SYSTEM AND METHOD FOR DETERMINING HEALTH INDICATORS FOR IMPELLERS

• US 20100256953A1
• Filed: 04/02/2009
• Published: 10/07/2010
• Est. Priority Date: 04/02/2009
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Kar, Chinmaya
• Granted Patent: US 8,620,622 B2
• Time in Patent Office: Days
• US Class Current: 702/185
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
• CPC Class Codes: G05B 23/0229 knowledge based, e.g. expert systems; genetic algorithms

Abstract

A system includes a plurality of sensors configured to measure one or more characteristics of an impeller. The system also includes an impeller condition indicator device, which includes a plurality of sensor interfaces configured to receive input signals associated with at least one stage of the impeller from the sensors. The impeller condition indicator device also includes a processor configured to identify a fault in the impeller using the input signals and an output interface configured to provide an indicator identifying the fault. The processor is configured to identify the fault by determining a family of frequencies related to at least one failure mode of the impeller, decomposing the input signals using the family of frequencies, reconstructing a impeller signal using the decomposed input signals, and comparing the reconstructed impeller signal to a baseline signal. The family of frequencies includes a vane pass frequency and its harmonics.

Claims

1. An apparatus comprising:

an input interface configured to receive an input signal associated with at least one stage of an impeller;

a processor configured to identify a fault in the impeller using the input signal; and

an output interface configured to provide an indicator identifying the fault;

wherein the processor is configured to identify the fault by;

determining a family of frequencies related to at least one failure mode of the impeller, the family of frequencies including a vane pass frequency and its harmonics;

decomposing the input signal using the family of frequencies;

reconstructing an impeller signal using the decomposed input signal; and

comparing the reconstructed impeller signal to a baseline signal.

2. The apparatus of claim 1, wherein the reconstructed impeller signal comprises at least one of:

a signal associated with the vane pass frequency and its harmonics;

a signal associated with a rotating shaft of the impeller;

a signal associated with shaft sidebands; and

a signal associated with background noise.

3. The apparatus of claim 1, wherein the processor is configured to deconstruct the input signal by decomposing the input signal through a plurality of band-pass filters.

4. The apparatus of claim 3, wherein the processor is configured to reconstruct the impeller signal by:

determining maximum and minimum frequencies and amplitudes in outputs of the band-pass filters;

uniting the maximum frequencies and amplitudes to produce a first union;

uniting the minimum frequencies and amplitudes to produce a second union; and

reconstructing multiple impeller signals using the first and second unions.

5. The apparatus of claim 1, wherein the processor further is configured to:

normalize the reconstructed signal with the baseline signal; and

apply a feature fusion technique to obtain a value for use by the indicator.

6. The apparatus of claim 1, wherein the processor is further configured to store a portion of the input signal, corresponding to normal operation of the impeller, as the baseline signal.

7. The apparatus of claim 1, wherein the indicator identifying the fault comprises at least one of:

an impeller wear indicator, an impeller crack indicator, a cavitation indicator, and an impeller health indicator.

8. The apparatus of claim 1, wherein:

the input signal comprises at least one of;

vibration information and speed information associated with the impeller;

the input interface comprises multiple input interfaces; and

the processor comprises an artificial intelligence portion.

9. A system comprising:

a plurality of sensors configured to measure one or more characteristics of an impeller; and

an impeller condition indicator device comprising;

an input interface configured to receive input signals associated with at least one stage of the impeller from the sensors;

a processor configured to identify a fault in the impeller using the input signals; and

an output interface configured to provide an indicator identifying the fault;

wherein the processor is configured to identify the fault by;

determining a family of frequencies related to at least one failure mode of the impeller, the family of frequencies including a vane pass frequency and its harmonics;

decomposing the input signals using the family of frequencies;

reconstructing an impeller signal using the decomposed input signals; and

comparing the reconstructed impeller signal to a baseline signal.

10. The system of claim 9, wherein the reconstructed impeller signal comprises at least one of:

a signal associated with the vane pass frequency and its harmonics;

a signal associated with a rotating shaft of the impeller;

a signal associated with shaft sidebands; and

a signal associated with background noise.

11. The system of claim 9, wherein the processor is configured to deconstruct the input signals by decomposing the input signals through a plurality of band-pass filters.

12. The system of claim 11, wherein the processor is configured to reconstruct the impeller signal by:

determining maximum and minimum frequencies and amplitudes in outputs of the band-pass filters;

uniting the maximum frequencies and amplitudes to produce a first union;

uniting the minimum frequencies and amplitudes to produce a second union; and

reconstructing multiple impeller signals using the first and second union.

13. The system of claim 9, wherein the processor is further configured to store a portion of the input signals, corresponding to normal operation of the impeller, as the baseline signal.

14. The system of claim 9, wherein the indicator identifying the fault comprises at least one of:

an impeller wear indicator, an impeller crack indicator, a cavitation indicator, and an impeller health indicator.

15. A method comprising:

receiving an input signal comprising at least one of vibration and speed information corresponding to at least one stage of an impeller;

determining a family of frequencies corresponding to at least one failure mode of the impeller, the family of frequencies including a vane pass frequency and its harmonics;

decomposing the input signal using the family of frequencies;

reconstructing an impeller signal using the decomposed input signal;

comparing the reconstructed impeller signal to a baseline signal; and

outputting an indicator identifying a fault when the reconstructed impeller signal differs from the baseline signal by a threshold amount.

16. The method of claim 15, wherein the reconstructed impeller signal comprises at least one of:

a signal associated with the vane pass frequency and its harmonics;

a signal associated with a rotating shaft of the impeller;

a signal associated with shaft sidebands; and

a signal associated with background noise.

17. The method of claim 15, wherein deconstructing the input signal comprises decomposing the input signal through plurality of band-pass filters;

and

wherein reconstructing the impeller signal comprises;

determining maximum and minimum frequencies and amplitudes in outputs of the band-pass filters;

uniting the maximum frequencies and amplitudes to produce a first union;

uniting the minimum frequencies and amplitudes to produce a second union; and

reconstructing multiple impeller signals using the first and second union.

18. The method of claim 15, further comprising:

normalizing the reconstructed signal with the baseline signal; and

applying a feature fusion technique to obtain a value for use by the indicator.

19. The method of claim 15, further comprising:

storing a portion of the vibration and speed information corresponding to normal operation of the impeller as the baseline signal.

20. The method of claim 15, wherein the threshold amount comprises a first amount associated with a warning threshold and a second amount associated with an alarm threshold.