Acoustic monitoring of machinery

• US 10,345,800 B2
• Filed: 12/19/2016
• Issued: 07/09/2019
• Est. Priority Date: 03/30/2016
• Status: Active Grant

• Current Assignee: 3D Signals Ltd.
• Original Assignee: 3D Signals Ltd.
• Inventors: Lavi, Yair, Ashkenazi, Amit, Affias, Ofer, Shenfeld, Amnon
• Primary Examiner(s): Ali, Mohammad
• Assistant Examiner(s): Sanders, Joshua T
• Application Number:
  US15/382,765
• Publication Number:
  US 20170285626A1
• Time in Patent Office: 932 Days
• Field of Search: 700 76
• CPC Class Codes: G01H 3/04 Frequency
• CPC Class Codes: G01M 13/028 Acoustic or vibration analysis
• CPC Class Codes: G01M 15/12 by monitoring vibrations
• CPC Class Codes: G01N 2291/0258 Structural degradation, e.g. fatigue of composites, ageing of oils
• CPC Class Codes: G01N 2291/2696 Wheels, Gears, Bearings
• CPC Class Codes: G01N 29/12 by measuring frequency or resonance of acoustic waves measuring frequency or resonant frequency of mechanical vibrations or acoustic waves in general G01H1/06, G01H3/04, G01H13/00; acoustic resonators G10K11/04; vibration or shock testing of structures G01M7/00
• CPC Class Codes: G01N 29/14 using acoustic emission techniques echo of particles G01N29/046; measuring mechanical vibrations or acoustic waves in solids in general G01H1/00
• CPC Class Codes: G01N 29/32 Arrangements for suppressing undesired influences, e.g. temperature or pressure variations , compensating for signal noise
• CPC Class Codes: G01N 29/4454 Signal recognition, e.g. specific values or portions, signal events, signatures
• CPC Class Codes: G01N 29/449 Statistical methods not provided for in G01N29/4409, e.g. averaging, smoothing and interpolation
• CPC Class Codes: G01N 29/46 by spectral analysis, e.g. Fourier analysis or wavelet analysis spectral signal processing per se G06F17/14
• CPC Class Codes: G05B 2219/37337 Noise, acoustic emission, sound
• CPC Class Codes: G05B 2219/42271 Monitor parameters, conditions servo for maintenance, lubrication, repair purposes
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
• CPC Class Codes: G05B 23/0289 Reconfiguration to prevent failure, e.g. usually as a reaction to incipient failure detection

Abstract

Monitoring of a machine is performed by an acoustic monitor which acquires, through an acoustic sensor, acoustic signals from a vicinity of a machine, while the machine is operative. A processor calculates a frequency spectrum of a segment of the acquired acoustic signals, determines boundaries of a frequency band to be analyzed and extracts, from the calculated frequency spectrum, a base frequency window in the determined boundaries, and one or more harmonics windows of harmonics of the determined boundaries. For each of the base and harmonic windows a weight based on a distribution of values of frequencies in the windows is determined and a parameter of operation of the machine is calculated as a function of a weighted sum of the base and harmonic windows. The operation of the machine is evaluated responsive to the calculated parameter.

Claims

1. A method of monitoring a machine, comprising:

acquiring, by an acoustic sensor, acoustic signals from a vicinity of a machine, while the machine is operative;

calculating, by a processor, a frequency spectrum of a segment of the acquired acoustic signals;

determining boundaries of a frequency band to be analyzed;

extracting, from the calculated frequency spectrum, a base frequency window in the determined boundaries, and one or more harmonics windows of harmonics of the determined boundaries;

determining for each of the base and harmonic windows a weight based on a distribution of values of frequencies in the windows;

calculating a parameter of operation of the machine as a function of a weighted sum of the base and harmonic windows; and

providing feedback on the operation of the machine, responsive to the calculated parameter, on a display coupled to the processor.

2. The method of claim 1, comprising generating an alert, responsive to a determination that the calculated parameter is outside a predefined range of values for the parameter.

3. The method of claim 1, comprising generating an alert, responsive to a determination that the calculated parameter is different than a corresponding value reported by a controller of the machine.

4. The method of claim 1, wherein calculating the operation parameter comprises determining a frequency in the weighted sum of the windows having a maximal power.

5. The method of claim 1, wherein calculating the operation parameter comprises determining a ratio between power in a segment around a given frequency in the weighted sum of the windows and a measure of power outside the segment.

6. The method of claim 1, wherein determining a weight for each window comprises determining a frequency-domain entropy of the window.

7. The method of claim 1, wherein further comprising determining a time until a required maintenance of the machine, as a function of the calculated parameter.

8. The method of claim 1, further comprising automatically changing an operation state of the machine responsive to the calculated parameter.

9. The method of claim 5, wherein determining the ratio comprises calculating a numerator of the ratio as a power in frequency segments around an operation frequency of the machine and one or more harmonics of the operation frequency.

10. The method of claim 9, wherein the operation frequency comprises a frequency corresponding to a time period of a single cog of a gear of the machine.

11. The method of claim 10, wherein providing the feedback comprises automatically providing an estimate of a time to a required replacement of the gear.

12. The method of claim 9, wherein the operation frequency comprises a frequency corresponding to an entire cycle of a gear of the machine.

13. The method of claim 12, wherein providing the feedback comprises determining that the ratio is in a predetermined range and providing an alert of a broken gear cog responsively to the determining.

14. The method of claim 5, wherein determining the ratio comprises calculating a denominator of the ratio as a power of the entire frequency spectrum.

15. The method of claim 5, wherein determining the ratio comprises calculating a denominator of the ratio as a power of the frequency spectrum not included in the segments.

16. The method of claim 5, wherein calculating the frequency spectrum comprises extracting a sample of a given duration from the acquired signals and calculating the frequency spectrum from the extracted sample.

17. The method of claim 16, wherein extracting the sample comprises extracting at times defined by an electrical timing signal from the machine.

18. An acoustic machine monitor, comprising:

an acoustic sensor for acquiring acoustic signals from a vicinity of a machine, while the machine is operative; and

a processor configured to calculate a frequency spectrum of a segment of the acquired acoustic signals, to determine boundaries of a frequency band to be analyzed, to extract from the calculated frequency spectrum, a base frequency window in the determined boundaries, and one or more harmonics windows of harmonics of the determined boundaries, to determine for each of the base and harmonic windows a weight based on a distribution of values of frequencies in the windows, to calculate a parameter of operation of the machine as a function of a weighted sum of the base and harmonic windows, and to provide feedback on the operation of the machine, responsive to the calculated parameter.

19. The monitor of claim 18, wherein the processor is configured to generate an alert, responsive to a determination that the calculated parameter is outside a predefined range of values for the parameter.