Apparatus and method for monitoring a device having a movable part

• US 10,725,439 B2
• Filed: 12/02/2014
• Issued: 07/28/2020
• Est. Priority Date: 12/02/2014
• Status: Active Grant

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Kozionov, Alexey Petrovich, Mangutov, Oleg Vladimirovich, Mokhov, Ilya Igorevich
• Primary Examiner(s): Yi, Roy Y
• Application Number:
  US15/531,800
• Publication Number:
  US 20170315516A1
• Time in Patent Office: 2,065 Days
• Field of Search: None
• CPC Class Codes: G01H 1/003 of rotating machines G01H1/10 takes precedence
• CPC Class Codes: G01M 13/045 Acoustic or vibration analysis
• CPC Class Codes: G05B 13/0285 using neural networks and fuzzy logic
• CPC Class Codes: G05B 23/0229 knowledge based, e.g. expert systems; genetic algorithms
• CPC Class Codes: G05B 23/0235 based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold
• CPC Class Codes: G05D 19/02 characterised by the use of electric means
• CPC Class Codes: G06F 17/142 Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04

Abstract

An apparatus for monitoring of a device including a moveable part, especially a rotating device, wherein the apparatus includes a control module which receives a measured vibration signal of the device provided by a sensor connected to the device, provides a spectrum of the measured vibration signal, pre-processes the spectrum to determine base frequencies and side frequencies, where the base frequencies are frequencies having peak powers corresponding to eigen frequencies of the device or faulty frequencies and the side frequencies correspond to other frequencies, where the control module additionally processes the base and side frequencies by applying separately a one-class classification on the base and side frequencies, combines the results of the one-class classifications to obtain a classification signal representing a confidence level, and outputs a decision support signal based on the classification signal, where the decision support signal indicates an error status of the monitored device.

Claims

1. An apparatus for monitoring a device having a moveable part, the apparatus comprising:

a control module configured to;

receive a measured vibration signal of the device provided by a sensor operatively connected to the device;

provide a spectrum of the measured vibration signal;

pre-process the spectrum to determine base frequencies and side frequencies, base frequencies comprising frequencies having peak powers corresponding to one of (i) eigen frequencies of the device and (ii) faulty frequencies, and side frequencies corresponding to other frequencies,

process the base frequencies and the side frequencies by applying separately a one-class classification on the base frequencies and side frequencies,

combine results of the one-class classifications to obtain a classification signal which represents a confidence level, and

output a decision support signal to a display of a computer based on the classification signal, said decision support signal indicating to a user an error status of the monitored device.

2. The apparatus according to claim 1, wherein the control module is further configured to reduce a noise level of the vibration transform during pre-processing.

3. The apparatus according to claim 1, wherein the control module is further configured to apply a threshold value on the vibration transform during preprocessing.

4. The apparatus according to claim 2, wherein the control module is further configured to apply a threshold value on the vibration transform during preprocessing.

5. The apparatus according to claim 1, wherein the control module is further configured to determine separately a sum of a power of the base frequencies and the side frequencies, respectively.

6. The apparatus according to claim 2, wherein the control module is further configured to determine separately a sum of a power of the base frequencies and the side frequencies, respectively.

7. The apparatus according to claim 3, wherein the control module is further configured to determine separately a sum of a power of the base frequencies and the side frequencies, respectively.

8. The apparatus according to claim 1, wherein the control module is further configured to consider dependence between the base frequencies and the side frequencies during processing.

9. The apparatus according to claim 1, wherein the control module comprises neural clouds for providing one-class classification.

10. The apparatus according to claim 9, characterized in that the control module is configured to train one-class classification based on data received from the vibration signal during error-free operation.

11. The apparatus according to claim 1, wherein the control module is further configured to utilize a support vector machine to provide one-class classification.

12. The apparatus according to claim 1, wherein the device comprises a rotating device.

13. A method for monitoring a device having a moveable part, the method comprising:

receiving a measured vibration signal of the device from a sensor operatively connected to the device;

providing a spectrum of the measured vibration signal;

pre-processing the spectrum to determine base frequencies and side frequencies, base frequencies comprising frequencies having peak powers corresponding to one of (i) eigen frequencies of the device and (ii) faulty frequencies, and side frequencies corresponding to other frequencies;

processing the base frequencies and the side frequencies by applying separately a one-class classification on the base frequencies and the side frequencies;

combining results of the one-class classifications to obtain a classification signal representing a confidence level; and

outputting a decision support signal to a display of a computer based on the classification signal, said decision support signal indicating to a user an error status of the monitored device.

14. The method according to claim 13, wherein the device comprises a rotating device.

15. A non-transitory computer-readable medium including a program executing on a processing device and comprising software code portions of a program which, when executed on the processing device, causes monitoring of a device having a moveable part, the program comprising:

software code for receiving a measured vibration signal of the device from a sensor operatively connected to the device;

software code for providing a spectrum of the measured vibration signal;

software code for pre-processing the spectrum to determine base frequencies and side frequencies, base frequencies comprising frequencies having peak power corresponding to one of (i) eigen frequencies of the device and (ii) faulty frequencies, and side frequencies corresponding to other frequencies;

software code for processing the base frequencies and the side frequencies by applying separately a one-class classification on the base frequencies and the side frequencies;

software code for combining results of the one-class classifications to obtain a classification signal representing a confidence level; and

software code for outputting a decision support signal to a display of a computer based on the classification signal, said decision support signal indicating to a user an error status of the monitored device.