In accordance with an implementation of the present technique, a method for processing data is disclosed. The method involves analyzing consistency of sensor readings obtained from a plurality of sensors monitoring a device, where each sensor reading is indicative of at least one operational paramet
In accordance with an implementation of the present technique, a method for processing data is disclosed. The method involves analyzing consistency of sensor readings obtained from a plurality of sensors monitoring a device, where each sensor reading is indicative of at least one operational parameter of the device. The method also involves assigning a confidence value to each of the sensor readings, where the confidence value is indicative of an operational condition of one of the plurality of sensors that provided the sensor reading. The method also includes weighting each sensor reading based on the confidence value assigned to the sensor reading to determine an acceptance or a rejection of the sensor reading and fusing the sensor readings that are accepted to obtain a fused sensor reading corresponding to the operational parameter measured by the sensors on the device.
대표청구항▼
The invention claimed is: 1. A method of controlling at least one operational characteristic of a device, the method comprising: analyzing consistency of a plurality of sensor readings obtained from a plurality of sensors monitoring the device, wherein each of the sensor readings is indicative of t
The invention claimed is: 1. A method of controlling at least one operational characteristic of a device, the method comprising: analyzing consistency of a plurality of sensor readings obtained from a plurality of sensors monitoring the device, wherein each of the sensor readings is indicative of the at least one operational parameter of the device; assigning a confidence value to each of the sensor readings, wherein the confidence value is indicative of an operational condition of one of the plurality of sensors that provided the sensor reading; weighting each of the sensor readings based on the confidence value assigned to the sensor reading to determine an acceptance or a rejection of the sensor reading; fusing the sensor readings that are accepted to obtain a fused sensor reading corresponding to the operational parameter measured by the sensors on the device; and controlling the at least one operational characteristic based on the fused sensor reading. 2. The method of claim 1, wherein analyzing the consistency of the plurality of sensor readings comprises analyzing a noise-level, a dynamic consistency or a value consistency for each of the sensor readings. 3. The method of claim 2, further comprising building a covariance matrix of the plurality of sensor readings for analyzing the dynamic consistency of each of the sensor readings based on deviation of an eigenvector of each of the sensor readings from each other, wherein the eigenvectors are determined via a principal component analysis of the covariance matrix. 4. The method of claim 3, wherein the covariance matrix is based on at least two auto covariances of the sensor readings or two cross covariances of the sensor readings. 5. The method of claim 2, further comprising evaluating a correlation of divergence of the sensor readings that have a substantially equivalent value consistency. 6. The method of claim 1, further comprising determining an auto-covariance of each of the sensor readings prior to assigning a noiselessness confidence value for each of the sensor readings. 7. The method of claim 1, wherein monitoring the device comprises monitoring an inlet temperature, an outlet temperature, an inlet pressure, an outlet pressure, a device temperature, a device vibration, a fuel consumption, a fuel level, or combinations thereof. 8. The method of claim 1, further comprising detecting a spike in each of the sensor readings to enable detection of a faulty sensor. 9. The method of claim 8, comprising isolating the faulty sensor based on a prediction model. 10. A sensor system, comprising: a plurality of sensors adapted to provide a plurality of sensor readings, wherein each of the sensor readings is indicative of an operational parameter of a device; a calculation module adapted to calculate a covariance of the sensor reading or a correlation of divergence of at least two of the sensor readings; an analysis module configured to assign a confidence value to the sensor reading or to determine a dynamic consistency of the sensor reading; and a fusion module configured to determine a reliable sensor reading based on at least a weighting of the sensor reading based on the confidence value assigned to the sensor reading or the dynamic consistency of the sensor reading. 11. The sensor system of claim 10, further comprising a fault detection and isolation module configured to detect and isolate failed sensors from the plurality of sensors, wherein any sensor reading assigned a confidence value of zero is isolated and wherein any sensor reading inconsistent with the rest of the sensor readings is isolated. 12. The sensor system of claim 10, wherein the analysis module comprises a noise analyzer, a value consistency analyzer or a dynamic consistency analyzer. 13. The sensor system of claim 10, wherein the analysis module is configured to detect a spiking in the sensor reading and identify a faulty sensor based upon the spiking. 14. The sensor system of claim 13, wherein the spiking is detected based on correlation of divergence of any two of the sensor readings. 15. The sensor system of claim 13, wherein the spiking is isolated based on the covariance of each of the sensor reading. 16. The sensor system of claim 15, wherein the auto-correlation is indicative of a drift in the any two of the sensor readings. 17. The sensor system of claim 16, wherein a drifting sensor is isolated based on a prediction model. 18. The sensor system of claim 16, wherein the analysis module assigns the confidence value to each of the data values based upon the drift. 19. The sensor system of claim 10, wherein the correlation of divergence of any two of the sensor readings is determined via an auto-correlation. 20. A system, comprising: an industrial device; a plurality of sensors configured to provide sensor readings, wherein each sensor reading is indicative of an operational parameter of the industrial device; a calculation module configured to calculate a covariance of at least two of the sensor readings or a correlation of divergence of at least two of the sensor readings; an analysis module configured to assign a confidence value to each of the sensor readings or to determine a dynamic consistency of each of the sensor readings; and a fusion module configured to determine a reliable sensor reading based on at least a weighting of the sensor readings based on the confidence value for each of the sensor readings or the dynamic consistency of each of the sensor readings. 21. The system of claim 20, wherein the industrial device comprises a gas turbine, a steam turbine, a water turbine, a fuel cell, or a wind turbine or a subcomponent thereof. 22. The system of claim 20, further comprising a fault isolation module configured to detect and isolate failed sensors from the plurality of sensors, wherein the sensor readings assigned a confidence value of zero are isolated and wherein any sensor reading inconsistent with the rest of the sensor readings is isolated. 23. The system of claim 20, wherein the analysis module comprises a noise analyzer, a value consistency analyzer or a dynamic consistency analyzer. 24. The system of claim 20, wherein the operational parameters comprise an inlet temperature, an outlet temperature, an inlet pressure, an outlet pressure, a device temperature, a device vibration, a fuel consumption, a fuel level, or combinations thereof.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (9)
Gibbs Bruce P. ; Porter David W. ; Yancey William E., Apparatus and method for fusing diverse data.
Maren Alianna J. ; Akita Richard M. ; Colbert Bradley D. ; Donovan David J. ; Glover Charles W. ; Mathia Karl ; Pap Robert M. ; Priddy Kevin L. ; Robinson Timothy W. ; Saeks Richard E., Sensor fusion apparatus and method.
Qiu, Hai; Iyer, Naresh Sundaram; Yan, Weizhong, Starter control valve failure prediction machine to predict and trend starter control valve failures in gas turbine engines using a starter control valve health prognostic, program product and related methods.
Donovan, John J; Hussain, Daniar, Systems and methods for correlating data from IP sensor networks for security, safety, and business productivity applications.
Donovan, John J; Hussain, Daniar, Systems and methods for correlating sensory events and legacy system events utilizing a correlation engine for security, safety, and business productivity.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.