Systems and Methods for Sensor-Level Machine Monitoring

• US 20100085205A1
• Filed: 10/07/2008
• Published: 04/08/2010
• Est. Priority Date: 10/07/2008
• Status: Active Grant

• Current Assignee: Baker Hughes, a GE Company, LLC (Baker Hughes Company)
• Original Assignee: General Electric Company
• Inventors: Hall, Richard Herman, Tompkins, Marc Steven
• Granted Patent: US 8,049,637 B2
• Time in Patent Office: Days
• US Class Current: 340/682
• CPC Class Codes: G01M 13/04 Bearings
• CPC Class Codes: G01M 13/045 Acoustic or vibration analysis
• CPC Class Codes: G01M 15/05 by combined monitoring of two or more different engine parameters
• CPC Class Codes: G01M 15/12 by monitoring vibrations
• CPC Class Codes: G05B 23/0229 knowledge based, e.g. expert systems; genetic algorithms

Abstract

According embodiments of the invention, systems and methods for sensor-level machine monitoring are provided. In one example embodiment, there is disclosed a system for monitoring a machine. The system may include a first sensor including a first processor and a second sensor including a second processor. The system may further include a communication trunk in communication with the first sensor and the second sensor, and operable to communicate sensor data between each of the first processor and the second processor. The first sensor and the second sensor are operable to generate sensor data associated with at least one machine condition. Further, at least one of the first processor or the second processor is operable to analyze sensor data generated by each of the first sensor and the second sensor and determine at least one machine fault based at least in part on the sensor data.

Claims

1. A system for monitoring a machine, comprising:

a first sensor comprising a first processor;

a second sensor comprising a second processor; and

at least one communication trunk in communication with the first sensor and the second sensor, and operable to communicate sensor data between each of the first processor and the second processor;

wherein the first sensor and the second sensor are operable to generate sensor data associated with at least one machine condition; and

wherein at least one of the first processor or the second processor is operable to;

analyze sensor data generated by each of the first sensor and the second sensor; and

determine at least one machine fault based at least in part on the sensor data.

2. The system of claim 1, wherein at least one of the first processor of the second processor is further operable to generate a characterization of the sensor data generated by each of the first sensor and the second sensor.

3. The system of claim 2, wherein the characterization comprises at least one of:

a machine orbit shape, a machine full spectrum, a machine filtered spectrum, or a rotor position.

4. The system of claim 1, wherein the at least one machine fault comprises at least one of:

machine imbalance, machine misalignment, machine bearing failure, machine bearing instability, machine thrust bearing failure, machine rub, shaft imbalance, shaft crack, machine mounting anomaly, fluid induced instability, air gap excursion, shorted rotor bar, loose rotor bar, axial float/magnetic-center excursion, or phasing anomaly.

5. The system of claim 1, wherein the machine comprises a rotating machine and wherein the first sensor and the second sensor comprise a pair of vibration sensors positioned in distinct planes with respect to each other.

6. The system of claim 1, wherein the first sensor and the second sensor each comprise a smart digital sensor.

7. The system of claim 1, wherein at least one of the first sensor or the second sensor comprise at least one of a vibration sensor, a temperature sensor, a pressure sensor, a position sensor, an accelerometer, a flow sensor, a level sensor, a density sensor, a material composition sensor, or an electrical power characterization sensor.

8. The system of claim 1, wherein at least one of the first processor or the second processor is further operable to perform at least one of a frequency domain analysis, a time domain analysis, or a filtered frequency analysis on the sensor data generated by each of the first sensor and the second sensor.

9. The system of claim 1, wherein at least one of the first processor or the second processor is further operable to communicate the at least one machine fault to at least one of a host system or a host controller.

10. The system of claim 9, wherein the host system or host controller is operable to facilitate at least one control action based at least in part on the at least one machine fault.

11. The system of claim 1, wherein both of the first processor and the second processor are operable to analyze the at least one machine condition and determine the at least one machine fault.

12. The system of claim 1, wherein at least one of the first processor or the second processor are operable to communicate at least one control action from the first processor or the second processor to at least one field device associated with the machine.

13. A method for monitoring a machine, comprising:

providing a plurality of sensors, each comprising a processor comprising instructions;

providing at least one communication trunk in communication with the plurality of sensors, and operable to communicate sensor data between each of the plurality of sensors;

sensing, by each of the plurality of sensors, at least one machine condition;

generating, by each of the plurality of sensors, sensor data associated with the at least one machine condition; and

executing the instructions in at least one processor of the plurality of sensors to;

analyze the sensor data generated by each of the plurality of sensors; and

determine at least one machine fault based at least in part on the at least one sensor data.

14. The method of claim 13, further comprising executing the instructions in at least one processor of the plurality of sensors to generate a characterization of the sensor data generated by each of the plurality of sensors.

15. The method of claim 14, wherein the characterization comprises at least one of:

a machine orbit shape, a machine full spectrum, a machine filtered spectrum, or a rotor position.

16. The method of claim 13, wherein executing the instructions to determine the at least one machine fault further comprises determining at least one of:

machine imbalance, machine misalignment, machine bearing failure, machine bearing instability, machine thrust bearing failure, machine rub, shaft imbalance, shaft crack, machine mounting anomaly, fluid induced instability, air gap excursion, shorted rotor bar, loose rotor bar, axial float/magnetic-center excursion, or phasing anomaly.

17. The method of claim 13, wherein executing the instructions to analyze the at least one machine condition further comprises performing at least one of a frequency domain analysis, a time domain analysis, or a filtered frequency analysis on the sensor data generated by each of the plurality of sensors.

18. The method of claim 13, further comprising:

communicating the at least one machine fault to at least one of a host system or a host controller; and

generating, by the host system or host controller, at least one control action based at least in part on the at least one machine fault.

19. The method of claim 13, further comprising:

generating by at least one of the first processor or the second processor at least one control action responsive to determining the at least one machine fault; and

communicating the at least one control action from the first processor or the second processor to at least one field device associated with the machine.

20. A system for monitoring a machine, comprising:

a plurality of sensors, each comprising a processor;

at least one communication trunk in communication with the plurality of sensors operable to communicate sensor data between each of the plurality of processors;

wherein each of the plurality of sensors is operable to detect at least one machine condition;

wherein at least one sensor of the plurality of sensors is operable to receive an indication associated with detection of the at least one machine condition from at least one other of the plurality of sensors;

wherein the processor of the at least one sensor comprises is operable to;

aggregate any of the received indications;

perform at least one of a frequency domain analysis, a time domain analysis, or a filtered frequency analysis on the aggregated indications;

characterize the at least one machine condition based at least in part on the aggregated indications; and

determine at least one machine fault based at least in part on the aggregated indications.