methods for vibrational analysis. In one embodiment, a method includes acquiring, by at least one sensor, vibrational data and an operational mode of rotating equipment. The method may then proceed with determining, by an equipment controller communicatively coupled to the sensor, at least one vibrational vector based on the vibrational data. The method may determine, by the equipment controller and based on a model, an expected vibrational vector for the operational mode. The method may calculate, by the equipment controller, a residual vector as a difference between the vibrational vector and the expected vector. The method may also determine, by the equipment controller, at least one abnormality associated with the rotating equipment based on the residual vector. The method may display a graph representing boundaries of a region of allotted residual vectors and a point representing the residual vector.

Modeling and visualization of vibration mechanics in residual space

A system is provided comprising a memory configured to store instructions and a processor configured to execute the instructions. The processor is configured to execute the instructions to receive sensor data comprising sensed operations for a machinery, the sensed operations sensed via one or more sensors disposed in the machinery, and to derive a first model matrix based on the sensor data. The processor is further configured to derive a covariance regression model based on the first model matrix, wherein the covariance regression model is configured to be executed to derive a predictive event based on operational machinery data as input.

System and method for issue detection of industrial processes

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.

System and method to enhance lean blowout monitoring

Streaming data at a sensor is sensed and received. The streaming data includes a plurality of observations. For a current observation in the plurality of observations, a health of the current observation is determined. Based upon the health of the current observation, a penalty is determined. A Sensor Health Index (SHI) for the current observation is obtained by aggregating the penalty with at least one SHI of one or more previous observations from the plurality of observations. An alarm is selectively generated based upon the SHI of the current observation.

Method and apparatus for determination of sensor health

Growing community of inventors

Atlanta, GA, United States of America

Devang Jagdish Gandhi